diff --git a/README.md b/README.md
index 0d1ed677..a38b06b5 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,52 @@
+### Change log [2025-12-31 07:49:10]
+1. New item created: `verify_schema` (version: `1.0.0`)
+
+### Change log [2025-12-31 07:49:05]
+1. Item Updated: `agent_deployer` (from version: `1.0.0` to `1.0.0`)
+2. Item Updated: `histogram_data_drift` (from version: `1.0.0` to `1.0.0`)
+3. Item Updated: `openai_proxy_app` (from version: `1.0.0` to `1.0.0`)
+4. New item created: `vllm_module` (version: `1.0.0`)
+5. Item Updated: `count_events` (from version: `1.0.0` to `1.0.0`)
+6. Item Updated: `evidently_iris` (from version: `1.0.0` to `1.0.0`)
+
+### Change log [2025-12-31 07:48:55]
+1. Item Updated: `test_classifier` (from version: `1.1.0` to `1.1.0`)
+2. Item Updated: `sklearn_classifier` (from version: `1.2.0` to `1.2.0`)
+3. Item Updated: `model_server_tester` (from version: `1.1.0` to `1.1.0`)
+4. Item Updated: `azureml_serving` (from version: `1.1.0` to `1.1.0`)
+5. Item Updated: `describe_dask` (from version: `1.2.0` to `1.2.0`)
+6. Item Updated: `batch_inference` (from version: `1.8.0` to `1.8.0`)
+7. Item Updated: `v2_model_server` (from version: `1.2.0` to `1.2.0`)
+8. Item Updated: `gen_class_data` (from version: `1.3.0` to `1.3.0`)
+9. Item Updated: `send_email` (from version: `1.2.0` to `1.2.0`)
+10. Item Updated: `tf2_serving` (from version: `1.1.0` to `1.1.0`)
+11. Item Updated: `aggregate` (from version: `1.4.0` to `1.4.0`)
+12. Item Updated: `open_archive` (from version: `1.2.0` to `1.2.0`)
+13. Item Updated: `describe` (from version: `1.4.0` to `1.4.0`)
+14. Item Updated: `v2_model_tester` (from version: `1.1.0` to `1.1.0`)
+15. Item Updated: `text_to_audio_generator` (from version: `1.3.0` to `1.3.0`)
+16. Item Updated: `pii_recognizer` (from version: `0.4.0` to `0.4.0`)
+17. Item Updated: `github_utils` (from version: `1.1.0` to `1.1.0`)
+18. Item Updated: `sklearn_classifier_dask` (from version: `1.1.1` to `1.1.1`)
+19. Item Updated: `azureml_utils` (from version: `1.4.0` to `1.4.0`)
+20. Item Updated: `question_answering` (from version: `0.5.0` to `0.5.0`)
+21. Item Updated: `structured_data_generator` (from version: `1.6.0` to `1.6.0`)
+22. Item Updated: `arc_to_parquet` (from version: `1.5.0` to `1.5.0`)
+23. Item Updated: `silero_vad` (from version: `1.4.0` to `1.4.0`)
+24. Item Updated: `load_dataset` (from version: `1.2.0` to `1.2.0`)
+25. Item Updated: `auto_trainer` (from version: `1.8.0` to `1.8.0`)
+26. Item Updated: `feature_selection` (from version: `1.6.0` to `1.6.0`)
+27. Item Updated: `translate` (from version: `0.3.0` to `0.3.0`)
+28. Item Updated: `describe_spark` (from version: `1.1.0` to `1.1.0`)
+29. Item Updated: `pyannote_audio` (from version: `1.3.0` to `1.3.0`)
+30. Item Updated: `onnx_utils` (from version: `1.3.0` to `1.3.0`)
+31. Item Updated: `batch_inference_v2` (from version: `2.6.0` to `2.6.0`)
+32. Item Updated: `transcribe` (from version: `1.2.0` to `1.2.0`)
+33. Item Updated: `model_server` (from version: `1.2.0` to `1.2.0`)
+34. Item Updated: `mlflow_utils` (from version: `1.1.0` to `1.1.0`)
+35. Item Updated: `noise_reduction` (from version: `1.1.0` to `1.1.0`)
+36. Item Updated: `hugging_face_serving` (from version: `1.1.0` to `1.1.0`)
+
 ### Change log [2025-12-28 14:17:26]
 1. Item Updated: `agent_deployer` (from version: `1.0.0` to `1.0.0`)
 2. Item Updated: `histogram_data_drift` (from version: `1.0.0` to `1.0.0`)
diff --git a/catalog.json b/catalog.json
index 19d629ff..dd5cc72d 100644
--- a/catalog.json
+++ b/catalog.json
@@ -1 +1 @@
-{"functions": {"development": {"tf2_serving": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "tf2 image classification server", "doc": "", "example": "tf2_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "tf2-serving", "platformVersion": "3.5.0", "spec": {"filename": "tf2_serving.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": ["requests", "pillow", "tensorflow>=2.1"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "tf2 image classification server", "doc": "", "example": "tf2_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "tf2-serving", "platformVersion": "3.5.0", "spec": {"filename": "tf2_serving.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": ["requests", "pillow", "tensorflow>=2.1"]}, "url": "", "version": "1.1.0"}}, "load_dataset": {"latest": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "load a toy dataset from scikit-learn", "doc": "README.md", "example": "load_dataset.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.6.0", "name": "load-dataset", "platformVersion": "3.5.5", "spec": {"filename": "load_dataset.py", "handler": "load_dataset", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "load a toy dataset from scikit-learn", "doc": "README.md", "example": "load_dataset.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.6.0", "name": "load-dataset", "platformVersion": "3.5.5", "spec": {"filename": "load_dataset.py", "handler": "load_dataset", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "model_server_tester": {"latest": {"apiVersion": "v1", "categories": ["monitoring", "model-serving"], "description": "test model servers", "doc": "", "example": "model_server_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "model-server-tester", "platformVersion": "3.5.0", "spec": {"filename": "model_server_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["monitoring", "model-serving"], "description": "test model servers", "doc": "", "example": "model_server_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "model-server-tester", "platformVersion": "3.5.0", "spec": {"filename": "model_server_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "feature_selection": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "machine-learning"], "description": "Select features through multiple Statistical and Model filters", "doc": "", "example": "feature_selection.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc40", "name": "feature-selection", "platformVersion": "3.6.0", "spec": {"filename": "feature_selection.py", "handler": "feature_selection", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.6.0"}, "1.6.0": {"apiVersion": "v1", "categories": ["data-preparation", "machine-learning"], "description": "Select features through multiple Statistical and Model filters", "doc": "", "example": "feature_selection.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc40", "name": "feature-selection", "platformVersion": "3.6.0", "spec": {"filename": "feature_selection.py", "handler": "feature_selection", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.6.0"}}, "aggregate": {"latest": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "Rolling aggregation over Metrics and Lables according to specifications", "doc": "", "example": "aggregate.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "aggregate", "platformVersion": "3.5.4", "spec": {"filename": "aggregate.py", "handler": "aggregate", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "Rolling aggregation over Metrics and Lables according to specifications", "doc": "", "example": "aggregate.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "aggregate", "platformVersion": "3.5.4", "spec": {"filename": "aggregate.py", "handler": "aggregate", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}}, "describe": {"latest": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "describe and visualizes dataset stats", "doc": "", "example": "describe.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "describe", "platformVersion": "3.5.3", "spec": {"filename": "describe.py", "handler": "analyze", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "describe and visualizes dataset stats", "doc": "", "example": "describe.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "describe", "platformVersion": "3.5.3", "spec": {"filename": "describe.py", "handler": "analyze", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}}, "model_server": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "model-server", "platformVersion": "3.5.0", "spec": {"filename": "model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "model-server", "platformVersion": "3.5.0", "spec": {"filename": "model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": []}, "url": "", "version": "1.2.0"}}, "describe_spark": {"latest": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "", "doc": "", "example": "describe_spark.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "describe-spark", "platformVersion": "3.5.0", "spec": {"filename": "describe_spark.py", "handler": "describe_spark", "image": "iguazio/shell:3.0_b5565_20201026062233_wsdf", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "", "doc": "", "example": "describe_spark.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "describe-spark", "platformVersion": "3.5.0", "spec": {"filename": "describe_spark.py", "handler": "describe_spark", "image": "iguazio/shell:3.0_b5565_20201026062233_wsdf", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "gen_class_data": {"latest": {"apiVersion": "v1", "categories": ["data-generation"], "description": "Create a binary classification sample dataset and save.", "doc": "", "example": "gen_class_data.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "gen_class_data", "platformVersion": "3.5.3", "spec": {"filename": "gen_class_data.py", "handler": "gen_class_data", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["data-generation"], "description": "Create a binary classification sample dataset and save.", "doc": "", "example": "gen_class_data.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "gen_class_data", "platformVersion": "3.5.3", "spec": {"filename": "gen_class_data.py", "handler": "gen_class_data", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.3.0"}}, "open_archive": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "Open a file/object archive into a target directory", "doc": "", "example": "open_archive.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc50", "name": "open-archive", "platformVersion": "3.5.0", "spec": {"filename": "open_archive.py", "handler": "open_archive", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["utils"], "description": "Open a file/object archive into a target directory", "doc": "", "example": "open_archive.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc50", "name": "open-archive", "platformVersion": "3.5.0", "spec": {"filename": "open_archive.py", "handler": "open_archive", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "send_email": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "Send Email messages through SMTP server", "doc": "", "example": "send_email.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.4.1", "name": "send-email", "platformVersion": "3.5.3", "spec": {"filename": "send_email.py", "handler": "send_email", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["utils"], "description": "Send Email messages through SMTP server", "doc": "", "example": "send_email.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.4.1", "name": "send-email", "platformVersion": "3.5.3", "spec": {"filename": "send_email.py", "handler": "send_email", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "v2_model_tester": {"latest": {"apiVersion": "v1", "categories": ["model-testing", "machine-learning"], "description": "test v2 model servers", "doc": "", "example": "v2_model_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-tester", "platformVersion": "3.5.0", "spec": {"filename": "v2_model_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-testing", "machine-learning"], "description": "test v2 model servers", "doc": "", "example": "v2_model_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-tester", "platformVersion": "3.5.0", "spec": {"filename": "v2_model_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "arc_to_parquet": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "retrieve remote archive, open and save as parquet", "doc": "", "example": "arc_to_parquet.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "arc-to-parquet", "platformVersion": "3.5.4", "spec": {"filename": "arc_to_parquet.py", "handler": "arc_to_parquet", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.5.0"}, "1.5.0": {"apiVersion": "v1", "categories": ["utils"], "description": "retrieve remote archive, open and save as parquet", "doc": "", "example": "arc_to_parquet.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "arc-to-parquet", "platformVersion": "3.5.4", "spec": {"filename": "arc_to_parquet.py", "handler": "arc_to_parquet", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.5.0"}}, "github_utils": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "add comments to github pull request", "doc": "", "example": "github_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "github-utils", "platformVersion": "3.5.0", "spec": {"filename": "github_utils.py", "handler": "run_summary_comment", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["utils"], "description": "add comments to github pull request", "doc": "", "example": "github_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "github-utils", "platformVersion": "3.5.0", "spec": {"filename": "github_utils.py", "handler": "run_summary_comment", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "v2_model_server": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "v2_model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-server", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "ClassifierModel"}, "filename": "v2_model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "v2_model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-server", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "ClassifierModel"}, "filename": "v2_model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": []}, "url": "", "version": "1.2.0"}}, "onnx_utils": {"latest": {"apiVersion": "v1", "categories": ["utils", "deep-learning"], "description": "ONNX intigration in MLRun, some utils functions for the ONNX framework, optimizing and converting models from different framework to ONNX using MLRun.", "doc": "", "example": "onnx_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.2", "name": "onnx_utils", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "with_mlrun": false}}, "filename": "onnx_utils.py", "handler": "to_onnx", "image": "mlrun/mlrun", "kind": "job", "requirements": ["tqdm~=4.67.1", "tensorflow~=2.19.0", "tf_keras~=2.19.0", "torch~=2.6.0", "torchvision~=0.21.0", "onnx~=1.17.0", "onnxruntime~=1.19.2", "onnxoptimizer~=0.3.13", "onnxmltools~=1.13.0", "tf2onnx~=1.16.1", "plotly~=5.23"]}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["utils", "deep-learning"], "description": "ONNX intigration in MLRun, some utils functions for the ONNX framework, optimizing and converting models from different framework to ONNX using MLRun.", "doc": "", "example": "onnx_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.2", "name": "onnx_utils", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "with_mlrun": false}}, "filename": "onnx_utils.py", "handler": "to_onnx", "image": "mlrun/mlrun", "kind": "job", "requirements": ["tqdm~=4.67.1", "tensorflow~=2.19.0", "tf_keras~=2.19.0", "torch~=2.6.0", "torchvision~=0.21.0", "onnx~=1.17.0", "onnxruntime~=1.19.2", "onnxoptimizer~=0.3.13", "onnxmltools~=1.13.0", "tf2onnx~=1.16.1", "plotly~=5.23"]}, "url": "", "version": "1.3.0"}}, "azureml_utils": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Azure AutoML integration in MLRun, including utils functions for training models on Azure AutoML platfrom.", "doc": "", "example": "azureml_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "azureml_utils", "platformVersion": "3.5.3", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "commands": ["apt-get update && apt-get install -y --no-install-recommends git", "apt install -y liblttng-ust0"], "with_mlrun": true}}, "filename": "azureml_utils.py", "handler": "train", "image": "python:3.9-bullseye", "kind": "job", "requirements": ["azureml-core==1.54.0.post1", "azureml-train-automl-client==1.54.0.post1", "plotly~=5.23"]}, "url": "", "version": "1.4.0", "test_valid": true}, "1.4.0": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Azure AutoML integration in MLRun, including utils functions for training models on Azure AutoML platfrom.", "doc": "", "example": "azureml_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "azureml_utils", "platformVersion": "3.5.3", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "commands": ["apt-get update && apt-get install -y --no-install-recommends git", "apt install -y liblttng-ust0"], "with_mlrun": true}}, "filename": "azureml_utils.py", "handler": "train", "image": "python:3.9-bullseye", "kind": "job", "requirements": ["azureml-core==1.54.0.post1", "azureml-train-automl-client==1.54.0.post1", "plotly~=5.23"]}, "url": "", "version": "1.4.0", "test_valid": true}}, "auto_trainer": {"latest": {"apiVersion": "v1", "categories": ["machine-learning", "model-training"], "description": "Automatic train, evaluate and predict functions for the ML frameworks - Scikit-Learn, XGBoost and LightGBM.", "doc": "", "example": "auto_trainer.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "auto_trainer", "platformVersion": "3.5.0", "spec": {"filename": "auto_trainer.py", "handler": "train", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.8.0"}, "1.8.0": {"apiVersion": "v1", "categories": ["machine-learning", "model-training"], "description": "Automatic train, evaluate and predict functions for the ML frameworks - Scikit-Learn, XGBoost and LightGBM.", "doc": "", "example": "auto_trainer.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "auto_trainer", "platformVersion": "3.5.0", "spec": {"filename": "auto_trainer.py", "handler": "train", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.8.0"}}, "azureml_serving": {"latest": {"apiVersion": "v1", "categories": ["machine-learning", "model-serving"], "description": "AzureML serving function", "doc": "", "example": "azureml_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "azureml_serving", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "mlrun.frameworks.sklearn.PickleModelServer"}, "filename": "azureml_serving.py", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["azureml-automl-runtime~=1.38.1"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["machine-learning", "model-serving"], "description": "AzureML serving function", "doc": "", "example": "azureml_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "azureml_serving", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "mlrun.frameworks.sklearn.PickleModelServer"}, "filename": "azureml_serving.py", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["azureml-automl-runtime~=1.38.1"]}, "url": "", "version": "1.1.0"}}, "batch_inference": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "batch_inference", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference.py", "handler": "infer", "image": "mlrun/ml-models", "kind": "job", "requirements": null}, "url": "", "version": "1.8.0"}, "1.8.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "batch_inference", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference.py", "handler": "infer", "image": "mlrun/ml-models", "kind": "job", "requirements": null}, "url": "", "version": "1.8.0"}}, "hugging_face_serving": {"latest": {"apiVersion": "v1", "categories": ["genai", "model-serving"], "description": "Generic Hugging Face model server.", "doc": "", "example": "hugging_face_serving.ipynb", "generationDate": "2022-09-05:17-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "hugging_face_serving", "platformVersion": "", "spec": {"customFields": {"default_class": "HuggingFaceModelServer"}, "filename": "hugging_face_serving.py", "handler": "handler", "image": "mlrun/ml-models", "kind": "serving", "requirements": ["transformers==4.21.3", "tensorflow==2.9.2"]}, "url": "", "version": "1.1.0", "test_valid": false}, "1.1.0": {"apiVersion": "v1", "categories": ["genai", "model-serving"], "description": "Generic Hugging Face model server.", "doc": "", "example": "hugging_face_serving.ipynb", "generationDate": "2022-09-05:17-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "hugging_face_serving", "platformVersion": "", "spec": {"customFields": {"default_class": "HuggingFaceModelServer"}, "filename": "hugging_face_serving.py", "handler": "handler", "image": "mlrun/ml-models", "kind": "serving", "requirements": ["transformers==4.21.3", "tensorflow==2.9.2"]}, "url": "", "version": "1.1.0", "test_valid": false}}, "transcribe": {"latest": {"apiVersion": "v1", "categories": ["audio", "genai"], "description": "Transcribe audio files into text files", "doc": "", "example": "transcribe.ipynb", "generationDate": "2023-07-13:11-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "transcribe", "platformVersion": "3.5.3", "spec": {"filename": "transcribe.py", "handler": "transcribe", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "tqdm", "torchaudio", "torch", "accelerate"]}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["audio", "genai"], "description": "Transcribe audio files into text files", "doc": "", "example": "transcribe.ipynb", "generationDate": "2023-07-13:11-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "transcribe", "platformVersion": "3.5.3", "spec": {"filename": "transcribe.py", "handler": "transcribe", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "tqdm", "torchaudio", "torch", "accelerate"]}, "url": "", "version": "1.2.0"}}, "question_answering": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "GenAI approach of question answering on a given data", "doc": "", "example": "question_answering.ipynb", "generationDate": "2023-08-07:11-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "question_answering", "platformVersion": "3.5.0", "spec": {"filename": "question_answering.py", "handler": "answer_questions", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "torch", "tqdm"]}, "url": "", "version": "0.5.0"}, "0.5.0": {"apiVersion": "v1", "categories": ["genai"], "description": "GenAI approach of question answering on a given data", "doc": "", "example": "question_answering.ipynb", "generationDate": "2023-08-07:11-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "question_answering", "platformVersion": "3.5.0", "spec": {"filename": "question_answering.py", "handler": "answer_questions", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "torch", "tqdm"]}, "url": "", "version": "0.5.0"}}, "pii_recognizer": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "NLP"], "description": "This function is used to recognize PII in a directory of text files", "doc": "", "example": "pii_recognizer.ipynb", "generationDate": "2023-08-15:10-24", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pii-recognizer", "platformVersion": "3.5.3", "spec": {"filename": "pii_recognizer.py", "handler": "recognize_pii", "image": "mlrun/mlrun", "kind": "job", "requirements": ["nltk", "pandas", "presidio-anonymizer", "presidio-analyzer", "torch", "flair@git+https://github.com/flairNLP/flair.git@d4ed67bf663e4066517f00397412510d90043653", "st-annotated-text", "https://huggingface.co/beki/en_spacy_pii_distilbert/resolve/main/en_spacy_pii_distilbert-any-py3-none-any.whl"]}, "url": "", "version": "0.4.0", "test_valid": false}, "0.4.0": {"apiVersion": "v1", "categories": ["data-preparation", "NLP"], "description": "This function is used to recognize PII in a directory of text files", "doc": "", "example": "pii_recognizer.ipynb", "generationDate": "2023-08-15:10-24", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pii-recognizer", "platformVersion": "3.5.3", "spec": {"filename": "pii_recognizer.py", "handler": "recognize_pii", "image": "mlrun/mlrun", "kind": "job", "requirements": ["nltk", "pandas", "presidio-anonymizer", "presidio-analyzer", "torch", "flair@git+https://github.com/flairNLP/flair.git@d4ed67bf663e4066517f00397412510d90043653", "st-annotated-text", "https://huggingface.co/beki/en_spacy_pii_distilbert/resolve/main/en_spacy_pii_distilbert-any-py3-none-any.whl"]}, "url": "", "version": "0.4.0", "test_valid": false}}, "batch_inference_v2": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference_v2.ipynb", "generationDate": "2023-08-07:12-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0-rc51", "name": "batch_inference_v2", "platformVersion": "3.6.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference_v2.py", "handler": "infer", "image": "mlrun/mlrun", "kind": "job", "requirements": null}, "url": "", "version": "2.6.0"}, "2.6.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference_v2.ipynb", "generationDate": "2023-08-07:12-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0-rc51", "name": "batch_inference_v2", "platformVersion": "3.6.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference_v2.py", "handler": "infer", "image": "mlrun/mlrun", "kind": "job", "requirements": null}, "url": "", "version": "2.6.0"}}, "translate": {"latest": {"apiVersion": "v1", "categories": ["genai", "NLP"], "description": "Translate text files from one language to another", "doc": "", "example": "translate.ipynb", "generationDate": "2023-12-05:17-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.10.0-rc41", "name": "translate", "platformVersion": "3.5.3", "spec": {"filename": "translate.py", "handler": "translate", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "sentencepiece", "torch>=2.6", "tqdm"]}, "url": "", "version": "0.3.0", "test_valid": true}, "0.3.0": {"apiVersion": "v1", "categories": ["genai", "NLP"], "description": "Translate text files from one language to another", "doc": "", "example": "translate.ipynb", "generationDate": "2023-12-05:17-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.10.0-rc41", "name": "translate", "platformVersion": "3.5.3", "spec": {"filename": "translate.py", "handler": "translate", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "sentencepiece", "torch>=2.6", "tqdm"]}, "url": "", "version": "0.3.0", "test_valid": true}}, "structured_data_generator": {"latest": {"apiVersion": "v1", "categories": ["data-generation", "genai"], "description": "GenAI approach of generating structured data according to a given schema", "doc": "", "example": "structured_data_generator.ipynb", "generationDate": "2023-12-14:10-50", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "structured_data_generator", "platformVersion": "3.5.5", "spec": {"filename": "structured_data_generator.py", "handler": "generate_data", "image": "mlrun/mlrun", "kind": "job", "requirements": ["langchain", "tqdm"]}, "url": "", "version": "1.6.0"}, "1.6.0": {"apiVersion": "v1", "categories": ["data-generation", "genai"], "description": "GenAI approach of generating structured data according to a given schema", "doc": "", "example": "structured_data_generator.ipynb", "generationDate": "2023-12-14:10-50", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "structured_data_generator", "platformVersion": "3.5.5", "spec": {"filename": "structured_data_generator.py", "handler": "generate_data", "image": "mlrun/mlrun", "kind": "job", "requirements": ["langchain", "tqdm"]}, "url": "", "version": "1.6.0"}}, "text_to_audio_generator": {"latest": {"apiVersion": "v1", "categories": ["data-generation", "audio"], "description": "Generate audio file from text using different speakers", "doc": "", "example": "text_to_audio_generator.ipynb", "generationDate": "2023-12-03:15-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.1", "name": "text_to_audio_generator", "platformVersion": "3.5.3", "spec": {"filename": "text_to_audio_generator.py", "handler": "generate_multi_speakers_audio", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torchaudio", "pydub"]}, "url": "", "version": "1.3.0", "test_valid": false}, "1.3.0": {"apiVersion": "v1", "categories": ["data-generation", "audio"], "description": "Generate audio file from text using different speakers", "doc": "", "example": "text_to_audio_generator.ipynb", "generationDate": "2023-12-03:15-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.1", "name": "text_to_audio_generator", "platformVersion": "3.5.3", "spec": {"filename": "text_to_audio_generator.py", "handler": "generate_multi_speakers_audio", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torchaudio", "pydub"]}, "url": "", "version": "1.3.0", "test_valid": false}}, "silero_vad": {"latest": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "Silero VAD (Voice Activity Detection) functions.", "doc": "", "example": "silero_vad.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "silero_vad", "platformVersion": "3.5.3", "spec": {"filename": "silero_vad.py", "handler": "detect_voice", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torch", "torchaudio", "tqdm", "onnxruntime"]}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "Silero VAD (Voice Activity Detection) functions.", "doc": "", "example": "silero_vad.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "silero_vad", "platformVersion": "3.5.3", "spec": {"filename": "silero_vad.py", "handler": "detect_voice", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torch", "torchaudio", "tqdm", "onnxruntime"]}, "url": "", "version": "1.4.0"}}, "pyannote_audio": {"latest": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "pyannote's speech diarization of audio files", "doc": "", "example": "pyannote_audio.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pyannote-audio", "platformVersion": "3.5.3", "spec": {"filename": "pyannote_audio.py", "handler": "diarize", "image": "mlrun/mlrun-gpu", "kind": "job", "requirements": ["pyannote.audio", "pyannote.core", "torchaudio", "tqdm"]}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "pyannote's speech diarization of audio files", "doc": "", "example": "pyannote_audio.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pyannote-audio", "platformVersion": "3.5.3", "spec": {"filename": "pyannote_audio.py", "handler": "diarize", "image": "mlrun/mlrun-gpu", "kind": "job", "requirements": ["pyannote.audio", "pyannote.core", "torchaudio", "tqdm"]}, "url": "", "version": "1.3.0"}}, "noise_reduction": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "audio"], "description": "Reduce noise from audio files", "doc": "", "example": "noise_reduction.ipynb", "generationDate": "2024-03-04:17-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "mlrunVersion": "1.7.0", "name": "noise-reduction", "platformVersion": "3.5.3", "spec": {"filename": "noise_reduction.py", "handler": "reduce_noise", "image": "mlrun/mlrun", "kind": "job", "requirements": ["librosa", "noisereduce", "deepfilternet", "torchaudio>=2.1.2"]}, "url": "", "version": "1.1.0", "test_valid": false}, "1.1.0": {"apiVersion": "v1", "categories": ["data-preparation", "audio"], "description": "Reduce noise from audio files", "doc": "", "example": "noise_reduction.ipynb", "generationDate": "2024-03-04:17-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "mlrunVersion": "1.7.0", "name": "noise-reduction", "platformVersion": "3.5.3", "spec": {"filename": "noise_reduction.py", "handler": "reduce_noise", "image": "mlrun/mlrun", "kind": "job", "requirements": ["librosa", "noisereduce", "deepfilternet", "torchaudio>=2.1.2"]}, "url": "", "version": "1.1.0", "test_valid": false}}, "mlflow_utils": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Mlflow model server, and additional utils.", "doc": "", "example": "mlflow_utils.ipynb", "generationDate": "2024-05-23:12-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "mlflow_utils", "platformVersion": "", "spec": {"customFields": {"default_class": "MLFlowModelServer"}, "filename": "mlflow_utils.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["mlflow~=2.22", "lightgbm", "xgboost"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Mlflow model server, and additional utils.", "doc": "", "example": "mlflow_utils.ipynb", "generationDate": "2024-05-23:12-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "mlflow_utils", "platformVersion": "", "spec": {"customFields": {"default_class": "MLFlowModelServer"}, "filename": "mlflow_utils.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["mlflow~=2.22", "lightgbm", "xgboost"]}, "url": "", "version": "1.1.0"}}}, "master": {"tf2_serving": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "tf2 image classification server", "doc": "", "example": "tf2_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "tf2-serving", "platformVersion": "3.5.0", "spec": {"filename": "tf2_serving.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": ["requests", "pillow", "tensorflow>=2.1"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "tf2 image classification server", "doc": "", "example": "tf2_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "tf2-serving", "platformVersion": "3.5.0", "spec": {"filename": "tf2_serving.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": ["requests", "pillow", "tensorflow>=2.1"]}, "url": "", "version": "1.1.0"}}, "load_dataset": {"latest": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "load a toy dataset from scikit-learn", "doc": "README.md", "example": "load_dataset.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.6.0", "name": "load-dataset", "platformVersion": "3.5.5", "spec": {"filename": "load_dataset.py", "handler": "load_dataset", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "load a toy dataset from scikit-learn", "doc": "README.md", "example": "load_dataset.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.6.0", "name": "load-dataset", "platformVersion": "3.5.5", "spec": {"filename": "load_dataset.py", "handler": "load_dataset", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "model_server_tester": {"latest": {"apiVersion": "v1", "categories": ["monitoring", "model-serving"], "description": "test model servers", "doc": "", "example": "model_server_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "model-server-tester", "platformVersion": "3.5.0", "spec": {"filename": "model_server_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["monitoring", "model-serving"], "description": "test model servers", "doc": "", "example": "model_server_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "model-server-tester", "platformVersion": "3.5.0", "spec": {"filename": "model_server_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "feature_selection": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "machine-learning"], "description": "Select features through multiple Statistical and Model filters", "doc": "", "example": "feature_selection.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc40", "name": "feature-selection", "platformVersion": "3.6.0", "spec": {"filename": "feature_selection.py", "handler": "feature_selection", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.6.0"}, "1.6.0": {"apiVersion": "v1", "categories": ["data-preparation", "machine-learning"], "description": "Select features through multiple Statistical and Model filters", "doc": "", "example": "feature_selection.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc40", "name": "feature-selection", "platformVersion": "3.6.0", "spec": {"filename": "feature_selection.py", "handler": "feature_selection", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.6.0"}}, "aggregate": {"latest": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "Rolling aggregation over Metrics and Lables according to specifications", "doc": "", "example": "aggregate.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "aggregate", "platformVersion": "3.5.4", "spec": {"filename": "aggregate.py", "handler": "aggregate", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "Rolling aggregation over Metrics and Lables according to specifications", "doc": "", "example": "aggregate.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "aggregate", "platformVersion": "3.5.4", "spec": {"filename": "aggregate.py", "handler": "aggregate", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}}, "describe": {"latest": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "describe and visualizes dataset stats", "doc": "", "example": "describe.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "describe", "platformVersion": "3.5.3", "spec": {"filename": "describe.py", "handler": "analyze", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "describe and visualizes dataset stats", "doc": "", "example": "describe.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "describe", "platformVersion": "3.5.3", "spec": {"filename": "describe.py", "handler": "analyze", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}}, "model_server": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "model-server", "platformVersion": "3.5.0", "spec": {"filename": "model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "model-server", "platformVersion": "3.5.0", "spec": {"filename": "model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": []}, "url": "", "version": "1.2.0"}}, "describe_spark": {"latest": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "", "doc": "", "example": "describe_spark.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "describe-spark", "platformVersion": "3.5.0", "spec": {"filename": "describe_spark.py", "handler": "describe_spark", "image": "iguazio/shell:3.0_b5565_20201026062233_wsdf", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "", "doc": "", "example": "describe_spark.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "describe-spark", "platformVersion": "3.5.0", "spec": {"filename": "describe_spark.py", "handler": "describe_spark", "image": "iguazio/shell:3.0_b5565_20201026062233_wsdf", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "gen_class_data": {"latest": {"apiVersion": "v1", "categories": ["data-generation"], "description": "Create a binary classification sample dataset and save.", "doc": "", "example": "gen_class_data.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "gen_class_data", "platformVersion": "3.5.3", "spec": {"filename": "gen_class_data.py", "handler": "gen_class_data", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["data-generation"], "description": "Create a binary classification sample dataset and save.", "doc": "", "example": "gen_class_data.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "gen_class_data", "platformVersion": "3.5.3", "spec": {"filename": "gen_class_data.py", "handler": "gen_class_data", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.3.0"}}, "open_archive": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "Open a file/object archive into a target directory", "doc": "", "example": "open_archive.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc50", "name": "open-archive", "platformVersion": "3.5.0", "spec": {"filename": "open_archive.py", "handler": "open_archive", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["utils"], "description": "Open a file/object archive into a target directory", "doc": "", "example": "open_archive.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc50", "name": "open-archive", "platformVersion": "3.5.0", "spec": {"filename": "open_archive.py", "handler": "open_archive", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "send_email": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "Send Email messages through SMTP server", "doc": "", "example": "send_email.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.4.1", "name": "send-email", "platformVersion": "3.5.3", "spec": {"filename": "send_email.py", "handler": "send_email", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["utils"], "description": "Send Email messages through SMTP server", "doc": "", "example": "send_email.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.4.1", "name": "send-email", "platformVersion": "3.5.3", "spec": {"filename": "send_email.py", "handler": "send_email", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "v2_model_tester": {"latest": {"apiVersion": "v1", "categories": ["model-testing", "machine-learning"], "description": "test v2 model servers", "doc": "", "example": "v2_model_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-tester", "platformVersion": "3.5.0", "spec": {"filename": "v2_model_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-testing", "machine-learning"], "description": "test v2 model servers", "doc": "", "example": "v2_model_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-tester", "platformVersion": "3.5.0", "spec": {"filename": "v2_model_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "arc_to_parquet": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "retrieve remote archive, open and save as parquet", "doc": "", "example": "arc_to_parquet.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "arc-to-parquet", "platformVersion": "3.5.4", "spec": {"filename": "arc_to_parquet.py", "handler": "arc_to_parquet", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.5.0"}, "1.5.0": {"apiVersion": "v1", "categories": ["utils"], "description": "retrieve remote archive, open and save as parquet", "doc": "", "example": "arc_to_parquet.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "arc-to-parquet", "platformVersion": "3.5.4", "spec": {"filename": "arc_to_parquet.py", "handler": "arc_to_parquet", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.5.0"}}, "github_utils": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "add comments to github pull request", "doc": "", "example": "github_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "github-utils", "platformVersion": "3.5.0", "spec": {"filename": "github_utils.py", "handler": "run_summary_comment", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["utils"], "description": "add comments to github pull request", "doc": "", "example": "github_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "github-utils", "platformVersion": "3.5.0", "spec": {"filename": "github_utils.py", "handler": "run_summary_comment", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "v2_model_server": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "v2_model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-server", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "ClassifierModel"}, "filename": "v2_model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "v2_model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-server", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "ClassifierModel"}, "filename": "v2_model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": []}, "url": "", "version": "1.2.0"}}, "onnx_utils": {"latest": {"apiVersion": "v1", "categories": ["utils", "deep-learning"], "description": "ONNX intigration in MLRun, some utils functions for the ONNX framework, optimizing and converting models from different framework to ONNX using MLRun.", "doc": "", "example": "onnx_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.2", "name": "onnx_utils", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "with_mlrun": false}}, "filename": "onnx_utils.py", "handler": "to_onnx", "image": "mlrun/mlrun", "kind": "job", "requirements": ["tqdm~=4.67.1", "tensorflow~=2.19.0", "tf_keras~=2.19.0", "torch~=2.6.0", "torchvision~=0.21.0", "onnx~=1.17.0", "onnxruntime~=1.19.2", "onnxoptimizer~=0.3.13", "onnxmltools~=1.13.0", "tf2onnx~=1.16.1", "plotly~=5.23"]}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["utils", "deep-learning"], "description": "ONNX intigration in MLRun, some utils functions for the ONNX framework, optimizing and converting models from different framework to ONNX using MLRun.", "doc": "", "example": "onnx_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.2", "name": "onnx_utils", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "with_mlrun": false}}, "filename": "onnx_utils.py", "handler": "to_onnx", "image": "mlrun/mlrun", "kind": "job", "requirements": ["tqdm~=4.67.1", "tensorflow~=2.19.0", "tf_keras~=2.19.0", "torch~=2.6.0", "torchvision~=0.21.0", "onnx~=1.17.0", "onnxruntime~=1.19.2", "onnxoptimizer~=0.3.13", "onnxmltools~=1.13.0", "tf2onnx~=1.16.1", "plotly~=5.23"]}, "url": "", "version": "1.3.0"}}, "azureml_utils": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Azure AutoML integration in MLRun, including utils functions for training models on Azure AutoML platfrom.", "doc": "", "example": "azureml_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "azureml_utils", "platformVersion": "3.5.3", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "commands": ["apt-get update && apt-get install -y --no-install-recommends git", "apt install -y liblttng-ust0"], "with_mlrun": true}}, "filename": "azureml_utils.py", "handler": "train", "image": "python:3.9-bullseye", "kind": "job", "requirements": ["azureml-core==1.54.0.post1", "azureml-train-automl-client==1.54.0.post1", "plotly~=5.23"]}, "url": "", "version": "1.4.0", "test_valid": true}, "1.4.0": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Azure AutoML integration in MLRun, including utils functions for training models on Azure AutoML platfrom.", "doc": "", "example": "azureml_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "azureml_utils", "platformVersion": "3.5.3", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "commands": ["apt-get update && apt-get install -y --no-install-recommends git", "apt install -y liblttng-ust0"], "with_mlrun": true}}, "filename": "azureml_utils.py", "handler": "train", "image": "python:3.9-bullseye", "kind": "job", "requirements": ["azureml-core==1.54.0.post1", "azureml-train-automl-client==1.54.0.post1", "plotly~=5.23"]}, "url": "", "version": "1.4.0", "test_valid": true}}, "auto_trainer": {"latest": {"apiVersion": "v1", "categories": ["machine-learning", "model-training"], "description": "Automatic train, evaluate and predict functions for the ML frameworks - Scikit-Learn, XGBoost and LightGBM.", "doc": "", "example": "auto_trainer.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "auto_trainer", "platformVersion": "3.5.0", "spec": {"filename": "auto_trainer.py", "handler": "train", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.8.0"}, "1.8.0": {"apiVersion": "v1", "categories": ["machine-learning", "model-training"], "description": "Automatic train, evaluate and predict functions for the ML frameworks - Scikit-Learn, XGBoost and LightGBM.", "doc": "", "example": "auto_trainer.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "auto_trainer", "platformVersion": "3.5.0", "spec": {"filename": "auto_trainer.py", "handler": "train", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.8.0"}}, "azureml_serving": {"latest": {"apiVersion": "v1", "categories": ["machine-learning", "model-serving"], "description": "AzureML serving function", "doc": "", "example": "azureml_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "azureml_serving", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "mlrun.frameworks.sklearn.PickleModelServer"}, "filename": "azureml_serving.py", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["azureml-automl-runtime~=1.38.1"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["machine-learning", "model-serving"], "description": "AzureML serving function", "doc": "", "example": "azureml_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "azureml_serving", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "mlrun.frameworks.sklearn.PickleModelServer"}, "filename": "azureml_serving.py", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["azureml-automl-runtime~=1.38.1"]}, "url": "", "version": "1.1.0"}}, "batch_inference": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "batch_inference", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference.py", "handler": "infer", "image": "mlrun/ml-models", "kind": "job", "requirements": null}, "url": "", "version": "1.8.0"}, "1.8.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "batch_inference", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference.py", "handler": "infer", "image": "mlrun/ml-models", "kind": "job", "requirements": null}, "url": "", "version": "1.8.0"}}, "hugging_face_serving": {"latest": {"apiVersion": "v1", "categories": ["genai", "model-serving"], "description": "Generic Hugging Face model server.", "doc": "", "example": "hugging_face_serving.ipynb", "generationDate": "2022-09-05:17-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "hugging_face_serving", "platformVersion": "", "spec": {"customFields": {"default_class": "HuggingFaceModelServer"}, "filename": "hugging_face_serving.py", "handler": "handler", "image": "mlrun/ml-models", "kind": "serving", "requirements": ["transformers==4.21.3", "tensorflow==2.9.2"]}, "url": "", "version": "1.1.0", "test_valid": false}, "1.1.0": {"apiVersion": "v1", "categories": ["genai", "model-serving"], "description": "Generic Hugging Face model server.", "doc": "", "example": "hugging_face_serving.ipynb", "generationDate": "2022-09-05:17-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "hugging_face_serving", "platformVersion": "", "spec": {"customFields": {"default_class": "HuggingFaceModelServer"}, "filename": "hugging_face_serving.py", "handler": "handler", "image": "mlrun/ml-models", "kind": "serving", "requirements": ["transformers==4.21.3", "tensorflow==2.9.2"]}, "url": "", "version": "1.1.0", "test_valid": false}}, "question_answering": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "GenAI approach of question answering on a given data", "doc": "", "example": "question_answering.ipynb", "generationDate": "2023-08-07:11-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "question_answering", "platformVersion": "3.5.0", "spec": {"filename": "question_answering.py", "handler": "answer_questions", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "torch", "tqdm"]}, "url": "", "version": "0.5.0"}, "0.5.0": {"apiVersion": "v1", "categories": ["genai"], "description": "GenAI approach of question answering on a given data", "doc": "", "example": "question_answering.ipynb", "generationDate": "2023-08-07:11-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "question_answering", "platformVersion": "3.5.0", "spec": {"filename": "question_answering.py", "handler": "answer_questions", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "torch", "tqdm"]}, "url": "", "version": "0.5.0"}}, "transcribe": {"latest": {"apiVersion": "v1", "categories": ["audio", "genai"], "description": "Transcribe audio files into text files", "doc": "", "example": "transcribe.ipynb", "generationDate": "2023-07-13:11-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "transcribe", "platformVersion": "3.5.3", "spec": {"filename": "transcribe.py", "handler": "transcribe", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "tqdm", "torchaudio", "torch", "accelerate"]}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["audio", "genai"], "description": "Transcribe audio files into text files", "doc": "", "example": "transcribe.ipynb", "generationDate": "2023-07-13:11-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "transcribe", "platformVersion": "3.5.3", "spec": {"filename": "transcribe.py", "handler": "transcribe", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "tqdm", "torchaudio", "torch", "accelerate"]}, "url": "", "version": "1.2.0"}}, "pii_recognizer": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "NLP"], "description": "This function is used to recognize PII in a directory of text files", "doc": "", "example": "pii_recognizer.ipynb", "generationDate": "2023-08-15:10-24", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pii-recognizer", "platformVersion": "3.5.3", "spec": {"filename": "pii_recognizer.py", "handler": "recognize_pii", "image": "mlrun/mlrun", "kind": "job", "requirements": ["nltk", "pandas", "presidio-anonymizer", "presidio-analyzer", "torch", "flair@git+https://github.com/flairNLP/flair.git@d4ed67bf663e4066517f00397412510d90043653", "st-annotated-text", "https://huggingface.co/beki/en_spacy_pii_distilbert/resolve/main/en_spacy_pii_distilbert-any-py3-none-any.whl"]}, "url": "", "version": "0.4.0", "test_valid": false}, "0.4.0": {"apiVersion": "v1", "categories": ["data-preparation", "NLP"], "description": "This function is used to recognize PII in a directory of text files", "doc": "", "example": "pii_recognizer.ipynb", "generationDate": "2023-08-15:10-24", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pii-recognizer", "platformVersion": "3.5.3", "spec": {"filename": "pii_recognizer.py", "handler": "recognize_pii", "image": "mlrun/mlrun", "kind": "job", "requirements": ["nltk", "pandas", "presidio-anonymizer", "presidio-analyzer", "torch", "flair@git+https://github.com/flairNLP/flair.git@d4ed67bf663e4066517f00397412510d90043653", "st-annotated-text", "https://huggingface.co/beki/en_spacy_pii_distilbert/resolve/main/en_spacy_pii_distilbert-any-py3-none-any.whl"]}, "url": "", "version": "0.4.0", "test_valid": false}}, "batch_inference_v2": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference_v2.ipynb", "generationDate": "2023-08-07:12-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0-rc51", "name": "batch_inference_v2", "platformVersion": "3.6.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference_v2.py", "handler": "infer", "image": "mlrun/mlrun", "kind": "job", "requirements": null}, "url": "", "version": "2.6.0"}, "2.6.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference_v2.ipynb", "generationDate": "2023-08-07:12-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0-rc51", "name": "batch_inference_v2", "platformVersion": "3.6.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference_v2.py", "handler": "infer", "image": "mlrun/mlrun", "kind": "job", "requirements": null}, "url": "", "version": "2.6.0"}}, "translate": {"latest": {"apiVersion": "v1", "categories": ["genai", "NLP"], "description": "Translate text files from one language to another", "doc": "", "example": "translate.ipynb", "generationDate": "2023-12-05:17-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.10.0-rc41", "name": "translate", "platformVersion": "3.5.3", "spec": {"filename": "translate.py", "handler": "translate", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "sentencepiece", "torch>=2.6", "tqdm"]}, "url": "", "version": "0.3.0", "test_valid": true}, "0.3.0": {"apiVersion": "v1", "categories": ["genai", "NLP"], "description": "Translate text files from one language to another", "doc": "", "example": "translate.ipynb", "generationDate": "2023-12-05:17-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.10.0-rc41", "name": "translate", "platformVersion": "3.5.3", "spec": {"filename": "translate.py", "handler": "translate", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "sentencepiece", "torch>=2.6", "tqdm"]}, "url": "", "version": "0.3.0", "test_valid": true}}, "structured_data_generator": {"latest": {"apiVersion": "v1", "categories": ["data-generation", "genai"], "description": "GenAI approach of generating structured data according to a given schema", "doc": "", "example": "structured_data_generator.ipynb", "generationDate": "2023-12-14:10-50", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "structured_data_generator", "platformVersion": "3.5.5", "spec": {"filename": "structured_data_generator.py", "handler": "generate_data", "image": "mlrun/mlrun", "kind": "job", "requirements": ["langchain", "tqdm"]}, "url": "", "version": "1.6.0"}, "1.6.0": {"apiVersion": "v1", "categories": ["data-generation", "genai"], "description": "GenAI approach of generating structured data according to a given schema", "doc": "", "example": "structured_data_generator.ipynb", "generationDate": "2023-12-14:10-50", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "structured_data_generator", "platformVersion": "3.5.5", "spec": {"filename": "structured_data_generator.py", "handler": "generate_data", "image": "mlrun/mlrun", "kind": "job", "requirements": ["langchain", "tqdm"]}, "url": "", "version": "1.6.0"}}, "text_to_audio_generator": {"latest": {"apiVersion": "v1", "categories": ["data-generation", "audio"], "description": "Generate audio file from text using different speakers", "doc": "", "example": "text_to_audio_generator.ipynb", "generationDate": "2023-12-03:15-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.1", "name": "text_to_audio_generator", "platformVersion": "3.5.3", "spec": {"filename": "text_to_audio_generator.py", "handler": "generate_multi_speakers_audio", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torchaudio", "pydub"]}, "url": "", "version": "1.3.0", "test_valid": false}, "1.3.0": {"apiVersion": "v1", "categories": ["data-generation", "audio"], "description": "Generate audio file from text using different speakers", "doc": "", "example": "text_to_audio_generator.ipynb", "generationDate": "2023-12-03:15-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.1", "name": "text_to_audio_generator", "platformVersion": "3.5.3", "spec": {"filename": "text_to_audio_generator.py", "handler": "generate_multi_speakers_audio", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torchaudio", "pydub"]}, "url": "", "version": "1.3.0", "test_valid": false}}, "silero_vad": {"latest": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "Silero VAD (Voice Activity Detection) functions.", "doc": "", "example": "silero_vad.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "silero_vad", "platformVersion": "3.5.3", "spec": {"filename": "silero_vad.py", "handler": "detect_voice", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torch", "torchaudio", "tqdm", "onnxruntime"]}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "Silero VAD (Voice Activity Detection) functions.", "doc": "", "example": "silero_vad.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "silero_vad", "platformVersion": "3.5.3", "spec": {"filename": "silero_vad.py", "handler": "detect_voice", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torch", "torchaudio", "tqdm", "onnxruntime"]}, "url": "", "version": "1.4.0"}}, "pyannote_audio": {"latest": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "pyannote's speech diarization of audio files", "doc": "", "example": "pyannote_audio.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pyannote-audio", "platformVersion": "3.5.3", "spec": {"filename": "pyannote_audio.py", "handler": "diarize", "image": "mlrun/mlrun-gpu", "kind": "job", "requirements": ["pyannote.audio", "pyannote.core", "torchaudio", "tqdm"]}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "pyannote's speech diarization of audio files", "doc": "", "example": "pyannote_audio.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pyannote-audio", "platformVersion": "3.5.3", "spec": {"filename": "pyannote_audio.py", "handler": "diarize", "image": "mlrun/mlrun-gpu", "kind": "job", "requirements": ["pyannote.audio", "pyannote.core", "torchaudio", "tqdm"]}, "url": "", "version": "1.3.0"}}, "mlflow_utils": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Mlflow model server, and additional utils.", "doc": "", "example": "mlflow_utils.ipynb", "generationDate": "2024-05-23:12-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "mlflow_utils", "platformVersion": "", "spec": {"customFields": {"default_class": "MLFlowModelServer"}, "filename": "mlflow_utils.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["mlflow~=2.22", "lightgbm", "xgboost"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Mlflow model server, and additional utils.", "doc": "", "example": "mlflow_utils.ipynb", "generationDate": "2024-05-23:12-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "mlflow_utils", "platformVersion": "", "spec": {"customFields": {"default_class": "MLFlowModelServer"}, "filename": "mlflow_utils.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["mlflow~=2.22", "lightgbm", "xgboost"]}, "url": "", "version": "1.1.0"}}, "noise_reduction": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "audio"], "description": "Reduce noise from audio files", "doc": "", "example": "noise_reduction.ipynb", "generationDate": "2024-03-04:17-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "mlrunVersion": "1.7.0", "name": "noise-reduction", "platformVersion": "3.5.3", "spec": {"filename": "noise_reduction.py", "handler": "reduce_noise", "image": "mlrun/mlrun", "kind": "job", "requirements": ["librosa", "noisereduce", "deepfilternet", "torchaudio>=2.1.2"]}, "url": "", "version": "1.1.0", "test_valid": false}, "1.1.0": {"apiVersion": "v1", "categories": ["data-preparation", "audio"], "description": "Reduce noise from audio files", "doc": "", "example": "noise_reduction.ipynb", "generationDate": "2024-03-04:17-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "mlrunVersion": "1.7.0", "name": "noise-reduction", "platformVersion": "3.5.3", "spec": {"filename": "noise_reduction.py", "handler": "reduce_noise", "image": "mlrun/mlrun", "kind": "job", "requirements": ["librosa", "noisereduce", "deepfilternet", "torchaudio>=2.1.2"]}, "url": "", "version": "1.1.0", "test_valid": false}}}}, "modules": {"development": {"count_events": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}}, "histogram_data_drift": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0"}}, "openai_proxy_app": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0"}}, "evidently_iris": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0"}}, "agent_deployer": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}}}, "master": {"count_events": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}}, "histogram_data_drift": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0"}}, "openai_proxy_app": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0"}}, "evidently_iris": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0"}}, "agent_deployer": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}}, "vllm_module": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.", "example": "vllm_module.ipynb", "generationDate": "2025-12-17:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "vllm_module", "spec": {"filename": "vllm_module.py", "image": "mlrun/mlrun", "kind": "generic"}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.", "example": "vllm_module.ipynb", "generationDate": "2025-12-17:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "vllm_module", "spec": {"filename": "vllm_module.py", "image": "mlrun/mlrun", "kind": "generic"}, "version": "1.0.0"}}}}, "steps": {"development": {}, "master": {}}}
\ No newline at end of file
+{"functions": {"development": {"tf2_serving": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "tf2 image classification server", "doc": "", "example": "tf2_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "tf2-serving", "platformVersion": "3.5.0", "spec": {"filename": "tf2_serving.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": ["requests", "pillow", "tensorflow>=2.1"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "tf2 image classification server", "doc": "", "example": "tf2_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "tf2-serving", "platformVersion": "3.5.0", "spec": {"filename": "tf2_serving.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": ["requests", "pillow", "tensorflow>=2.1"]}, "url": "", "version": "1.1.0"}}, "load_dataset": {"latest": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "load a toy dataset from scikit-learn", "doc": "README.md", "example": "load_dataset.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.6.0", "name": "load-dataset", "platformVersion": "3.5.5", "spec": {"filename": "load_dataset.py", "handler": "load_dataset", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "load a toy dataset from scikit-learn", "doc": "README.md", "example": "load_dataset.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.6.0", "name": "load-dataset", "platformVersion": "3.5.5", "spec": {"filename": "load_dataset.py", "handler": "load_dataset", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "model_server_tester": {"latest": {"apiVersion": "v1", "categories": ["monitoring", "model-serving"], "description": "test model servers", "doc": "", "example": "model_server_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "model-server-tester", "platformVersion": "3.5.0", "spec": {"filename": "model_server_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["monitoring", "model-serving"], "description": "test model servers", "doc": "", "example": "model_server_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "model-server-tester", "platformVersion": "3.5.0", "spec": {"filename": "model_server_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "feature_selection": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "machine-learning"], "description": "Select features through multiple Statistical and Model filters", "doc": "", "example": "feature_selection.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc40", "name": "feature-selection", "platformVersion": "3.6.0", "spec": {"filename": "feature_selection.py", "handler": "feature_selection", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.6.0"}, "1.6.0": {"apiVersion": "v1", "categories": ["data-preparation", "machine-learning"], "description": "Select features through multiple Statistical and Model filters", "doc": "", "example": "feature_selection.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc40", "name": "feature-selection", "platformVersion": "3.6.0", "spec": {"filename": "feature_selection.py", "handler": "feature_selection", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.6.0"}}, "aggregate": {"latest": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "Rolling aggregation over Metrics and Lables according to specifications", "doc": "", "example": "aggregate.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "aggregate", "platformVersion": "3.5.4", "spec": {"filename": "aggregate.py", "handler": "aggregate", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "Rolling aggregation over Metrics and Lables according to specifications", "doc": "", "example": "aggregate.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "aggregate", "platformVersion": "3.5.4", "spec": {"filename": "aggregate.py", "handler": "aggregate", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}}, "describe": {"latest": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "describe and visualizes dataset stats", "doc": "", "example": "describe.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "describe", "platformVersion": "3.5.3", "spec": {"filename": "describe.py", "handler": "analyze", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "describe and visualizes dataset stats", "doc": "", "example": "describe.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "describe", "platformVersion": "3.5.3", "spec": {"filename": "describe.py", "handler": "analyze", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}}, "model_server": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "model-server", "platformVersion": "3.5.0", "spec": {"filename": "model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "model-server", "platformVersion": "3.5.0", "spec": {"filename": "model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": []}, "url": "", "version": "1.2.0"}}, "describe_spark": {"latest": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "", "doc": "", "example": "describe_spark.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "describe-spark", "platformVersion": "3.5.0", "spec": {"filename": "describe_spark.py", "handler": "describe_spark", "image": "iguazio/shell:3.0_b5565_20201026062233_wsdf", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "", "doc": "", "example": "describe_spark.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "describe-spark", "platformVersion": "3.5.0", "spec": {"filename": "describe_spark.py", "handler": "describe_spark", "image": "iguazio/shell:3.0_b5565_20201026062233_wsdf", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "gen_class_data": {"latest": {"apiVersion": "v1", "categories": ["data-generation"], "description": "Create a binary classification sample dataset and save.", "doc": "", "example": "gen_class_data.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "gen_class_data", "platformVersion": "3.5.3", "spec": {"filename": "gen_class_data.py", "handler": "gen_class_data", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["data-generation"], "description": "Create a binary classification sample dataset and save.", "doc": "", "example": "gen_class_data.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "gen_class_data", "platformVersion": "3.5.3", "spec": {"filename": "gen_class_data.py", "handler": "gen_class_data", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.3.0"}}, "open_archive": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "Open a file/object archive into a target directory", "doc": "", "example": "open_archive.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc50", "name": "open-archive", "platformVersion": "3.5.0", "spec": {"filename": "open_archive.py", "handler": "open_archive", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["utils"], "description": "Open a file/object archive into a target directory", "doc": "", "example": "open_archive.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc50", "name": "open-archive", "platformVersion": "3.5.0", "spec": {"filename": "open_archive.py", "handler": "open_archive", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "send_email": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "Send Email messages through SMTP server", "doc": "", "example": "send_email.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.4.1", "name": "send-email", "platformVersion": "3.5.3", "spec": {"filename": "send_email.py", "handler": "send_email", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["utils"], "description": "Send Email messages through SMTP server", "doc": "", "example": "send_email.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.4.1", "name": "send-email", "platformVersion": "3.5.3", "spec": {"filename": "send_email.py", "handler": "send_email", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "v2_model_tester": {"latest": {"apiVersion": "v1", "categories": ["model-testing", "machine-learning"], "description": "test v2 model servers", "doc": "", "example": "v2_model_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-tester", "platformVersion": "3.5.0", "spec": {"filename": "v2_model_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-testing", "machine-learning"], "description": "test v2 model servers", "doc": "", "example": "v2_model_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-tester", "platformVersion": "3.5.0", "spec": {"filename": "v2_model_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "arc_to_parquet": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "retrieve remote archive, open and save as parquet", "doc": "", "example": "arc_to_parquet.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "arc-to-parquet", "platformVersion": "3.5.4", "spec": {"filename": "arc_to_parquet.py", "handler": "arc_to_parquet", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.5.0"}, "1.5.0": {"apiVersion": "v1", "categories": ["utils"], "description": "retrieve remote archive, open and save as parquet", "doc": "", "example": "arc_to_parquet.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "arc-to-parquet", "platformVersion": "3.5.4", "spec": {"filename": "arc_to_parquet.py", "handler": "arc_to_parquet", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.5.0"}}, "github_utils": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "add comments to github pull request", "doc": "", "example": "github_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "github-utils", "platformVersion": "3.5.0", "spec": {"filename": "github_utils.py", "handler": "run_summary_comment", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["utils"], "description": "add comments to github pull request", "doc": "", "example": "github_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "github-utils", "platformVersion": "3.5.0", "spec": {"filename": "github_utils.py", "handler": "run_summary_comment", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "v2_model_server": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "v2_model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-server", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "ClassifierModel"}, "filename": "v2_model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "v2_model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-server", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "ClassifierModel"}, "filename": "v2_model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": []}, "url": "", "version": "1.2.0"}}, "onnx_utils": {"latest": {"apiVersion": "v1", "categories": ["utils", "deep-learning"], "description": "ONNX intigration in MLRun, some utils functions for the ONNX framework, optimizing and converting models from different framework to ONNX using MLRun.", "doc": "", "example": "onnx_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.2", "name": "onnx_utils", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "with_mlrun": false}}, "filename": "onnx_utils.py", "handler": "to_onnx", "image": "mlrun/mlrun", "kind": "job", "requirements": ["tqdm~=4.67.1", "tensorflow~=2.19.0", "tf_keras~=2.19.0", "torch~=2.6.0", "torchvision~=0.21.0", "onnx~=1.17.0", "onnxruntime~=1.19.2", "onnxoptimizer~=0.3.13", "onnxmltools~=1.13.0", "tf2onnx~=1.16.1", "plotly~=5.23"]}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["utils", "deep-learning"], "description": "ONNX intigration in MLRun, some utils functions for the ONNX framework, optimizing and converting models from different framework to ONNX using MLRun.", "doc": "", "example": "onnx_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.2", "name": "onnx_utils", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "with_mlrun": false}}, "filename": "onnx_utils.py", "handler": "to_onnx", "image": "mlrun/mlrun", "kind": "job", "requirements": ["tqdm~=4.67.1", "tensorflow~=2.19.0", "tf_keras~=2.19.0", "torch~=2.6.0", "torchvision~=0.21.0", "onnx~=1.17.0", "onnxruntime~=1.19.2", "onnxoptimizer~=0.3.13", "onnxmltools~=1.13.0", "tf2onnx~=1.16.1", "plotly~=5.23"]}, "url": "", "version": "1.3.0"}}, "azureml_utils": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Azure AutoML integration in MLRun, including utils functions for training models on Azure AutoML platfrom.", "doc": "", "example": "azureml_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "azureml_utils", "platformVersion": "3.5.3", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "commands": ["apt-get update && apt-get install -y --no-install-recommends git", "apt install -y liblttng-ust0"], "with_mlrun": true}}, "filename": "azureml_utils.py", "handler": "train", "image": "python:3.9-bullseye", "kind": "job", "requirements": ["azureml-core==1.54.0.post1", "azureml-train-automl-client==1.54.0.post1", "plotly~=5.23"]}, "url": "", "version": "1.4.0", "test_valid": true}, "1.4.0": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Azure AutoML integration in MLRun, including utils functions for training models on Azure AutoML platfrom.", "doc": "", "example": "azureml_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "azureml_utils", "platformVersion": "3.5.3", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "commands": ["apt-get update && apt-get install -y --no-install-recommends git", "apt install -y liblttng-ust0"], "with_mlrun": true}}, "filename": "azureml_utils.py", "handler": "train", "image": "python:3.9-bullseye", "kind": "job", "requirements": ["azureml-core==1.54.0.post1", "azureml-train-automl-client==1.54.0.post1", "plotly~=5.23"]}, "url": "", "version": "1.4.0", "test_valid": true}}, "auto_trainer": {"latest": {"apiVersion": "v1", "categories": ["machine-learning", "model-training"], "description": "Automatic train, evaluate and predict functions for the ML frameworks - Scikit-Learn, XGBoost and LightGBM.", "doc": "", "example": "auto_trainer.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "auto_trainer", "platformVersion": "3.5.0", "spec": {"filename": "auto_trainer.py", "handler": "train", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.8.0"}, "1.8.0": {"apiVersion": "v1", "categories": ["machine-learning", "model-training"], "description": "Automatic train, evaluate and predict functions for the ML frameworks - Scikit-Learn, XGBoost and LightGBM.", "doc": "", "example": "auto_trainer.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "auto_trainer", "platformVersion": "3.5.0", "spec": {"filename": "auto_trainer.py", "handler": "train", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.8.0"}}, "azureml_serving": {"latest": {"apiVersion": "v1", "categories": ["machine-learning", "model-serving"], "description": "AzureML serving function", "doc": "", "example": "azureml_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "azureml_serving", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "mlrun.frameworks.sklearn.PickleModelServer"}, "filename": "azureml_serving.py", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["azureml-automl-runtime~=1.38.1"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["machine-learning", "model-serving"], "description": "AzureML serving function", "doc": "", "example": "azureml_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "azureml_serving", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "mlrun.frameworks.sklearn.PickleModelServer"}, "filename": "azureml_serving.py", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["azureml-automl-runtime~=1.38.1"]}, "url": "", "version": "1.1.0"}}, "batch_inference": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "batch_inference", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference.py", "handler": "infer", "image": "mlrun/ml-models", "kind": "job", "requirements": null}, "url": "", "version": "1.8.0"}, "1.8.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "batch_inference", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference.py", "handler": "infer", "image": "mlrun/ml-models", "kind": "job", "requirements": null}, "url": "", "version": "1.8.0"}}, "hugging_face_serving": {"latest": {"apiVersion": "v1", "categories": ["genai", "model-serving"], "description": "Generic Hugging Face model server.", "doc": "", "example": "hugging_face_serving.ipynb", "generationDate": "2022-09-05:17-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "hugging_face_serving", "platformVersion": "", "spec": {"customFields": {"default_class": "HuggingFaceModelServer"}, "filename": "hugging_face_serving.py", "handler": "handler", "image": "mlrun/ml-models", "kind": "serving", "requirements": ["transformers==4.21.3", "tensorflow==2.9.2"]}, "url": "", "version": "1.1.0", "test_valid": false}, "1.1.0": {"apiVersion": "v1", "categories": ["genai", "model-serving"], "description": "Generic Hugging Face model server.", "doc": "", "example": "hugging_face_serving.ipynb", "generationDate": "2022-09-05:17-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "hugging_face_serving", "platformVersion": "", "spec": {"customFields": {"default_class": "HuggingFaceModelServer"}, "filename": "hugging_face_serving.py", "handler": "handler", "image": "mlrun/ml-models", "kind": "serving", "requirements": ["transformers==4.21.3", "tensorflow==2.9.2"]}, "url": "", "version": "1.1.0", "test_valid": false}}, "transcribe": {"latest": {"apiVersion": "v1", "categories": ["audio", "genai"], "description": "Transcribe audio files into text files", "doc": "", "example": "transcribe.ipynb", "generationDate": "2023-07-13:11-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "transcribe", "platformVersion": "3.5.3", "spec": {"filename": "transcribe.py", "handler": "transcribe", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "tqdm", "torchaudio", "torch", "accelerate"]}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["audio", "genai"], "description": "Transcribe audio files into text files", "doc": "", "example": "transcribe.ipynb", "generationDate": "2023-07-13:11-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "transcribe", "platformVersion": "3.5.3", "spec": {"filename": "transcribe.py", "handler": "transcribe", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "tqdm", "torchaudio", "torch", "accelerate"]}, "url": "", "version": "1.2.0"}}, "question_answering": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "GenAI approach of question answering on a given data", "doc": "", "example": "question_answering.ipynb", "generationDate": "2023-08-07:11-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "question_answering", "platformVersion": "3.5.0", "spec": {"filename": "question_answering.py", "handler": "answer_questions", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "torch", "tqdm"]}, "url": "", "version": "0.5.0"}, "0.5.0": {"apiVersion": "v1", "categories": ["genai"], "description": "GenAI approach of question answering on a given data", "doc": "", "example": "question_answering.ipynb", "generationDate": "2023-08-07:11-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "question_answering", "platformVersion": "3.5.0", "spec": {"filename": "question_answering.py", "handler": "answer_questions", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "torch", "tqdm"]}, "url": "", "version": "0.5.0"}}, "pii_recognizer": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "NLP"], "description": "This function is used to recognize PII in a directory of text files", "doc": "", "example": "pii_recognizer.ipynb", "generationDate": "2023-08-15:10-24", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pii-recognizer", "platformVersion": "3.5.3", "spec": {"filename": "pii_recognizer.py", "handler": "recognize_pii", "image": "mlrun/mlrun", "kind": "job", "requirements": ["nltk", "pandas", "presidio-anonymizer", "presidio-analyzer", "torch", "flair@git+https://github.com/flairNLP/flair.git@d4ed67bf663e4066517f00397412510d90043653", "st-annotated-text", "https://huggingface.co/beki/en_spacy_pii_distilbert/resolve/main/en_spacy_pii_distilbert-any-py3-none-any.whl"]}, "url": "", "version": "0.4.0", "test_valid": false}, "0.4.0": {"apiVersion": "v1", "categories": ["data-preparation", "NLP"], "description": "This function is used to recognize PII in a directory of text files", "doc": "", "example": "pii_recognizer.ipynb", "generationDate": "2023-08-15:10-24", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pii-recognizer", "platformVersion": "3.5.3", "spec": {"filename": "pii_recognizer.py", "handler": "recognize_pii", "image": "mlrun/mlrun", "kind": "job", "requirements": ["nltk", "pandas", "presidio-anonymizer", "presidio-analyzer", "torch", "flair@git+https://github.com/flairNLP/flair.git@d4ed67bf663e4066517f00397412510d90043653", "st-annotated-text", "https://huggingface.co/beki/en_spacy_pii_distilbert/resolve/main/en_spacy_pii_distilbert-any-py3-none-any.whl"]}, "url": "", "version": "0.4.0", "test_valid": false}}, "batch_inference_v2": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference_v2.ipynb", "generationDate": "2023-08-07:12-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0-rc51", "name": "batch_inference_v2", "platformVersion": "3.6.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference_v2.py", "handler": "infer", "image": "mlrun/mlrun", "kind": "job", "requirements": null}, "url": "", "version": "2.6.0"}, "2.6.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference_v2.ipynb", "generationDate": "2023-08-07:12-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0-rc51", "name": "batch_inference_v2", "platformVersion": "3.6.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference_v2.py", "handler": "infer", "image": "mlrun/mlrun", "kind": "job", "requirements": null}, "url": "", "version": "2.6.0"}}, "translate": {"latest": {"apiVersion": "v1", "categories": ["genai", "NLP"], "description": "Translate text files from one language to another", "doc": "", "example": "translate.ipynb", "generationDate": "2023-12-05:17-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.10.0-rc41", "name": "translate", "platformVersion": "3.5.3", "spec": {"filename": "translate.py", "handler": "translate", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "sentencepiece", "torch>=2.6", "tqdm"]}, "url": "", "version": "0.3.0", "test_valid": true}, "0.3.0": {"apiVersion": "v1", "categories": ["genai", "NLP"], "description": "Translate text files from one language to another", "doc": "", "example": "translate.ipynb", "generationDate": "2023-12-05:17-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.10.0-rc41", "name": "translate", "platformVersion": "3.5.3", "spec": {"filename": "translate.py", "handler": "translate", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "sentencepiece", "torch>=2.6", "tqdm"]}, "url": "", "version": "0.3.0", "test_valid": true}}, "structured_data_generator": {"latest": {"apiVersion": "v1", "categories": ["data-generation", "genai"], "description": "GenAI approach of generating structured data according to a given schema", "doc": "", "example": "structured_data_generator.ipynb", "generationDate": "2023-12-14:10-50", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "structured_data_generator", "platformVersion": "3.5.5", "spec": {"filename": "structured_data_generator.py", "handler": "generate_data", "image": "mlrun/mlrun", "kind": "job", "requirements": ["langchain", "tqdm"]}, "url": "", "version": "1.6.0"}, "1.6.0": {"apiVersion": "v1", "categories": ["data-generation", "genai"], "description": "GenAI approach of generating structured data according to a given schema", "doc": "", "example": "structured_data_generator.ipynb", "generationDate": "2023-12-14:10-50", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "structured_data_generator", "platformVersion": "3.5.5", "spec": {"filename": "structured_data_generator.py", "handler": "generate_data", "image": "mlrun/mlrun", "kind": "job", "requirements": ["langchain", "tqdm"]}, "url": "", "version": "1.6.0"}}, "text_to_audio_generator": {"latest": {"apiVersion": "v1", "categories": ["data-generation", "audio"], "description": "Generate audio file from text using different speakers", "doc": "", "example": "text_to_audio_generator.ipynb", "generationDate": "2023-12-03:15-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.1", "name": "text_to_audio_generator", "platformVersion": "3.5.3", "spec": {"filename": "text_to_audio_generator.py", "handler": "generate_multi_speakers_audio", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torchaudio", "pydub"]}, "url": "", "version": "1.3.0", "test_valid": false}, "1.3.0": {"apiVersion": "v1", "categories": ["data-generation", "audio"], "description": "Generate audio file from text using different speakers", "doc": "", "example": "text_to_audio_generator.ipynb", "generationDate": "2023-12-03:15-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.1", "name": "text_to_audio_generator", "platformVersion": "3.5.3", "spec": {"filename": "text_to_audio_generator.py", "handler": "generate_multi_speakers_audio", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torchaudio", "pydub"]}, "url": "", "version": "1.3.0", "test_valid": false}}, "silero_vad": {"latest": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "Silero VAD (Voice Activity Detection) functions.", "doc": "", "example": "silero_vad.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "silero_vad", "platformVersion": "3.5.3", "spec": {"filename": "silero_vad.py", "handler": "detect_voice", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torch", "torchaudio", "tqdm", "onnxruntime"]}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "Silero VAD (Voice Activity Detection) functions.", "doc": "", "example": "silero_vad.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "silero_vad", "platformVersion": "3.5.3", "spec": {"filename": "silero_vad.py", "handler": "detect_voice", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torch", "torchaudio", "tqdm", "onnxruntime"]}, "url": "", "version": "1.4.0"}}, "pyannote_audio": {"latest": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "pyannote's speech diarization of audio files", "doc": "", "example": "pyannote_audio.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pyannote-audio", "platformVersion": "3.5.3", "spec": {"filename": "pyannote_audio.py", "handler": "diarize", "image": "mlrun/mlrun-gpu", "kind": "job", "requirements": ["pyannote.audio", "pyannote.core", "torchaudio", "tqdm"]}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "pyannote's speech diarization of audio files", "doc": "", "example": "pyannote_audio.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pyannote-audio", "platformVersion": "3.5.3", "spec": {"filename": "pyannote_audio.py", "handler": "diarize", "image": "mlrun/mlrun-gpu", "kind": "job", "requirements": ["pyannote.audio", "pyannote.core", "torchaudio", "tqdm"]}, "url": "", "version": "1.3.0"}}, "noise_reduction": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "audio"], "description": "Reduce noise from audio files", "doc": "", "example": "noise_reduction.ipynb", "generationDate": "2024-03-04:17-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "mlrunVersion": "1.7.0", "name": "noise-reduction", "platformVersion": "3.5.3", "spec": {"filename": "noise_reduction.py", "handler": "reduce_noise", "image": "mlrun/mlrun", "kind": "job", "requirements": ["librosa", "noisereduce", "deepfilternet", "torchaudio>=2.1.2"]}, "url": "", "version": "1.1.0", "test_valid": false}, "1.1.0": {"apiVersion": "v1", "categories": ["data-preparation", "audio"], "description": "Reduce noise from audio files", "doc": "", "example": "noise_reduction.ipynb", "generationDate": "2024-03-04:17-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "mlrunVersion": "1.7.0", "name": "noise-reduction", "platformVersion": "3.5.3", "spec": {"filename": "noise_reduction.py", "handler": "reduce_noise", "image": "mlrun/mlrun", "kind": "job", "requirements": ["librosa", "noisereduce", "deepfilternet", "torchaudio>=2.1.2"]}, "url": "", "version": "1.1.0", "test_valid": false}}, "mlflow_utils": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Mlflow model server, and additional utils.", "doc": "", "example": "mlflow_utils.ipynb", "generationDate": "2024-05-23:12-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "mlflow_utils", "platformVersion": "", "spec": {"customFields": {"default_class": "MLFlowModelServer"}, "filename": "mlflow_utils.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["mlflow~=2.22", "lightgbm", "xgboost"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Mlflow model server, and additional utils.", "doc": "", "example": "mlflow_utils.ipynb", "generationDate": "2024-05-23:12-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "mlflow_utils", "platformVersion": "", "spec": {"customFields": {"default_class": "MLFlowModelServer"}, "filename": "mlflow_utils.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["mlflow~=2.22", "lightgbm", "xgboost"]}, "url": "", "version": "1.1.0"}}}, "master": {"tf2_serving": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "tf2 image classification server", "doc": "", "example": "tf2_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "tf2-serving", "platformVersion": "3.5.0", "spec": {"filename": "tf2_serving.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": ["requests", "pillow", "tensorflow>=2.1"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "tf2 image classification server", "doc": "", "example": "tf2_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "tf2-serving", "platformVersion": "3.5.0", "spec": {"filename": "tf2_serving.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": ["requests", "pillow", "tensorflow>=2.1"]}, "url": "", "version": "1.1.0"}}, "load_dataset": {"latest": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "load a toy dataset from scikit-learn", "doc": "README.md", "example": "load_dataset.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.6.0", "name": "load-dataset", "platformVersion": "3.5.5", "spec": {"filename": "load_dataset.py", "handler": "load_dataset", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "load a toy dataset from scikit-learn", "doc": "README.md", "example": "load_dataset.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.6.0", "name": "load-dataset", "platformVersion": "3.5.5", "spec": {"filename": "load_dataset.py", "handler": "load_dataset", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "model_server_tester": {"latest": {"apiVersion": "v1", "categories": ["monitoring", "model-serving"], "description": "test model servers", "doc": "", "example": "model_server_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "model-server-tester", "platformVersion": "3.5.0", "spec": {"filename": "model_server_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["monitoring", "model-serving"], "description": "test model servers", "doc": "", "example": "model_server_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "model-server-tester", "platformVersion": "3.5.0", "spec": {"filename": "model_server_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "feature_selection": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "machine-learning"], "description": "Select features through multiple Statistical and Model filters", "doc": "", "example": "feature_selection.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc40", "name": "feature-selection", "platformVersion": "3.6.0", "spec": {"filename": "feature_selection.py", "handler": "feature_selection", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.6.0"}, "1.6.0": {"apiVersion": "v1", "categories": ["data-preparation", "machine-learning"], "description": "Select features through multiple Statistical and Model filters", "doc": "", "example": "feature_selection.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc40", "name": "feature-selection", "platformVersion": "3.6.0", "spec": {"filename": "feature_selection.py", "handler": "feature_selection", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.6.0"}}, "aggregate": {"latest": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "Rolling aggregation over Metrics and Lables according to specifications", "doc": "", "example": "aggregate.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "aggregate", "platformVersion": "3.5.4", "spec": {"filename": "aggregate.py", "handler": "aggregate", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["data-preparation"], "description": "Rolling aggregation over Metrics and Lables according to specifications", "doc": "", "example": "aggregate.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "aggregate", "platformVersion": "3.5.4", "spec": {"filename": "aggregate.py", "handler": "aggregate", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}}, "describe": {"latest": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "describe and visualizes dataset stats", "doc": "", "example": "describe.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "describe", "platformVersion": "3.5.3", "spec": {"filename": "describe.py", "handler": "analyze", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "describe and visualizes dataset stats", "doc": "", "example": "describe.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "describe", "platformVersion": "3.5.3", "spec": {"filename": "describe.py", "handler": "analyze", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.4.0"}}, "model_server": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "model-server", "platformVersion": "3.5.0", "spec": {"filename": "model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "model-server", "platformVersion": "3.5.0", "spec": {"filename": "model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "nuclio:serving", "requirements": []}, "url": "", "version": "1.2.0"}}, "describe_spark": {"latest": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "", "doc": "", "example": "describe_spark.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "describe-spark", "platformVersion": "3.5.0", "spec": {"filename": "describe_spark.py", "handler": "describe_spark", "image": "iguazio/shell:3.0_b5565_20201026062233_wsdf", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["data-analysis"], "description": "", "doc": "", "example": "describe_spark.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "describe-spark", "platformVersion": "3.5.0", "spec": {"filename": "describe_spark.py", "handler": "describe_spark", "image": "iguazio/shell:3.0_b5565_20201026062233_wsdf", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "gen_class_data": {"latest": {"apiVersion": "v1", "categories": ["data-generation"], "description": "Create a binary classification sample dataset and save.", "doc": "", "example": "gen_class_data.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "gen_class_data", "platformVersion": "3.5.3", "spec": {"filename": "gen_class_data.py", "handler": "gen_class_data", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["data-generation"], "description": "Create a binary classification sample dataset and save.", "doc": "", "example": "gen_class_data.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "gen_class_data", "platformVersion": "3.5.3", "spec": {"filename": "gen_class_data.py", "handler": "gen_class_data", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.3.0"}}, "open_archive": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "Open a file/object archive into a target directory", "doc": "", "example": "open_archive.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc50", "name": "open-archive", "platformVersion": "3.5.0", "spec": {"filename": "open_archive.py", "handler": "open_archive", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["utils"], "description": "Open a file/object archive into a target directory", "doc": "", "example": "open_archive.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0-rc50", "name": "open-archive", "platformVersion": "3.5.0", "spec": {"filename": "open_archive.py", "handler": "open_archive", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "send_email": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "Send Email messages through SMTP server", "doc": "", "example": "send_email.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.4.1", "name": "send-email", "platformVersion": "3.5.3", "spec": {"filename": "send_email.py", "handler": "send_email", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["utils"], "description": "Send Email messages through SMTP server", "doc": "", "example": "send_email.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.4.1", "name": "send-email", "platformVersion": "3.5.3", "spec": {"filename": "send_email.py", "handler": "send_email", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.2.0"}}, "v2_model_tester": {"latest": {"apiVersion": "v1", "categories": ["model-testing", "machine-learning"], "description": "test v2 model servers", "doc": "", "example": "v2_model_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-tester", "platformVersion": "3.5.0", "spec": {"filename": "v2_model_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-testing", "machine-learning"], "description": "test v2 model servers", "doc": "", "example": "v2_model_tester.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-tester", "platformVersion": "3.5.0", "spec": {"filename": "v2_model_tester.py", "handler": "model_server_tester", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "arc_to_parquet": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "retrieve remote archive, open and save as parquet", "doc": "", "example": "arc_to_parquet.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "arc-to-parquet", "platformVersion": "3.5.4", "spec": {"filename": "arc_to_parquet.py", "handler": "arc_to_parquet", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.5.0"}, "1.5.0": {"apiVersion": "v1", "categories": ["utils"], "description": "retrieve remote archive, open and save as parquet", "doc": "", "example": "arc_to_parquet.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "arc-to-parquet", "platformVersion": "3.5.4", "spec": {"filename": "arc_to_parquet.py", "handler": "arc_to_parquet", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.5.0"}}, "github_utils": {"latest": {"apiVersion": "v1", "categories": ["utils"], "description": "add comments to github pull request", "doc": "", "example": "github_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "github-utils", "platformVersion": "3.5.0", "spec": {"filename": "github_utils.py", "handler": "run_summary_comment", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["utils"], "description": "add comments to github pull request", "doc": "", "example": "github_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "github-utils", "platformVersion": "3.5.0", "spec": {"filename": "github_utils.py", "handler": "run_summary_comment", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.1.0"}}, "v2_model_server": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "v2_model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-server", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "ClassifierModel"}, "filename": "v2_model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": []}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["model-serving", "machine-learning"], "description": "generic sklearn model server", "doc": "", "example": "v2_model_server.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio", "framework": "sklearn"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "v2-model-server", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "ClassifierModel"}, "filename": "v2_model_server.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": []}, "url": "", "version": "1.2.0"}}, "onnx_utils": {"latest": {"apiVersion": "v1", "categories": ["utils", "deep-learning"], "description": "ONNX intigration in MLRun, some utils functions for the ONNX framework, optimizing and converting models from different framework to ONNX using MLRun.", "doc": "", "example": "onnx_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.2", "name": "onnx_utils", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "with_mlrun": false}}, "filename": "onnx_utils.py", "handler": "to_onnx", "image": "mlrun/mlrun", "kind": "job", "requirements": ["tqdm~=4.67.1", "tensorflow~=2.19.0", "tf_keras~=2.19.0", "torch~=2.6.0", "torchvision~=0.21.0", "onnx~=1.17.0", "onnxruntime~=1.19.2", "onnxoptimizer~=0.3.13", "onnxmltools~=1.13.0", "tf2onnx~=1.16.1", "plotly~=5.23"]}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["utils", "deep-learning"], "description": "ONNX intigration in MLRun, some utils functions for the ONNX framework, optimizing and converting models from different framework to ONNX using MLRun.", "doc": "", "example": "onnx_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.2", "name": "onnx_utils", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "with_mlrun": false}}, "filename": "onnx_utils.py", "handler": "to_onnx", "image": "mlrun/mlrun", "kind": "job", "requirements": ["tqdm~=4.67.1", "tensorflow~=2.19.0", "tf_keras~=2.19.0", "torch~=2.6.0", "torchvision~=0.21.0", "onnx~=1.17.0", "onnxruntime~=1.19.2", "onnxoptimizer~=0.3.13", "onnxmltools~=1.13.0", "tf2onnx~=1.16.1", "plotly~=5.23"]}, "url": "", "version": "1.3.0"}}, "azureml_utils": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Azure AutoML integration in MLRun, including utils functions for training models on Azure AutoML platfrom.", "doc": "", "example": "azureml_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "azureml_utils", "platformVersion": "3.5.3", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "commands": ["apt-get update && apt-get install -y --no-install-recommends git", "apt install -y liblttng-ust0"], "with_mlrun": true}}, "filename": "azureml_utils.py", "handler": "train", "image": "python:3.9-bullseye", "kind": "job", "requirements": ["azureml-core==1.54.0.post1", "azureml-train-automl-client==1.54.0.post1", "plotly~=5.23"]}, "url": "", "version": "1.4.0", "test_valid": true}, "1.4.0": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Azure AutoML integration in MLRun, including utils functions for training models on Azure AutoML platfrom.", "doc": "", "example": "azureml_utils.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "azureml_utils", "platformVersion": "3.5.3", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": true, "commands": ["apt-get update && apt-get install -y --no-install-recommends git", "apt install -y liblttng-ust0"], "with_mlrun": true}}, "filename": "azureml_utils.py", "handler": "train", "image": "python:3.9-bullseye", "kind": "job", "requirements": ["azureml-core==1.54.0.post1", "azureml-train-automl-client==1.54.0.post1", "plotly~=5.23"]}, "url": "", "version": "1.4.0", "test_valid": true}}, "auto_trainer": {"latest": {"apiVersion": "v1", "categories": ["machine-learning", "model-training"], "description": "Automatic train, evaluate and predict functions for the ML frameworks - Scikit-Learn, XGBoost and LightGBM.", "doc": "", "example": "auto_trainer.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "auto_trainer", "platformVersion": "3.5.0", "spec": {"filename": "auto_trainer.py", "handler": "train", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.8.0"}, "1.8.0": {"apiVersion": "v1", "categories": ["machine-learning", "model-training"], "description": "Automatic train, evaluate and predict functions for the ML frameworks - Scikit-Learn, XGBoost and LightGBM.", "doc": "", "example": "auto_trainer.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "auto_trainer", "platformVersion": "3.5.0", "spec": {"filename": "auto_trainer.py", "handler": "train", "image": "mlrun/mlrun", "kind": "job", "requirements": []}, "url": "", "version": "1.8.0"}}, "azureml_serving": {"latest": {"apiVersion": "v1", "categories": ["machine-learning", "model-serving"], "description": "AzureML serving function", "doc": "", "example": "azureml_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "azureml_serving", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "mlrun.frameworks.sklearn.PickleModelServer"}, "filename": "azureml_serving.py", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["azureml-automl-runtime~=1.38.1"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["machine-learning", "model-serving"], "description": "AzureML serving function", "doc": "", "example": "azureml_serving.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "azureml_serving", "platformVersion": "3.5.0", "spec": {"customFields": {"default_class": "mlrun.frameworks.sklearn.PickleModelServer"}, "filename": "azureml_serving.py", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["azureml-automl-runtime~=1.38.1"]}, "url": "", "version": "1.1.0"}}, "batch_inference": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "batch_inference", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference.py", "handler": "infer", "image": "mlrun/ml-models", "kind": "job", "requirements": null}, "url": "", "version": "1.8.0"}, "1.8.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference.ipynb", "generationDate": "2022-08-28:17-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "batch_inference", "platformVersion": "3.5.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference.py", "handler": "infer", "image": "mlrun/ml-models", "kind": "job", "requirements": null}, "url": "", "version": "1.8.0"}}, "hugging_face_serving": {"latest": {"apiVersion": "v1", "categories": ["genai", "model-serving"], "description": "Generic Hugging Face model server.", "doc": "", "example": "hugging_face_serving.ipynb", "generationDate": "2022-09-05:17-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "hugging_face_serving", "platformVersion": "", "spec": {"customFields": {"default_class": "HuggingFaceModelServer"}, "filename": "hugging_face_serving.py", "handler": "handler", "image": "mlrun/ml-models", "kind": "serving", "requirements": ["transformers==4.21.3", "tensorflow==2.9.2"]}, "url": "", "version": "1.1.0", "test_valid": false}, "1.1.0": {"apiVersion": "v1", "categories": ["genai", "model-serving"], "description": "Generic Hugging Face model server.", "doc": "", "example": "hugging_face_serving.ipynb", "generationDate": "2022-09-05:17-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.1.0", "name": "hugging_face_serving", "platformVersion": "", "spec": {"customFields": {"default_class": "HuggingFaceModelServer"}, "filename": "hugging_face_serving.py", "handler": "handler", "image": "mlrun/ml-models", "kind": "serving", "requirements": ["transformers==4.21.3", "tensorflow==2.9.2"]}, "url": "", "version": "1.1.0", "test_valid": false}}, "question_answering": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "GenAI approach of question answering on a given data", "doc": "", "example": "question_answering.ipynb", "generationDate": "2023-08-07:11-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "question_answering", "platformVersion": "3.5.0", "spec": {"filename": "question_answering.py", "handler": "answer_questions", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "torch", "tqdm"]}, "url": "", "version": "0.5.0"}, "0.5.0": {"apiVersion": "v1", "categories": ["genai"], "description": "GenAI approach of question answering on a given data", "doc": "", "example": "question_answering.ipynb", "generationDate": "2023-08-07:11-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "question_answering", "platformVersion": "3.5.0", "spec": {"filename": "question_answering.py", "handler": "answer_questions", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "torch", "tqdm"]}, "url": "", "version": "0.5.0"}}, "transcribe": {"latest": {"apiVersion": "v1", "categories": ["audio", "genai"], "description": "Transcribe audio files into text files", "doc": "", "example": "transcribe.ipynb", "generationDate": "2023-07-13:11-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "transcribe", "platformVersion": "3.5.3", "spec": {"filename": "transcribe.py", "handler": "transcribe", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "tqdm", "torchaudio", "torch", "accelerate"]}, "url": "", "version": "1.2.0"}, "1.2.0": {"apiVersion": "v1", "categories": ["audio", "genai"], "description": "Transcribe audio files into text files", "doc": "", "example": "transcribe.ipynb", "generationDate": "2023-07-13:11-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "transcribe", "platformVersion": "3.5.3", "spec": {"filename": "transcribe.py", "handler": "transcribe", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "tqdm", "torchaudio", "torch", "accelerate"]}, "url": "", "version": "1.2.0"}}, "pii_recognizer": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "NLP"], "description": "This function is used to recognize PII in a directory of text files", "doc": "", "example": "pii_recognizer.ipynb", "generationDate": "2023-08-15:10-24", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pii-recognizer", "platformVersion": "3.5.3", "spec": {"filename": "pii_recognizer.py", "handler": "recognize_pii", "image": "mlrun/mlrun", "kind": "job", "requirements": ["nltk", "pandas", "presidio-anonymizer", "presidio-analyzer", "torch", "flair@git+https://github.com/flairNLP/flair.git@d4ed67bf663e4066517f00397412510d90043653", "st-annotated-text", "https://huggingface.co/beki/en_spacy_pii_distilbert/resolve/main/en_spacy_pii_distilbert-any-py3-none-any.whl"]}, "url": "", "version": "0.4.0", "test_valid": false}, "0.4.0": {"apiVersion": "v1", "categories": ["data-preparation", "NLP"], "description": "This function is used to recognize PII in a directory of text files", "doc": "", "example": "pii_recognizer.ipynb", "generationDate": "2023-08-15:10-24", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pii-recognizer", "platformVersion": "3.5.3", "spec": {"filename": "pii_recognizer.py", "handler": "recognize_pii", "image": "mlrun/mlrun", "kind": "job", "requirements": ["nltk", "pandas", "presidio-anonymizer", "presidio-analyzer", "torch", "flair@git+https://github.com/flairNLP/flair.git@d4ed67bf663e4066517f00397412510d90043653", "st-annotated-text", "https://huggingface.co/beki/en_spacy_pii_distilbert/resolve/main/en_spacy_pii_distilbert-any-py3-none-any.whl"]}, "url": "", "version": "0.4.0", "test_valid": false}}, "batch_inference_v2": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference_v2.ipynb", "generationDate": "2023-08-07:12-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0-rc51", "name": "batch_inference_v2", "platformVersion": "3.6.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference_v2.py", "handler": "infer", "image": "mlrun/mlrun", "kind": "job", "requirements": null}, "url": "", "version": "2.6.0"}, "2.6.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Batch inference (also knows as prediction) for the common ML frameworks (SciKit-Learn, XGBoost and LightGBM) while performing data drift analysis.", "doc": "", "example": "batch_inference_v2.ipynb", "generationDate": "2023-08-07:12-25", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0-rc51", "name": "batch_inference_v2", "platformVersion": "3.6.0", "spec": {"extra_spec": {"allow_empty_resources": true, "build": {"auto_build": false, "with_mlrun": false}}, "filename": "batch_inference_v2.py", "handler": "infer", "image": "mlrun/mlrun", "kind": "job", "requirements": null}, "url": "", "version": "2.6.0"}}, "translate": {"latest": {"apiVersion": "v1", "categories": ["genai", "NLP"], "description": "Translate text files from one language to another", "doc": "", "example": "translate.ipynb", "generationDate": "2023-12-05:17-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.10.0-rc41", "name": "translate", "platformVersion": "3.5.3", "spec": {"filename": "translate.py", "handler": "translate", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "sentencepiece", "torch>=2.6", "tqdm"]}, "url": "", "version": "0.3.0", "test_valid": true}, "0.3.0": {"apiVersion": "v1", "categories": ["genai", "NLP"], "description": "Translate text files from one language to another", "doc": "", "example": "translate.ipynb", "generationDate": "2023-12-05:17-20", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.10.0-rc41", "name": "translate", "platformVersion": "3.5.3", "spec": {"filename": "translate.py", "handler": "translate", "image": "mlrun/mlrun", "kind": "job", "requirements": ["transformers", "sentencepiece", "torch>=2.6", "tqdm"]}, "url": "", "version": "0.3.0", "test_valid": true}}, "structured_data_generator": {"latest": {"apiVersion": "v1", "categories": ["data-generation", "genai"], "description": "GenAI approach of generating structured data according to a given schema", "doc": "", "example": "structured_data_generator.ipynb", "generationDate": "2023-12-14:10-50", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "structured_data_generator", "platformVersion": "3.5.5", "spec": {"filename": "structured_data_generator.py", "handler": "generate_data", "image": "mlrun/mlrun", "kind": "job", "requirements": ["langchain", "tqdm"]}, "url": "", "version": "1.6.0"}, "1.6.0": {"apiVersion": "v1", "categories": ["data-generation", "genai"], "description": "GenAI approach of generating structured data according to a given schema", "doc": "", "example": "structured_data_generator.ipynb", "generationDate": "2023-12-14:10-50", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "structured_data_generator", "platformVersion": "3.5.5", "spec": {"filename": "structured_data_generator.py", "handler": "generate_data", "image": "mlrun/mlrun", "kind": "job", "requirements": ["langchain", "tqdm"]}, "url": "", "version": "1.6.0"}}, "text_to_audio_generator": {"latest": {"apiVersion": "v1", "categories": ["data-generation", "audio"], "description": "Generate audio file from text using different speakers", "doc": "", "example": "text_to_audio_generator.ipynb", "generationDate": "2023-12-03:15-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.1", "name": "text_to_audio_generator", "platformVersion": "3.5.3", "spec": {"filename": "text_to_audio_generator.py", "handler": "generate_multi_speakers_audio", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torchaudio", "pydub"]}, "url": "", "version": "1.3.0", "test_valid": false}, "1.3.0": {"apiVersion": "v1", "categories": ["data-generation", "audio"], "description": "Generate audio file from text using different speakers", "doc": "", "example": "text_to_audio_generator.ipynb", "generationDate": "2023-12-03:15-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.1", "name": "text_to_audio_generator", "platformVersion": "3.5.3", "spec": {"filename": "text_to_audio_generator.py", "handler": "generate_multi_speakers_audio", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torchaudio", "pydub"]}, "url": "", "version": "1.3.0", "test_valid": false}}, "silero_vad": {"latest": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "Silero VAD (Voice Activity Detection) functions.", "doc": "", "example": "silero_vad.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "silero_vad", "platformVersion": "3.5.3", "spec": {"filename": "silero_vad.py", "handler": "detect_voice", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torch", "torchaudio", "tqdm", "onnxruntime"]}, "url": "", "version": "1.4.0"}, "1.4.0": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "Silero VAD (Voice Activity Detection) functions.", "doc": "", "example": "silero_vad.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "silero_vad", "platformVersion": "3.5.3", "spec": {"filename": "silero_vad.py", "handler": "detect_voice", "image": "mlrun/mlrun", "kind": "job", "requirements": ["torch", "torchaudio", "tqdm", "onnxruntime"]}, "url": "", "version": "1.4.0"}}, "pyannote_audio": {"latest": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "pyannote's speech diarization of audio files", "doc": "", "example": "pyannote_audio.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pyannote-audio", "platformVersion": "3.5.3", "spec": {"filename": "pyannote_audio.py", "handler": "diarize", "image": "mlrun/mlrun-gpu", "kind": "job", "requirements": ["pyannote.audio", "pyannote.core", "torchaudio", "tqdm"]}, "url": "", "version": "1.3.0"}, "1.3.0": {"apiVersion": "v1", "categories": ["deep-learning", "audio"], "description": "pyannote's speech diarization of audio files", "doc": "", "example": "pyannote_audio.ipynb", "generationDate": "2023-12-03:14-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.7.0", "name": "pyannote-audio", "platformVersion": "3.5.3", "spec": {"filename": "pyannote_audio.py", "handler": "diarize", "image": "mlrun/mlrun-gpu", "kind": "job", "requirements": ["pyannote.audio", "pyannote.core", "torchaudio", "tqdm"]}, "url": "", "version": "1.3.0"}}, "mlflow_utils": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Mlflow model server, and additional utils.", "doc": "", "example": "mlflow_utils.ipynb", "generationDate": "2024-05-23:12-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "mlflow_utils", "platformVersion": "", "spec": {"customFields": {"default_class": "MLFlowModelServer"}, "filename": "mlflow_utils.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["mlflow~=2.22", "lightgbm", "xgboost"]}, "url": "", "version": "1.1.0"}, "1.1.0": {"apiVersion": "v1", "categories": ["model-serving", "utils"], "description": "Mlflow model server, and additional utils.", "doc": "", "example": "mlflow_utils.ipynb", "generationDate": "2024-05-23:12-00", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "marketplaceType": "", "mlrunVersion": "1.8.0", "name": "mlflow_utils", "platformVersion": "", "spec": {"customFields": {"default_class": "MLFlowModelServer"}, "filename": "mlflow_utils.py", "handler": "handler", "image": "mlrun/mlrun", "kind": "serving", "requirements": ["mlflow~=2.22", "lightgbm", "xgboost"]}, "url": "", "version": "1.1.0"}}, "noise_reduction": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "audio"], "description": "Reduce noise from audio files", "doc": "", "example": "noise_reduction.ipynb", "generationDate": "2024-03-04:17-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "mlrunVersion": "1.7.0", "name": "noise-reduction", "platformVersion": "3.5.3", "spec": {"filename": "noise_reduction.py", "handler": "reduce_noise", "image": "mlrun/mlrun", "kind": "job", "requirements": ["librosa", "noisereduce", "deepfilternet", "torchaudio>=2.1.2"]}, "url": "", "version": "1.1.0", "test_valid": false}, "1.1.0": {"apiVersion": "v1", "categories": ["data-preparation", "audio"], "description": "Reduce noise from audio files", "doc": "", "example": "noise_reduction.ipynb", "generationDate": "2024-03-04:17-30", "hidden": false, "icon": "", "labels": {"author": "Iguazio"}, "maintainers": [], "mlrunVersion": "1.7.0", "name": "noise-reduction", "platformVersion": "3.5.3", "spec": {"filename": "noise_reduction.py", "handler": "reduce_noise", "image": "mlrun/mlrun", "kind": "job", "requirements": ["librosa", "noisereduce", "deepfilternet", "torchaudio>=2.1.2"]}, "url": "", "version": "1.1.0", "test_valid": false}}}}, "modules": {"development": {"count_events": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}}, "histogram_data_drift": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0"}}, "openai_proxy_app": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0"}}, "evidently_iris": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0"}}, "agent_deployer": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}}, "vllm_module": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.", "example": "vllm_module.ipynb", "generationDate": "2025-12-17:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "vllm_module", "spec": {"filename": "vllm_module.py", "image": "mlrun/mlrun", "kind": "generic"}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.", "example": "vllm_module.ipynb", "generationDate": "2025-12-17:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "vllm_module", "spec": {"filename": "vllm_module.py", "image": "mlrun/mlrun", "kind": "generic"}, "version": "1.0.0"}}}, "master": {"count_events": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}}, "histogram_data_drift": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0"}}, "openai_proxy_app": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0"}}, "evidently_iris": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0"}}, "agent_deployer": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0"}}, "vllm_module": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.", "example": "vllm_module.ipynb", "generationDate": "2025-12-17:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "vllm_module", "spec": {"filename": "vllm_module.py", "image": "mlrun/mlrun", "kind": "generic"}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.", "example": "vllm_module.ipynb", "generationDate": "2025-12-17:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "vllm_module", "spec": {"filename": "vllm_module.py", "image": "mlrun/mlrun", "kind": "generic"}, "version": "1.0.0"}}}}, "steps": {"development": {"verify_schema": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "model-serving", "utilities"], "description": "Verifies the event is aligned with the provided schema", "example": "verify_schema.ipynb", "generationDate": "2025-12-29:11-59", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "verify_schema", "className": "VerifySchema", "defaultHandler": null, "spec": {"filename": "verify_schema.py", "image": "mlrun/mlrun", "requirements": null}, "version": "1.0.0"}, "1.0.0": {"apiVersion": "v1", "categories": ["data-preparation", "model-serving", "utilities"], "description": "Verifies the event is aligned with the provided schema", "example": "verify_schema.ipynb", "generationDate": "2025-12-29:11-59", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "verify_schema", "className": "VerifySchema", "defaultHandler": null, "spec": {"filename": "verify_schema.py", "image": "mlrun/mlrun", "requirements": null}, "version": "1.0.0"}}}, "master": {}}}
\ No newline at end of file
diff --git a/functions/development/tags.json b/functions/development/tags.json
index 31c481ca..47524bb0 100644
--- a/functions/development/tags.json
+++ b/functions/development/tags.json
@@ -1 +1 @@
-{"categories": ["NLP", "monitoring", "deep-learning", "audio", "utils", "machine-learning", "model-serving", "model-testing", "data-analysis", "genai", "model-training", "data-preparation", "data-generation"], "kind": ["job", "serving", "nuclio:serving"]}
\ No newline at end of file
+{"kind": ["nuclio:serving", "job", "serving"], "categories": ["utils", "genai", "deep-learning", "NLP", "model-serving", "machine-learning", "data-generation", "monitoring", "audio", "model-testing", "data-preparation", "model-training", "data-analysis"]}
\ No newline at end of file
diff --git a/modules/development/agent_deployer/1.0.0/src/agent_deployer.ipynb b/modules/development/agent_deployer/1.0.0/src/agent_deployer.ipynb
index 944dba11..98531ecd 100644
--- a/modules/development/agent_deployer/1.0.0/src/agent_deployer.ipynb
+++ b/modules/development/agent_deployer/1.0.0/src/agent_deployer.ipynb
@@ -10,18 +10,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
    "id": "be42e7c5-b2af-476f-8041-c17be56edb52",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "> 2025-12-03 07:17:36,530 [info] Project loaded successfully: {\"project_name\":\"langchain-example-10\"}\n"
-     ]
-    }
-   ],
    "source": [
     "%config Completer.use_jedi = False\n",
     "\n",
@@ -31,7 +21,9 @@
     "image = \"mlrun/mlrun\"\n",
     "project_name = \"langchain-example\"\n",
     "project = get_or_create_project(project_name, context=\"./\", allow_cross_project=True)"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "cell_type": "markdown",
@@ -43,17 +35,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
    "id": "a47d7789-2ea2-493e-8905-f53b978e2abd",
    "metadata": {},
-   "outputs": [],
    "source": [
     "# Create project secrets for project\n",
     "secrets = {\"OPENAI_API_KEY\": \"\", # add your OpenAI API key here\n",
     "          \"OPENAI_BASE_URL\": \"\" # add your OpenAI base url here if needed\n",
     "          }\n",
     "project.set_secrets(secrets=secrets, provider=\"kubernetes\")"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "cell_type": "markdown",
@@ -65,10 +57,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
    "id": "25cbd982-86de-43b5-91ef-24fc60b2d758",
    "metadata": {},
-   "outputs": [],
    "source": [
     "%%writefile langchain_model.py\n",
     "\n",
@@ -197,7 +187,9 @@
     "        result[\"total_cost_usd\"] = input_cost + output_cost\n",
     "        return result\n",
     "            "
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "cell_type": "markdown",
@@ -209,20 +201,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
    "id": "691e9068-ec9c-40d6-9ac8-e6c3e605b44c",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "> 2025-12-03 10:55:46,194 [info] Project loaded successfully: {\"project_name\":\"langchain-example-10\"}\n",
-      "> 2025-12-03 10:55:46,463 [info] Model monitoring credentials were set successfully. Please keep in mind that if you already had model monitoring functions / model monitoring infra / tracked model server deployed on your project, you will need to redeploy them. For redeploying the model monitoring infra, first disable it using `project.disable_model_monitoring()` and then enable it using `project.enable_model_monitoring()`.\n",
-      "details: MLRunConflictError(\"The following model-montioring infrastructure functions are already deployed, aborting: ['model-monitoring-controller', 'model-monitoring-writer']\\nIf you want to redeploy the model-monitoring controller (maybe with different base-period), use update_model_monitoring_controller.If you want to redeploy all of model-monitoring infrastructure, call disable_model_monitoringbefore calling enable_model_monitoring again.\")\n"
-     ]
-    }
-   ],
    "source": [
     "module = mlrun.import_module(\"hub://agent_deployer\")\n",
     "\n",
@@ -237,11 +217,11 @@
     "            prompt_template= \"\"\"\n",
     "            Answer the following questions as best you can.\n",
     "            You have access to the following tools:\n",
-    "            {tools}\n",
+    "            {{tools}}\n",
     "            Use the following format:\n",
     "            Question: the input question you must answer\n",
     "            Thought: you should always think about what to do\n",
-    "            Action: the action to take, should be one of [{tool_names}]\n",
+    "            Action: the action to take, should be one of [{{tool_names}}]\n",
     "            Action Input: the input to the action\n",
     "            Observation: the result of the action\n",
     "            ... (this Thought/Action/Action Input/Observation can repeat N times)\n",
@@ -252,16 +232,18 @@
     "            Question: {input}\n",
     "            Thought:{agent_scratchpad}\n",
     "            \"\"\",\n",
-    ")"
-   ]
+    ")\n"
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
    "id": "0bb1c4d1-5d7c-4d1c-bf51-8f53b319e91f",
    "metadata": {},
+   "source": "func = agent.deploy_function(enable_tracking=True)",
    "outputs": [],
-   "source": "func = agent.deploy_function(enable_tracking=True)"
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -272,10 +254,10 @@
   {
    "metadata": {},
    "cell_type": "code",
+   "source": "func.invoke(\"./\", {\"question\" : \"If a pizza costs $18.75 and I want to buy 3, what is the total cost?\"})",
+   "id": "ac5c3ba174d2cf8b",
    "outputs": [],
-   "execution_count": null,
-   "source": "func.invoke(\"./\", {\"question\" : \"If a pizza costs $18.75 and I want to buy 3, plus a 15% tip, what is the total cost?\"})",
-   "id": "ac5c3ba174d2cf8b"
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -289,8 +271,6 @@
   {
    "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": [
     "%%writefile monitoring_application.py\n",
     "\n",
@@ -405,7 +385,9 @@
     "            value=value,\n",
     "        )\n"
    ],
-   "id": "377487422f5ed289"
+   "id": "377487422f5ed289",
+   "outputs": [],
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -416,8 +398,6 @@
   {
    "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": [
     "llm_monitoring_app = project.set_model_monitoring_function(\n",
     "    func=\"monitoring_application.py\",\n",
@@ -428,7 +408,9 @@
     "\n",
     "project.deploy_function(llm_monitoring_app)"
    ],
-   "id": "9d6ad2a4a47a44bd"
+   "id": "9d6ad2a4a47a44bd",
+   "outputs": [],
+   "execution_count": null
   }
  ],
  "metadata": {
diff --git a/modules/development/agent_deployer/1.0.0/static/example.html b/modules/development/agent_deployer/1.0.0/static/example.html
index f4062a13..c6798e77 100644
--- a/modules/development/agent_deployer/1.0.0/static/example.html
+++ b/modules/development/agent_deployer/1.0.0/static/example.html
@@ -193,11 +193,6 @@ <h1>Configure mlrun project:<a class="headerlink" href="#configure-mlrun-project
 </pre></div>
 </div>
 </div>
-<div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&gt; 2025-12-03 07:17:36,530 [info] Project loaded successfully: {"project_name":"langchain-example-10"}
-</pre></div>
-</div>
-</div>
 </div>
 </section>
 <section id="create-openai-secret">
@@ -367,11 +362,11 @@ <h1>Import the module from the hub:<a class="headerlink" href="#import-the-modul
             <span class="n">prompt_template</span><span class="o">=</span> <span class="s2">"""</span>
 <span class="s2">            Answer the following questions as best you can.</span>
 <span class="s2">            You have access to the following tools:</span>
-<span class="s2">            </span><span class="si">{tools}</span>
+<span class="s2">            {{tools}}</span>
 <span class="s2">            Use the following format:</span>
 <span class="s2">            Question: the input question you must answer</span>
 <span class="s2">            Thought: you should always think about what to do</span>
-<span class="s2">            Action: the action to take, should be one of [</span><span class="si">{tool_names}</span><span class="s2">]</span>
+<span class="s2">            Action: the action to take, should be one of [{{tool_names}}]</span>
 <span class="s2">            Action Input: the input to the action</span>
 <span class="s2">            Observation: the result of the action</span>
 <span class="s2">            ... (this Thought/Action/Action Input/Observation can repeat N times)</span>
@@ -386,13 +381,6 @@ <h1>Import the module from the hub:<a class="headerlink" href="#import-the-modul
 </pre></div>
 </div>
 </div>
-<div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&gt; 2025-12-03 10:55:46,194 [info] Project loaded successfully: {"project_name":"langchain-example-10"}
-&gt; 2025-12-03 10:55:46,463 [info] Model monitoring credentials were set successfully. Please keep in mind that if you already had model monitoring functions / model monitoring infra / tracked model server deployed on your project, you will need to redeploy them. For redeploying the model monitoring infra, first disable it using `project.disable_model_monitoring()` and then enable it using `project.enable_model_monitoring()`.
-details: MLRunConflictError("The following model-montioring infrastructure functions are already deployed, aborting: ['model-monitoring-controller', 'model-monitoring-writer']\nIf you want to redeploy the model-monitoring controller (maybe with different base-period), use update_model_monitoring_controller.If you want to redeploy all of model-monitoring infrastructure, call disable_model_monitoringbefore calling enable_model_monitoring again.")
-</pre></div>
-</div>
-</div>
 </div>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
@@ -406,7 +394,7 @@ <h1>Import the module from the hub:<a class="headerlink" href="#import-the-modul
 <h1>Invoke the deployed agent:<a class="headerlink" href="#invoke-the-deployed-agent" title="Link to this heading">#</a></h1>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">func</span><span class="o">.</span><span class="n">invoke</span><span class="p">(</span><span class="s2">"./"</span><span class="p">,</span> <span class="p">{</span><span class="s2">"question"</span> <span class="p">:</span> <span class="s2">"If a pizza costs $18.75 and I want to buy 3, plus a 15% tip, what is the total cost?"</span><span class="p">})</span>
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">func</span><span class="o">.</span><span class="n">invoke</span><span class="p">(</span><span class="s2">"./"</span><span class="p">,</span> <span class="p">{</span><span class="s2">"question"</span> <span class="p">:</span> <span class="s2">"If a pizza costs $18.75 and I want to buy 3, what is the total cost?"</span><span class="p">})</span>
 </pre></div>
 </div>
 </div>
diff --git a/modules/development/agent_deployer/latest/src/agent_deployer.ipynb b/modules/development/agent_deployer/latest/src/agent_deployer.ipynb
index 944dba11..98531ecd 100644
--- a/modules/development/agent_deployer/latest/src/agent_deployer.ipynb
+++ b/modules/development/agent_deployer/latest/src/agent_deployer.ipynb
@@ -10,18 +10,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
    "id": "be42e7c5-b2af-476f-8041-c17be56edb52",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "> 2025-12-03 07:17:36,530 [info] Project loaded successfully: {\"project_name\":\"langchain-example-10\"}\n"
-     ]
-    }
-   ],
    "source": [
     "%config Completer.use_jedi = False\n",
     "\n",
@@ -31,7 +21,9 @@
     "image = \"mlrun/mlrun\"\n",
     "project_name = \"langchain-example\"\n",
     "project = get_or_create_project(project_name, context=\"./\", allow_cross_project=True)"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "cell_type": "markdown",
@@ -43,17 +35,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
    "id": "a47d7789-2ea2-493e-8905-f53b978e2abd",
    "metadata": {},
-   "outputs": [],
    "source": [
     "# Create project secrets for project\n",
     "secrets = {\"OPENAI_API_KEY\": \"\", # add your OpenAI API key here\n",
     "          \"OPENAI_BASE_URL\": \"\" # add your OpenAI base url here if needed\n",
     "          }\n",
     "project.set_secrets(secrets=secrets, provider=\"kubernetes\")"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "cell_type": "markdown",
@@ -65,10 +57,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
    "id": "25cbd982-86de-43b5-91ef-24fc60b2d758",
    "metadata": {},
-   "outputs": [],
    "source": [
     "%%writefile langchain_model.py\n",
     "\n",
@@ -197,7 +187,9 @@
     "        result[\"total_cost_usd\"] = input_cost + output_cost\n",
     "        return result\n",
     "            "
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "cell_type": "markdown",
@@ -209,20 +201,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
    "id": "691e9068-ec9c-40d6-9ac8-e6c3e605b44c",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "> 2025-12-03 10:55:46,194 [info] Project loaded successfully: {\"project_name\":\"langchain-example-10\"}\n",
-      "> 2025-12-03 10:55:46,463 [info] Model monitoring credentials were set successfully. Please keep in mind that if you already had model monitoring functions / model monitoring infra / tracked model server deployed on your project, you will need to redeploy them. For redeploying the model monitoring infra, first disable it using `project.disable_model_monitoring()` and then enable it using `project.enable_model_monitoring()`.\n",
-      "details: MLRunConflictError(\"The following model-montioring infrastructure functions are already deployed, aborting: ['model-monitoring-controller', 'model-monitoring-writer']\\nIf you want to redeploy the model-monitoring controller (maybe with different base-period), use update_model_monitoring_controller.If you want to redeploy all of model-monitoring infrastructure, call disable_model_monitoringbefore calling enable_model_monitoring again.\")\n"
-     ]
-    }
-   ],
    "source": [
     "module = mlrun.import_module(\"hub://agent_deployer\")\n",
     "\n",
@@ -237,11 +217,11 @@
     "            prompt_template= \"\"\"\n",
     "            Answer the following questions as best you can.\n",
     "            You have access to the following tools:\n",
-    "            {tools}\n",
+    "            {{tools}}\n",
     "            Use the following format:\n",
     "            Question: the input question you must answer\n",
     "            Thought: you should always think about what to do\n",
-    "            Action: the action to take, should be one of [{tool_names}]\n",
+    "            Action: the action to take, should be one of [{{tool_names}}]\n",
     "            Action Input: the input to the action\n",
     "            Observation: the result of the action\n",
     "            ... (this Thought/Action/Action Input/Observation can repeat N times)\n",
@@ -252,16 +232,18 @@
     "            Question: {input}\n",
     "            Thought:{agent_scratchpad}\n",
     "            \"\"\",\n",
-    ")"
-   ]
+    ")\n"
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
    "id": "0bb1c4d1-5d7c-4d1c-bf51-8f53b319e91f",
    "metadata": {},
+   "source": "func = agent.deploy_function(enable_tracking=True)",
    "outputs": [],
-   "source": "func = agent.deploy_function(enable_tracking=True)"
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -272,10 +254,10 @@
   {
    "metadata": {},
    "cell_type": "code",
+   "source": "func.invoke(\"./\", {\"question\" : \"If a pizza costs $18.75 and I want to buy 3, what is the total cost?\"})",
+   "id": "ac5c3ba174d2cf8b",
    "outputs": [],
-   "execution_count": null,
-   "source": "func.invoke(\"./\", {\"question\" : \"If a pizza costs $18.75 and I want to buy 3, plus a 15% tip, what is the total cost?\"})",
-   "id": "ac5c3ba174d2cf8b"
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -289,8 +271,6 @@
   {
    "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": [
     "%%writefile monitoring_application.py\n",
     "\n",
@@ -405,7 +385,9 @@
     "            value=value,\n",
     "        )\n"
    ],
-   "id": "377487422f5ed289"
+   "id": "377487422f5ed289",
+   "outputs": [],
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -416,8 +398,6 @@
   {
    "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": [
     "llm_monitoring_app = project.set_model_monitoring_function(\n",
     "    func=\"monitoring_application.py\",\n",
@@ -428,7 +408,9 @@
     "\n",
     "project.deploy_function(llm_monitoring_app)"
    ],
-   "id": "9d6ad2a4a47a44bd"
+   "id": "9d6ad2a4a47a44bd",
+   "outputs": [],
+   "execution_count": null
   }
  ],
  "metadata": {
diff --git a/modules/development/agent_deployer/latest/static/example.html b/modules/development/agent_deployer/latest/static/example.html
index f4062a13..c6798e77 100644
--- a/modules/development/agent_deployer/latest/static/example.html
+++ b/modules/development/agent_deployer/latest/static/example.html
@@ -193,11 +193,6 @@ <h1>Configure mlrun project:<a class="headerlink" href="#configure-mlrun-project
 </pre></div>
 </div>
 </div>
-<div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&gt; 2025-12-03 07:17:36,530 [info] Project loaded successfully: {"project_name":"langchain-example-10"}
-</pre></div>
-</div>
-</div>
 </div>
 </section>
 <section id="create-openai-secret">
@@ -367,11 +362,11 @@ <h1>Import the module from the hub:<a class="headerlink" href="#import-the-modul
             <span class="n">prompt_template</span><span class="o">=</span> <span class="s2">"""</span>
 <span class="s2">            Answer the following questions as best you can.</span>
 <span class="s2">            You have access to the following tools:</span>
-<span class="s2">            </span><span class="si">{tools}</span>
+<span class="s2">            {{tools}}</span>
 <span class="s2">            Use the following format:</span>
 <span class="s2">            Question: the input question you must answer</span>
 <span class="s2">            Thought: you should always think about what to do</span>
-<span class="s2">            Action: the action to take, should be one of [</span><span class="si">{tool_names}</span><span class="s2">]</span>
+<span class="s2">            Action: the action to take, should be one of [{{tool_names}}]</span>
 <span class="s2">            Action Input: the input to the action</span>
 <span class="s2">            Observation: the result of the action</span>
 <span class="s2">            ... (this Thought/Action/Action Input/Observation can repeat N times)</span>
@@ -386,13 +381,6 @@ <h1>Import the module from the hub:<a class="headerlink" href="#import-the-modul
 </pre></div>
 </div>
 </div>
-<div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&gt; 2025-12-03 10:55:46,194 [info] Project loaded successfully: {"project_name":"langchain-example-10"}
-&gt; 2025-12-03 10:55:46,463 [info] Model monitoring credentials were set successfully. Please keep in mind that if you already had model monitoring functions / model monitoring infra / tracked model server deployed on your project, you will need to redeploy them. For redeploying the model monitoring infra, first disable it using `project.disable_model_monitoring()` and then enable it using `project.enable_model_monitoring()`.
-details: MLRunConflictError("The following model-montioring infrastructure functions are already deployed, aborting: ['model-monitoring-controller', 'model-monitoring-writer']\nIf you want to redeploy the model-monitoring controller (maybe with different base-period), use update_model_monitoring_controller.If you want to redeploy all of model-monitoring infrastructure, call disable_model_monitoringbefore calling enable_model_monitoring again.")
-</pre></div>
-</div>
-</div>
 </div>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
@@ -406,7 +394,7 @@ <h1>Import the module from the hub:<a class="headerlink" href="#import-the-modul
 <h1>Invoke the deployed agent:<a class="headerlink" href="#invoke-the-deployed-agent" title="Link to this heading">#</a></h1>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">func</span><span class="o">.</span><span class="n">invoke</span><span class="p">(</span><span class="s2">"./"</span><span class="p">,</span> <span class="p">{</span><span class="s2">"question"</span> <span class="p">:</span> <span class="s2">"If a pizza costs $18.75 and I want to buy 3, plus a 15% tip, what is the total cost?"</span><span class="p">})</span>
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">func</span><span class="o">.</span><span class="n">invoke</span><span class="p">(</span><span class="s2">"./"</span><span class="p">,</span> <span class="p">{</span><span class="s2">"question"</span> <span class="p">:</span> <span class="s2">"If a pizza costs $18.75 and I want to buy 3, what is the total cost?"</span><span class="p">})</span>
 </pre></div>
 </div>
 </div>
diff --git a/modules/development/catalog.json b/modules/development/catalog.json
index 1a88d608..3749545b 100644
--- a/modules/development/catalog.json
+++ b/modules/development/catalog.json
@@ -1 +1 @@
-{"count_events": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/count_events.ipynb", "source": "src/count_events.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/count_events.ipynb", "source": "src/count_events.py", "docs": "static/documentation.html"}}}, "histogram_data_drift": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0", "assets": {"example": "src/histogram_data_drift.ipynb", "source": "src/histogram_data_drift.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0", "assets": {"example": "src/histogram_data_drift.ipynb", "source": "src/histogram_data_drift.py", "docs": "static/documentation.html"}}}, "openai_proxy_app": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0", "assets": {"example": "src/openai_proxy_app.ipynb", "source": "src/openai_proxy_app.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0", "assets": {"example": "src/openai_proxy_app.ipynb", "source": "src/openai_proxy_app.py", "docs": "static/documentation.html"}}}, "evidently_iris": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0", "assets": {"example": "src/evidently_iris.ipynb", "source": "src/evidently_iris.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0", "assets": {"example": "src/evidently_iris.ipynb", "source": "src/evidently_iris.py", "docs": "static/documentation.html"}}}, "agent_deployer": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/agent_deployer.ipynb", "source": "src/agent_deployer.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/agent_deployer.ipynb", "source": "src/agent_deployer.py", "docs": "static/documentation.html"}}}}
\ No newline at end of file
+{"count_events": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/count_events.ipynb", "source": "src/count_events.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Count events in each time window", "example": "count_events.ipynb", "generationDate": "2025-09-16:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "count_events", "spec": {"filename": "count_events.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/count_events.ipynb", "source": "src/count_events.py", "docs": "static/documentation.html"}}}, "histogram_data_drift": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0", "assets": {"example": "src/histogram_data_drift.ipynb", "source": "src/histogram_data_drift.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Model-monitoring application for detecting and visualizing data drift", "example": "histogram_data_drift.ipynb", "generationDate": "2025-11-06:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "histogram_data_drift", "spec": {"filename": "histogram_data_drift.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["plotly~=5.23", "pandas"]}, "version": "1.0.0", "assets": {"example": "src/histogram_data_drift.ipynb", "source": "src/histogram_data_drift.py", "docs": "static/documentation.html"}}}, "openai_proxy_app": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0", "assets": {"example": "src/openai_proxy_app.ipynb", "source": "src/openai_proxy_app.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "OpenAI application runtime based on fastapi", "example": "openai_proxy_app.ipynb", "generationDate": "2025-11-11:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "openai_proxy_app", "spec": {"filename": "openai_proxy_app.py", "image": "mlrun/mlrun", "requirements": ["fastapi==0.124.0", "uvicorn[standard]==0.38.0", "gunicorn==23.0.0", "requests==2.32.5"], "kind": "generic"}, "version": "1.0.0", "assets": {"example": "src/openai_proxy_app.ipynb", "source": "src/openai_proxy_app.py", "docs": "static/documentation.html"}}}, "evidently_iris": {"latest": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0", "assets": {"example": "src/evidently_iris.ipynb", "source": "src/evidently_iris.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving", "structured-ML"], "description": "Demonstrates Evidently integration in MLRun for data quality and drift monitoring using the Iris dataset", "example": "evidently_iris.ipynb", "generationDate": "2025-11-09:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0-rc41", "name": "evidently_iris", "spec": {"filename": "evidently_iris.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": ["scikit-learn~=1.5.2", "evidently~=0.7.5", "pandas", "sniffio~=1.3.0"]}, "version": "1.0.0", "assets": {"example": "src/evidently_iris.ipynb", "source": "src/evidently_iris.py", "docs": "static/documentation.html"}}}, "agent_deployer": {"latest": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/agent_deployer.ipynb", "source": "src/agent_deployer.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["model-serving"], "description": "Helper for serving function deploy of an AI agents using MLRun", "example": "agent_deployer.ipynb", "generationDate": "2025-12-07", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "agent_deployer", "spec": {"filename": "agent_deployer.py", "image": "mlrun/mlrun", "kind": "monitoring_application", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/agent_deployer.ipynb", "source": "src/agent_deployer.py", "docs": "static/documentation.html"}}}, "vllm_module": {"latest": {"apiVersion": "v1", "categories": ["genai"], "description": "Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.", "example": "vllm_module.ipynb", "generationDate": "2025-12-17:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "vllm_module", "spec": {"filename": "vllm_module.py", "image": "mlrun/mlrun", "kind": "generic"}, "version": "1.0.0", "assets": {"example": "src/vllm_module.ipynb", "source": "src/vllm_module.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["genai"], "description": "Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.", "example": "vllm_module.ipynb", "generationDate": "2025-12-17:12-25", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "vllm_module", "spec": {"filename": "vllm_module.py", "image": "mlrun/mlrun", "kind": "generic"}, "version": "1.0.0", "assets": {"example": "src/vllm_module.ipynb", "source": "src/vllm_module.py", "docs": "static/documentation.html"}}}}
\ No newline at end of file
diff --git a/modules/development/tags.json b/modules/development/tags.json
index c5b981b0..1a982877 100644
--- a/modules/development/tags.json
+++ b/modules/development/tags.json
@@ -1 +1 @@
-{"categories": ["structured-ML", "genai", "model-serving"], "kind": ["generic", "monitoring_application"]}
\ No newline at end of file
+{"categories": ["model-serving", "genai", "structured-ML"], "kind": ["generic", "monitoring_application"]}
\ No newline at end of file
diff --git a/modules/development/vllm_module/1.0.0/src/item.yaml b/modules/development/vllm_module/1.0.0/src/item.yaml
new file mode 100644
index 00000000..ca684340
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/src/item.yaml
@@ -0,0 +1,16 @@
+apiVersion: v1
+categories:
+- genai
+description: Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.
+example: vllm_module.ipynb
+generationDate: 2025-12-17:12-25
+hidden: false
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0
+name: vllm_module
+spec:
+    filename: vllm_module.py
+    image: mlrun/mlrun
+    kind: generic
+version: 1.0.0
diff --git a/modules/development/vllm_module/1.0.0/src/test_vllm_module.py b/modules/development/vllm_module/1.0.0/src/test_vllm_module.py
new file mode 100644
index 00000000..3a5f422a
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/src/test_vllm_module.py
@@ -0,0 +1,35 @@
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from vllm_module import VLLMModule
+import mlrun
+
+
+class TestVllmModule:
+    """Test suite for VLLMModule class."""
+
+    def setup_method(self):
+        project = mlrun.new_project("vllm", save=False)
+
+        # if your VLLMModule requires node_selector as keyword-only, keep it here
+        self.TestVllmModule = VLLMModule(
+            project,
+            node_selector={"alpha.eksctl.io/nodegroup-name": "added-gpu"},
+        )
+
+    def test_vllm_module(self):
+        assert (
+            type(self.TestVllmModule.vllm_app) == mlrun.runtimes.nuclio.application.application.ApplicationRuntime
+        )
diff --git a/modules/development/vllm_module/1.0.0/src/vllm_module.ipynb b/modules/development/vllm_module/1.0.0/src/vllm_module.ipynb
new file mode 100644
index 00000000..2452dbd2
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/src/vllm_module.ipynb
@@ -0,0 +1,234 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7d551647-dfc2-47da-bc8a-3792af622073",
+   "metadata": {},
+   "source": [
+    "# vLLM Module with MLRun\n",
+    "\n",
+    "This notebook shows how to configure and deploy a vLLM OpenAI compatible server as an MLRun application runtime, then showcases how to send a chat request to it to the vLLM server."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7707b270-30cc-448a-a828-cb93aa28030d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import mlrun\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d5cff681-bfdf-4468-a1d1-2aeadb56065e",
+   "metadata": {},
+   "source": [
+    "## Prerequisite\n",
+    "* At lease one GPU is required for running this notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d5c84798-289f-4b4f-8c1b-f4dd12a3bda5",
+   "metadata": {},
+   "source": [
+    "## What this notebook does\n",
+    "\n",
+    "In this notebook we will:\n",
+    "\n",
+    "- Create or load an **MLRun project**\n",
+    "- Import a custom **vLLM module** from the MLRun Hub\n",
+    "- Deploy a **vLLM OpenAI-compatible server** as an MLRun application runtime\n",
+    "- Configure deployment parameters such as model, GPU count, memory, node selector, port, and log level\n",
+    "- Invoke the deployed service using the `/v1/chat/completions` endpoint\n",
+    "- Parse the response and extract only the assistant’s generated text\n",
+    "\n",
+    "By the end of this notebook, you will have a working vLLM deployment that can be queried directly from a Jupyter notebook using OpenAI-style APIs.\n",
+    "\n",
+    "For more information about [vLLM documentation](https://docs.vllm.ai/en/latest/serving/openai_compatible_server/)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "879ca641-ee35-4682-9995-4eb319d89090",
+   "metadata": {},
+   "source": [
+    "## 1. Create an MLRun project\n",
+    "\n",
+    "In this section we create or load an MLRun project that will own the deployed vLLM application runtime."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6eac263a-17d1-4454-9e19-459dfbe2f231",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "project = mlrun.get_or_create_project(name=\"vllm-module\", context=\"\", user_project=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "da49d335-b704-4fb6-801f-4d07b64f9be6",
+   "metadata": {},
+   "source": [
+    "## 2. Import the vLLM module from the MLRun Hub\n",
+    "\n",
+    "In this section we import the vLLM module from the MLRun Hub so we can instantiate `VLLMModule` and deploy it as an application runtime."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e6d89dee-db58-4c0c-8009-b37020c9599a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vllm = mlrun.import_module(\"hub://vllm-module\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1202ddd5-0ce7-4769-be29-8fc264c1f80e",
+   "metadata": {},
+   "source": [
+    "## 3. Deploy the vLLM application runtime\n",
+    "\n",
+    "Configure the vLLM deployment parameters and deploy the application.\n",
+    "\n",
+    "The returned address is the service URL for the application runtime."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e433123a-e64b-4a7a-8c7f-8165bcdcc6d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize the vLLM app\n",
+    "vllm_module = vllm.VLLMModule(\n",
+    "    project=project,\n",
+    "    node_selector={\"alpha.eksctl.io/nodegroup-name\": \"added-gpu\"},\n",
+    "    name=\"qwen-vllm\",\n",
+    "    image=\"vllm/vllm-openai:latest\",\n",
+    "    model=\"Qwen/Qwen2.5-Omni-3B\",\n",
+    "    gpus=1,\n",
+    "    mem=\"10G\",\n",
+    "    port=8000,\n",
+    "    dtype=\"auto\",\n",
+    "    uvicorn_log_level=\"info\",\n",
+    "    max_tokens = 501,\n",
+    ")\n",
+    "\n",
+    "# Deploy the vLLM app\n",
+    "addr = vllm_module.vllm_app.deploy(with_mlrun=True)\n",
+    "addr"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "06832de3-5c31-43bf-b07b-0e71fb2d072d",
+   "metadata": {},
+   "source": [
+    "## 4. Get the runtime handle\n",
+    "\n",
+    "Fetch the runtime object and invoke the service using `app.invoke(...)`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "102d3fd0-1ee6-49b8-8c86-df742ac1c559",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: get_runtime() method uses to get the MLRun application runtime\n",
+    "app = vllm_module.get_runtime()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "925730c1-0ac5-454b-8fb2-ab8cebb3f3ac",
+   "metadata": {},
+   "source": [
+    "## 5. Send a chat request for testing\n",
+    "\n",
+    "Call the OpenAI compatible endpoint `/v1/chat/completions`, parse the JSON response, and print only the assistant message text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "31bc78d4-1c6f-439c-b894-1522e3a6d3e6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "body = {\n",
+    "    \"model\": vllm_module.model,\n",
+    "    \"messages\": [{\"role\": \"user\", \"content\": \"what are the 3 countries with the most gpu as far as you know\"}],\n",
+    "    \"max_tokens\": vllm_module.max_tokens,     # start smaller for testing\n",
+    "}\n",
+    "\n",
+    "resp = app.invoke(path=\"/v1/chat/completions\", body=body)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "a459d5f8-dad0-4735-94c2-3801d4f94bb5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "assistant:\n",
+      "\n",
+      "As of the most commonly cited estimates, the three countries with the largest GPU capacity for AI workloads are the United States, China, and India.\n"
+     ]
+    }
+   ],
+   "source": [
+    "data = resp\n",
+    "assistant_text = data[\"choices\"][0][\"message\"][\"content\"]\n",
+    "\n",
+    "print(\"\\nassistant:\\n\")\n",
+    "print(assistant_text.strip())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "957b5d21-7ade-4131-9100-878652c477fc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "mlrun-base",
+   "language": "python",
+   "name": "conda-env-mlrun-base-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.22"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/modules/development/vllm_module/1.0.0/src/vllm_module.py b/modules/development/vllm_module/1.0.0/src/vllm_module.py
new file mode 100644
index 00000000..50bc9f03
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/src/vllm_module.py
@@ -0,0 +1,131 @@
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+#This module acts as a lightweight gateway to OpenAI-compatible APIs.
+#You can send chat prompts, create embeddings, or get model responses without worrying about authentication or endpoint differences. 
+#It simplifies access so you can test, analyze, or integrate AI features directly into your projects or notebooks with minimal setup.
+
+
+from typing import Dict, Optional, List
+
+class VLLMModule:
+    """
+    VLLMModule
+    
+    This module provides a lightweight wrapper for deploying a vLLM
+    (OpenAI-compatible) large language model server as an MLRun application runtime.
+    
+    The VLLMModule is responsible for:
+    - Creating an MLRun application runtime based on a vLLM container image
+    - Configuring GPU resources, memory limits, and Kubernetes node selection
+    - Launching the model using `vllm serve` with configurable runtime flags
+    - Supporting multi-GPU inference via tensor parallelism
+    - Automatically configuring shared memory (/dev/shm) when using multiple GPUs
+    - Exposing an OpenAI-compatible API (e.g. /v1/chat/completions) for inference
+    - Providing a simple Python interface for deployment and invocation from Jupyter notebooks
+    
+    The module is designed to be used in Jupyter notebooks and MLRun pipelines,
+    allowing users to deploy and test large language models on Kubernetes
+    with minimal configuration.
+    """
+
+    def __init__(
+            self,
+            project: str,
+            *,
+            node_selector: Optional[Dict[str, str]] = None,
+            name: str = "vllm",
+            image: str = "vllm/vllm-openai:latest",
+            model: str = "Qwen/Qwen2.5-Omni-3B",
+            gpus: int = 1,
+            mem: str = "10G",
+            port: int = 8000,
+            dtype: str = "auto",
+            uvicorn_log_level: str = "info",
+            max_tokens: int = 500,
+    ):
+        if gpus < 1:
+            raise ValueError("gpus must be >= 1")
+
+        
+        
+        if node_selector is None:
+            node_selector = {"alpha.eksctl.io/nodegroup-name": "added-gpu"}
+        
+        if not isinstance(max_tokens, int):
+            raise TypeError("max_tokens must be an integer")
+
+        if max_tokens < 1:
+            raise ValueError("max_tokens must be >= 1")
+
+        self.project = project
+        self.name = name
+        self.image = image
+        self.model = model
+        self.gpus = gpus
+        self.mem = mem
+        self.node_selector = node_selector
+        self.port = port
+        self.dtype = dtype
+        self.uvicorn_log_level = uvicorn_log_level
+        self.max_tokens = max_tokens
+
+        self.vllm_app = self.project.set_function(
+            name=self.name,
+            kind="application",
+            image=self.image,
+        )
+
+        self.vllm_app.with_limits(gpus=self.gpus, mem=self.mem)
+
+        if self.node_selector:
+            self.vllm_app.with_node_selection(node_selector=self.node_selector)
+
+        self.vllm_app.set_internal_application_port(self.port)
+
+        args: List[str] = [
+            "serve",
+            self.model,
+            "--dtype",
+            self.dtype,
+            "--port",
+            str(self.port),
+        ]
+
+        if self.uvicorn_log_level:
+            args += ["--uvicorn-log-level", self.uvicorn_log_level]
+
+        if self.gpus > 1:
+            args += ["--tensor-parallel-size", str(gpus)]
+
+            # For more than one GPU you should create a share volume for the multiple GPUs
+            self.vllm_app.spec.volumes = [{"name": "dshm", "emptyDir": {"medium": "Memory"}}]
+            self.vllm_app.spec.volume_mounts = [{"name": "dshm", "mountPath": "/dev/shm"}]
+
+    
+
+        self.vllm_app.spec.command = "vllm"
+        self.vllm_app.spec.args = args
+
+        self.vllm_app.spec.min_replicas = 1
+        self.vllm_app.spec.max_replicas = 1
+
+    def get_runtime(self):
+        return self.vllm_app
+
+    def add_args(self, extra_args: List[str]):
+        if not isinstance(extra_args, list) or not all(isinstance(x, str) for x in extra_args):
+            raise ValueError("extra_args must be a list of strings")
+        self.vllm_app.spec.args += extra_args
+
diff --git a/modules/development/vllm_module/1.0.0/static/documentation.html b/modules/development/vllm_module/1.0.0/static/documentation.html
new file mode 100644
index 00000000..f6b121d8
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/static/documentation.html
@@ -0,0 +1,270 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="./" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/><meta content="width=device-width, initial-scale=1" name="viewport"/>
+<title>vllm_module package</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = 'vllm_module';</script>
+<link href="genindex.html" rel="index" title="Index"/>
+<link href="search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<div class="dropdown dropdown-download-buttons">
+<button aria-expanded="false" aria-label="Download this page" class="btn dropdown-toggle" data-bs-toggle="dropdown" type="button">
+<i class="fas fa-download"></i>
+</button>
+<ul class="dropdown-menu">
+<li><a class="btn btn-sm btn-download-source-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" href="_sources/vllm_module.rst" target="_blank" title="Download source file">
+<span class="btn__icon-container">
+<i class="fas fa-file"></i>
+</span>
+<span class="btn__text-container">.rst</span>
+</a>
+</li>
+<li>
+<button class="btn btn-sm btn-download-pdf-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" onclick="window.print()" title="Print to PDF">
+<span class="btn__icon-container">
+<i class="fas fa-file-pdf"></i>
+</span>
+<span class="btn__text-container">.pdf</span>
+</button>
+</li>
+</ul>
+</div>
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+<button class="sidebar-toggle secondary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle secondary sidebar">
+<span class="fa-solid fa-list"></span>
+</button>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1>vllm_module package</h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+<div>
+<h2> Contents </h2>
+</div>
+<nav aria-label="Page">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#submodules">Submodules</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-vllm_module.vllm_module">vllm_module.vllm_module module</a><ul class="nav section-nav flex-column">
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule"><code class="docutils literal notranslate"><span class="pre">VLLMModule</span></code></a><ul class="nav section-nav flex-column">
+<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule.add_args"><code class="docutils literal notranslate"><span class="pre">VLLMModule.add_args()</span></code></a></li>
+<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule.get_runtime"><code class="docutils literal notranslate"><span class="pre">VLLMModule.get_runtime()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-vllm_module">Module contents</a></li>
+</ul>
+</nav>
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+<section id="vllm-module-package">
+<h1>vllm_module package<a class="headerlink" href="#vllm-module-package" title="Link to this heading">#</a></h1>
+<section id="submodules">
+<h2>Submodules<a class="headerlink" href="#submodules" title="Link to this heading">#</a></h2>
+</section>
+<section id="module-vllm_module.vllm_module">
+<span id="vllm-module-vllm-module-module"></span><h2>vllm_module.vllm_module module<a class="headerlink" href="#module-vllm_module.vllm_module" title="Link to this heading">#</a></h2>
+<dl class="py class">
+<dt class="sig sig-object py" id="vllm_module.vllm_module.VLLMModule">
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">vllm_module.vllm_module.</span></span><span class="sig-name descname"><span class="pre">VLLMModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">project</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">node_selector</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">None</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'vllm'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">image</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'vllm/vllm-openai:latest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'Qwen/Qwen2.5-Omni-3B'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gpus</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mem</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'10G'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">8000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">uvicorn_log_level</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'info'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_tokens</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">500</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="vllm_module.html#VLLMModule"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#vllm_module.vllm_module.VLLMModule" title="Link to this definition">#</a></dt>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
+<p>This module provides a lightweight wrapper for deploying a vLLM
+(OpenAI-compatible) large language model server as an MLRun application runtime.</p>
+<p>The VLLMModule is responsible for:
+- Creating an MLRun application runtime based on a vLLM container image
+- Configuring GPU resources, memory limits, and Kubernetes node selection
+- Launching the model using <cite>vllm serve</cite> with configurable runtime flags
+- Supporting multi-GPU inference via tensor parallelism
+- Automatically configuring shared memory (/dev/shm) when using multiple GPUs
+- Exposing an OpenAI-compatible API (e.g. /v1/chat/completions) for inference
+- Providing a simple Python interface for deployment and invocation from Jupyter notebooks</p>
+<p>The module is designed to be used in Jupyter notebooks and MLRun pipelines,
+allowing users to deploy and test large language models on Kubernetes
+with minimal configuration.</p>
+<dl class="py method">
+<dt class="sig sig-object py" id="vllm_module.vllm_module.VLLMModule.add_args">
+<span class="sig-name descname"><span class="pre">add_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">extra_args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference internal" href="vllm_module.html#VLLMModule.add_args"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#vllm_module.vllm_module.VLLMModule.add_args" title="Link to this definition">#</a></dt>
+<dd></dd></dl>
+<dl class="py method">
+<dt class="sig sig-object py" id="vllm_module.vllm_module.VLLMModule.get_runtime">
+<span class="sig-name descname"><span class="pre">get_runtime</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="vllm_module.html#VLLMModule.get_runtime"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#vllm_module.vllm_module.VLLMModule.get_runtime" title="Link to this definition">#</a></dt>
+<dd></dd></dl>
+</dd></dl>
+</section>
+<section id="module-vllm_module">
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-vllm_module" title="Link to this heading">#</a></h2>
+</section>
+</section>
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
+<div class="sidebar-secondary-item">
+<div class="page-toc tocsection onthispage">
+<i class="fa-solid fa-list"></i> Contents
+  </div>
+<nav class="bd-toc-nav page-toc">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#submodules">Submodules</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-vllm_module.vllm_module">vllm_module.vllm_module module</a><ul class="nav section-nav flex-column">
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule"><code class="docutils literal notranslate"><span class="pre">VLLMModule</span></code></a><ul class="nav section-nav flex-column">
+<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule.add_args"><code class="docutils literal notranslate"><span class="pre">VLLMModule.add_args()</span></code></a></li>
+<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule.get_runtime"><code class="docutils literal notranslate"><span class="pre">VLLMModule.get_runtime()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-vllm_module">Module contents</a></li>
+</ul>
+</nav></div>
+</div></div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/1.0.0/static/example.html b/modules/development/vllm_module/1.0.0/static/example.html
new file mode 100644
index 00000000..4c570c74
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/static/example.html
@@ -0,0 +1,355 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="./" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/><meta content="width=device-width, initial-scale=1" name="viewport"/>
+<title>vLLM Module with MLRun</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = 'vllm_module_example';</script>
+<link href="genindex.html" rel="index" title="Index"/>
+<link href="search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<div class="dropdown dropdown-download-buttons">
+<button aria-expanded="false" aria-label="Download this page" class="btn dropdown-toggle" data-bs-toggle="dropdown" type="button">
+<i class="fas fa-download"></i>
+</button>
+<ul class="dropdown-menu">
+<li><a class="btn btn-sm btn-download-source-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" href="../src/vllm_module.ipynb" target="_blank" title="Download source file">
+<span class="btn__icon-container">
+<i class="fas fa-file"></i>
+</span>
+<span class="btn__text-container">.ipynb</span>
+</a>
+</li>
+<li>
+<button class="btn btn-sm btn-download-pdf-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" onclick="window.print()" title="Print to PDF">
+<span class="btn__icon-container">
+<i class="fas fa-file-pdf"></i>
+</span>
+<span class="btn__text-container">.pdf</span>
+</button>
+</li>
+</ul>
+</div>
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+<button class="sidebar-toggle secondary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle secondary sidebar">
+<span class="fa-solid fa-list"></span>
+</button>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1>vLLM Module with MLRun</h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+<div>
+<h2> Contents </h2>
+</div>
+<nav aria-label="Page">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#prerequisite">Prerequisite</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#what-this-notebook-does">What this notebook does</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#create-an-mlrun-project">1. Create an MLRun project</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#import-the-vllm-module-from-the-mlrun-hub">2. Import the vLLM module from the MLRun Hub</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#deploy-the-vllm-application-runtime">3. Deploy the vLLM application runtime</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#get-the-runtime-handle">4. Get the runtime handle</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#send-a-chat-request-for-testing">5. Send a chat request for testing</a></li>
+</ul>
+</nav>
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+<section id="vllm-module-with-mlrun">
+<h1>vLLM Module with MLRun<a class="headerlink" href="#vllm-module-with-mlrun" title="Link to this heading">#</a></h1>
+<p>This notebook shows how to configure and deploy a vLLM OpenAI compatible server as an MLRun application runtime, then showcases how to send a chat request to it to the vLLM server.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">mlrun</span>
+</pre></div>
+</div>
+</div>
+</div>
+<section id="prerequisite">
+<h2>Prerequisite<a class="headerlink" href="#prerequisite" title="Link to this heading">#</a></h2>
+<ul class="simple">
+<li><p>At lease one GPU is required for running this notebook.</p></li>
+</ul>
+</section>
+<section id="what-this-notebook-does">
+<h2>What this notebook does<a class="headerlink" href="#what-this-notebook-does" title="Link to this heading">#</a></h2>
+<p>In this notebook we will:</p>
+<ul class="simple">
+<li><p>Create or load an <strong>MLRun project</strong></p></li>
+<li><p>Import a custom <strong>vLLM module</strong> from the MLRun Hub</p></li>
+<li><p>Deploy a <strong>vLLM OpenAI-compatible server</strong> as an MLRun application runtime</p></li>
+<li><p>Configure deployment parameters such as model, GPU count, memory, node selector, port, and log level</p></li>
+<li><p>Invoke the deployed service using the <code class="docutils literal notranslate"><span class="pre">/v1/chat/completions</span></code> endpoint</p></li>
+<li><p>Parse the response and extract only the assistant’s generated text</p></li>
+</ul>
+<p>By the end of this notebook, you will have a working vLLM deployment that can be queried directly from a Jupyter notebook using OpenAI-style APIs.</p>
+<p>For more information about <a class="reference external" href="https://docs.vllm.ai/en/latest/serving/openai_compatible_server/">vLLM documentation</a></p>
+</section>
+<section id="create-an-mlrun-project">
+<h2>1. Create an MLRun project<a class="headerlink" href="#create-an-mlrun-project" title="Link to this heading">#</a></h2>
+<p>In this section we create or load an MLRun project that will own the deployed vLLM application runtime.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">project</span> <span class="o">=</span> <span class="n">mlrun</span><span class="o">.</span><span class="n">get_or_create_project</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">"vllm-module"</span><span class="p">,</span> <span class="n">context</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span> <span class="n">user_project</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+<section id="import-the-vllm-module-from-the-mlrun-hub">
+<h2>2. Import the vLLM module from the MLRun Hub<a class="headerlink" href="#import-the-vllm-module-from-the-mlrun-hub" title="Link to this heading">#</a></h2>
+<p>In this section we import the vLLM module from the MLRun Hub so we can instantiate <code class="docutils literal notranslate"><span class="pre">VLLMModule</span></code> and deploy it as an application runtime.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">vllm</span> <span class="o">=</span> <span class="n">mlrun</span><span class="o">.</span><span class="n">import_module</span><span class="p">(</span><span class="s2">"hub://vllm-module"</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+<section id="deploy-the-vllm-application-runtime">
+<h2>3. Deploy the vLLM application runtime<a class="headerlink" href="#deploy-the-vllm-application-runtime" title="Link to this heading">#</a></h2>
+<p>Configure the vLLM deployment parameters and deploy the application.</p>
+<p>The returned address is the service URL for the application runtime.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Initialize the vLLM app</span>
+<span class="n">vllm_module</span> <span class="o">=</span> <span class="n">vllm</span><span class="o">.</span><span class="n">VLLMModule</span><span class="p">(</span>
+    <span class="n">project</span><span class="o">=</span><span class="n">project</span><span class="p">,</span>
+    <span class="n">node_selector</span><span class="o">=</span><span class="p">{</span><span class="s2">"alpha.eksctl.io/nodegroup-name"</span><span class="p">:</span> <span class="s2">"added-gpu"</span><span class="p">},</span>
+    <span class="n">name</span><span class="o">=</span><span class="s2">"qwen-vllm"</span><span class="p">,</span>
+    <span class="n">image</span><span class="o">=</span><span class="s2">"vllm/vllm-openai:latest"</span><span class="p">,</span>
+    <span class="n">model</span><span class="o">=</span><span class="s2">"Qwen/Qwen2.5-Omni-3B"</span><span class="p">,</span>
+    <span class="n">gpus</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
+    <span class="n">mem</span><span class="o">=</span><span class="s2">"10G"</span><span class="p">,</span>
+    <span class="n">port</span><span class="o">=</span><span class="mi">8000</span><span class="p">,</span>
+    <span class="n">dtype</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">,</span>
+    <span class="n">uvicorn_log_level</span><span class="o">=</span><span class="s2">"info"</span><span class="p">,</span>
+    <span class="n">max_tokens</span> <span class="o">=</span> <span class="mi">501</span><span class="p">,</span>
+<span class="p">)</span>
+
+<span class="c1"># Deploy the vLLM app</span>
+<span class="n">addr</span> <span class="o">=</span> <span class="n">vllm_module</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">deploy</span><span class="p">(</span><span class="n">with_mlrun</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<span class="n">addr</span>
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+<section id="get-the-runtime-handle">
+<h2>4. Get the runtime handle<a class="headerlink" href="#get-the-runtime-handle" title="Link to this heading">#</a></h2>
+<p>Fetch the runtime object and invoke the service using <code class="docutils literal notranslate"><span class="pre">app.invoke(...)</span></code>.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Optional: get_runtime() method uses to get the MLRun application runtime</span>
+<span class="n">app</span> <span class="o">=</span> <span class="n">vllm_module</span><span class="o">.</span><span class="n">get_runtime</span><span class="p">()</span>
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+<section id="send-a-chat-request-for-testing">
+<h2>5. Send a chat request for testing<a class="headerlink" href="#send-a-chat-request-for-testing" title="Link to this heading">#</a></h2>
+<p>Call the OpenAI compatible endpoint <code class="docutils literal notranslate"><span class="pre">/v1/chat/completions</span></code>, parse the JSON response, and print only the assistant message text.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">body</span> <span class="o">=</span> <span class="p">{</span>
+    <span class="s2">"model"</span><span class="p">:</span> <span class="n">vllm_module</span><span class="o">.</span><span class="n">model</span><span class="p">,</span>
+    <span class="s2">"messages"</span><span class="p">:</span> <span class="p">[{</span><span class="s2">"role"</span><span class="p">:</span> <span class="s2">"user"</span><span class="p">,</span> <span class="s2">"content"</span><span class="p">:</span> <span class="s2">"what are the 3 countries with the most gpu as far as you know"</span><span class="p">}],</span>
+    <span class="s2">"max_tokens"</span><span class="p">:</span> <span class="n">vllm_module</span><span class="o">.</span><span class="n">max_tokens</span><span class="p">,</span>     <span class="c1"># start smaller for testing</span>
+<span class="p">}</span>
+
+<span class="n">resp</span> <span class="o">=</span> <span class="n">app</span><span class="o">.</span><span class="n">invoke</span><span class="p">(</span><span class="n">path</span><span class="o">=</span><span class="s2">"/v1/chat/completions"</span><span class="p">,</span> <span class="n">body</span><span class="o">=</span><span class="n">body</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+</div>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">data</span> <span class="o">=</span> <span class="n">resp</span>
+<span class="n">assistant_text</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="s2">"choices"</span><span class="p">][</span><span class="mi">0</span><span class="p">][</span><span class="s2">"message"</span><span class="p">][</span><span class="s2">"content"</span><span class="p">]</span>
+
+<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">assistant:</span><span class="se">\n</span><span class="s2">"</span><span class="p">)</span>
+<span class="nb">print</span><span class="p">(</span><span class="n">assistant_text</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span>
+</pre></div>
+</div>
+</div>
+<div class="cell_output docutils container">
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>assistant:
+
+As of the most commonly cited estimates, the three countries with the largest GPU capacity for AI workloads are the United States, China, and India.
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+</section>
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
+<div class="sidebar-secondary-item">
+<div class="page-toc tocsection onthispage">
+<i class="fa-solid fa-list"></i> Contents
+  </div>
+<nav class="bd-toc-nav page-toc">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#prerequisite">Prerequisite</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#what-this-notebook-does">What this notebook does</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#create-an-mlrun-project">1. Create an MLRun project</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#import-the-vllm-module-from-the-mlrun-hub">2. Import the vLLM module from the MLRun Hub</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#deploy-the-vllm-application-runtime">3. Deploy the vLLM application runtime</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#get-the-runtime-handle">4. Get the runtime handle</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#send-a-chat-request-for-testing">5. Send a chat request for testing</a></li>
+</ul>
+</nav></div>
+</div></div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/1.0.0/static/item.html b/modules/development/vllm_module/1.0.0/static/item.html
new file mode 100644
index 00000000..9c7a1da0
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/static/item.html
@@ -0,0 +1,51 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta content="IE=edge" http-equiv="X-UA-Compatible">
+    <meta content="width=device-width, initial-scale=1.0" name="viewport">
+    <link
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/styles/atom-one-dark.min.css"
+            rel="stylesheet"
+            integrity="sha384-oaMLBGEzBOJx3UHwac0cVndtX5fxGQIfnAeFZ35RTgqPcYlbprH9o9PUV/F8Le07"
+            crossorigin="anonymous"
+    />
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/highlight.min.js"
+            integrity="sha384-RH2xi4eIQ/gjtbs9fUXM68sLSi99C7ZWBRX1vDrVv6GQXRibxXLbwO2NGZB74MbU"
+            crossorigin="anonymous"
+    ></script>
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/languages/yaml.min.js"
+            integrity="sha384-A/iMReLA0Bo3tLydBIoOQXQzYnrwL90jkHYUubrtERUGCbIuU7U0EHge0Xd2s5sr"
+            crossorigin="anonymous"
+    ></script>
+    <title>Source</title>
+    <script>hljs.highlightAll();</script>
+</head>
+
+<body style="background-color:darkgray; margin: 0 0 0 0;">
+    <pre style="margin: 0 1em;">
+        <code class="yaml">
+apiVersion: v1
+categories:
+- genai
+description: Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.
+example: vllm_module.ipynb
+generationDate: 2025-12-17:12-25
+hidden: false
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0
+name: vllm_module
+spec:
+    filename: vllm_module.py
+    image: mlrun/mlrun
+    kind: generic
+version: 1.0.0
+
+        </code>
+    </pre>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/1.0.0/static/source.html b/modules/development/vllm_module/1.0.0/static/source.html
new file mode 100644
index 00000000..4c6299ad
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/static/source.html
@@ -0,0 +1,166 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta content="IE=edge" http-equiv="X-UA-Compatible">
+    <meta content="width=device-width, initial-scale=1.0" name="viewport">
+    <link
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/styles/atom-one-dark.min.css"
+            rel="stylesheet"
+            integrity="sha384-oaMLBGEzBOJx3UHwac0cVndtX5fxGQIfnAeFZ35RTgqPcYlbprH9o9PUV/F8Le07"
+            crossorigin="anonymous"
+    />
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/highlight.min.js"
+            integrity="sha384-RH2xi4eIQ/gjtbs9fUXM68sLSi99C7ZWBRX1vDrVv6GQXRibxXLbwO2NGZB74MbU"
+            crossorigin="anonymous"
+    ></script>
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/languages/python.min.js"
+            integrity="sha384-eXRt+aAa2ig1yFVDQCLis8k9s/1dikTcigj+/R07yNdIxc8BAG/b1uHDyEW3of17"
+            crossorigin="anonymous"
+    ></script>
+    <title>Source</title>
+    <script>hljs.highlightAll();</script>
+</head>
+
+<body style="background-color:darkgray; margin: 0 0 0 0;">
+    <pre style="margin: 0 1em;">
+        <code class="python">
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+#This module acts as a lightweight gateway to OpenAI-compatible APIs.
+#You can send chat prompts, create embeddings, or get model responses without worrying about authentication or endpoint differences. 
+#It simplifies access so you can test, analyze, or integrate AI features directly into your projects or notebooks with minimal setup.
+
+
+from typing import Dict, Optional, List
+
+class VLLMModule:
+    """
+    VLLMModule
+    
+    This module provides a lightweight wrapper for deploying a vLLM
+    (OpenAI-compatible) large language model server as an MLRun application runtime.
+    
+    The VLLMModule is responsible for:
+    - Creating an MLRun application runtime based on a vLLM container image
+    - Configuring GPU resources, memory limits, and Kubernetes node selection
+    - Launching the model using `vllm serve` with configurable runtime flags
+    - Supporting multi-GPU inference via tensor parallelism
+    - Automatically configuring shared memory (/dev/shm) when using multiple GPUs
+    - Exposing an OpenAI-compatible API (e.g. /v1/chat/completions) for inference
+    - Providing a simple Python interface for deployment and invocation from Jupyter notebooks
+    
+    The module is designed to be used in Jupyter notebooks and MLRun pipelines,
+    allowing users to deploy and test large language models on Kubernetes
+    with minimal configuration.
+    """
+
+    def __init__(
+            self,
+            project: str,
+            *,
+            node_selector: Optional[Dict[str, str]] = None,
+            name: str = "vllm",
+            image: str = "vllm/vllm-openai:latest",
+            model: str = "Qwen/Qwen2.5-Omni-3B",
+            gpus: int = 1,
+            mem: str = "10G",
+            port: int = 8000,
+            dtype: str = "auto",
+            uvicorn_log_level: str = "info",
+            max_tokens: int = 500,
+    ):
+        if gpus < 1:
+            raise ValueError("gpus must be >= 1")
+
+        
+        
+        if node_selector is None:
+            node_selector = {"alpha.eksctl.io/nodegroup-name": "added-gpu"}
+        
+        if not isinstance(max_tokens, int):
+            raise TypeError("max_tokens must be an integer")
+
+        if max_tokens < 1:
+            raise ValueError("max_tokens must be >= 1")
+
+        self.project = project
+        self.name = name
+        self.image = image
+        self.model = model
+        self.gpus = gpus
+        self.mem = mem
+        self.node_selector = node_selector
+        self.port = port
+        self.dtype = dtype
+        self.uvicorn_log_level = uvicorn_log_level
+        self.max_tokens = max_tokens
+
+        self.vllm_app = self.project.set_function(
+            name=self.name,
+            kind="application",
+            image=self.image,
+        )
+
+        self.vllm_app.with_limits(gpus=self.gpus, mem=self.mem)
+
+        if self.node_selector:
+            self.vllm_app.with_node_selection(node_selector=self.node_selector)
+
+        self.vllm_app.set_internal_application_port(self.port)
+
+        args: List[str] = [
+            "serve",
+            self.model,
+            "--dtype",
+            self.dtype,
+            "--port",
+            str(self.port),
+        ]
+
+        if self.uvicorn_log_level:
+            args += ["--uvicorn-log-level", self.uvicorn_log_level]
+
+        if self.gpus > 1:
+            args += ["--tensor-parallel-size", str(gpus)]
+
+            # For more than one GPU you should create a share volume for the multiple GPUs
+            self.vllm_app.spec.volumes = [{"name": "dshm", "emptyDir": {"medium": "Memory"}}]
+            self.vllm_app.spec.volume_mounts = [{"name": "dshm", "mountPath": "/dev/shm"}]
+
+    
+
+        self.vllm_app.spec.command = "vllm"
+        self.vllm_app.spec.args = args
+
+        self.vllm_app.spec.min_replicas = 1
+        self.vllm_app.spec.max_replicas = 1
+
+    def get_runtime(self):
+        return self.vllm_app
+
+    def add_args(self, extra_args: List[str]):
+        if not isinstance(extra_args, list) or not all(isinstance(x, str) for x in extra_args):
+            raise ValueError("extra_args must be a list of strings")
+        self.vllm_app.spec.args += extra_args
+
+
+        </code>
+    </pre>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/1.0.0/static/vllm_module.html b/modules/development/vllm_module/1.0.0/static/vllm_module.html
new file mode 100644
index 00000000..7b22280c
--- /dev/null
+++ b/modules/development/vllm_module/1.0.0/static/vllm_module.html
@@ -0,0 +1,312 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="../../" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/>
+<title>vllm_module.vllm_module</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = '_modules/vllm_module/vllm_module';</script>
+<link href="../../genindex.html" rel="index" title="Index"/>
+<link href="../../search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="../../search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="../../index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1></h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+<h1>Source code for vllm_module.vllm_module</h1><div class="highlight"><pre>
+<span></span><span class="c1"># Copyright 2025 Iguazio</span>
+<span class="c1">#</span>
+<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
+<span class="c1"># you may not use this file except in compliance with the License.</span>
+<span class="c1"># You may obtain a copy of the License at</span>
+<span class="c1">#</span>
+<span class="c1">#     http://www.apache.org/licenses/LICENSE-2.0</span>
+<span class="c1">#</span>
+<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
+<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
+<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
+<span class="c1"># See the License for the specific language governing permissions and</span>
+<span class="c1"># limitations under the License.</span>
+<span class="c1">#</span>
+<span class="c1">#This module acts as a lightweight gateway to OpenAI-compatible APIs.</span>
+<span class="c1">#You can send chat prompts, create embeddings, or get model responses without worrying about authentication or endpoint differences. </span>
+<span class="c1">#It simplifies access so you can test, analyze, or integrate AI features directly into your projects or notebooks with minimal setup.</span>
+
+
+<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">List</span>
+
+<div class="viewcode-block" id="VLLMModule">
+<a class="viewcode-back" href="documentation.html#vllm_module.vllm_module.VLLMModule">[docs]</a>
+<span class="k">class</span><span class="w"> </span><span class="nc">VLLMModule</span><span class="p">:</span>
+<span class="w">    </span><span class="sd">"""</span>
+<span class="sd">    VLLMModule</span>
+<span class="sd">    </span>
+<span class="sd">    This module provides a lightweight wrapper for deploying a vLLM</span>
+<span class="sd">    (OpenAI-compatible) large language model server as an MLRun application runtime.</span>
+<span class="sd">    </span>
+<span class="sd">    The VLLMModule is responsible for:</span>
+<span class="sd">    - Creating an MLRun application runtime based on a vLLM container image</span>
+<span class="sd">    - Configuring GPU resources, memory limits, and Kubernetes node selection</span>
+<span class="sd">    - Launching the model using `vllm serve` with configurable runtime flags</span>
+<span class="sd">    - Supporting multi-GPU inference via tensor parallelism</span>
+<span class="sd">    - Automatically configuring shared memory (/dev/shm) when using multiple GPUs</span>
+<span class="sd">    - Exposing an OpenAI-compatible API (e.g. /v1/chat/completions) for inference</span>
+<span class="sd">    - Providing a simple Python interface for deployment and invocation from Jupyter notebooks</span>
+<span class="sd">    </span>
+<span class="sd">    The module is designed to be used in Jupyter notebooks and MLRun pipelines,</span>
+<span class="sd">    allowing users to deploy and test large language models on Kubernetes</span>
+<span class="sd">    with minimal configuration.</span>
+<span class="sd">    """</span>
+
+    <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span>
+            <span class="bp">self</span><span class="p">,</span>
+            <span class="n">project</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
+            <span class="o">*</span><span class="p">,</span>
+            <span class="n">node_selector</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
+            <span class="n">name</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"vllm"</span><span class="p">,</span>
+            <span class="n">image</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"vllm/vllm-openai:latest"</span><span class="p">,</span>
+            <span class="n">model</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"Qwen/Qwen2.5-Omni-3B"</span><span class="p">,</span>
+            <span class="n">gpus</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
+            <span class="n">mem</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"10G"</span><span class="p">,</span>
+            <span class="n">port</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">8000</span><span class="p">,</span>
+            <span class="n">dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"auto"</span><span class="p">,</span>
+            <span class="n">uvicorn_log_level</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"info"</span><span class="p">,</span>
+            <span class="n">max_tokens</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">500</span><span class="p">,</span>
+    <span class="p">):</span>
+        <span class="k">if</span> <span class="n">gpus</span> <span class="o">&lt;</span> <span class="mi">1</span><span class="p">:</span>
+            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"gpus must be &gt;= 1"</span><span class="p">)</span>
+
+        
+        
+        <span class="k">if</span> <span class="n">node_selector</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+            <span class="n">node_selector</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"alpha.eksctl.io/nodegroup-name"</span><span class="p">:</span> <span class="s2">"added-gpu"</span><span class="p">}</span>
+        
+        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">max_tokens</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
+            <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"max_tokens must be an integer"</span><span class="p">)</span>
+
+        <span class="k">if</span> <span class="n">max_tokens</span> <span class="o">&lt;</span> <span class="mi">1</span><span class="p">:</span>
+            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"max_tokens must be &gt;= 1"</span><span class="p">)</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">project</span> <span class="o">=</span> <span class="n">project</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">name</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">image</span> <span class="o">=</span> <span class="n">image</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">gpus</span> <span class="o">=</span> <span class="n">gpus</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">mem</span> <span class="o">=</span> <span class="n">mem</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">node_selector</span> <span class="o">=</span> <span class="n">node_selector</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">port</span> <span class="o">=</span> <span class="n">port</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">dtype</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">uvicorn_log_level</span> <span class="o">=</span> <span class="n">uvicorn_log_level</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">max_tokens</span> <span class="o">=</span> <span class="n">max_tokens</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="o">.</span><span class="n">set_function</span><span class="p">(</span>
+            <span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">,</span>
+            <span class="n">kind</span><span class="o">=</span><span class="s2">"application"</span><span class="p">,</span>
+            <span class="n">image</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">image</span><span class="p">,</span>
+        <span class="p">)</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">with_limits</span><span class="p">(</span><span class="n">gpus</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gpus</span><span class="p">,</span> <span class="n">mem</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mem</span><span class="p">)</span>
+
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">node_selector</span><span class="p">:</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">with_node_selection</span><span class="p">(</span><span class="n">node_selector</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">node_selector</span><span class="p">)</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">set_internal_application_port</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="p">)</span>
+
+        <span class="n">args</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span>
+            <span class="s2">"serve"</span><span class="p">,</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">,</span>
+            <span class="s2">"--dtype"</span><span class="p">,</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
+            <span class="s2">"--port"</span><span class="p">,</span>
+            <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="p">),</span>
+        <span class="p">]</span>
+
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">uvicorn_log_level</span><span class="p">:</span>
+            <span class="n">args</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--uvicorn-log-level"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uvicorn_log_level</span><span class="p">]</span>
+
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">gpus</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
+            <span class="n">args</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--tensor-parallel-size"</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">gpus</span><span class="p">)]</span>
+
+            <span class="c1"># For more than one GPU you should create a share volume for the multiple GPUs</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">volumes</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"dshm"</span><span class="p">,</span> <span class="s2">"emptyDir"</span><span class="p">:</span> <span class="p">{</span><span class="s2">"medium"</span><span class="p">:</span> <span class="s2">"Memory"</span><span class="p">}}]</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">volume_mounts</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"dshm"</span><span class="p">,</span> <span class="s2">"mountPath"</span><span class="p">:</span> <span class="s2">"/dev/shm"</span><span class="p">}]</span>
+
+    
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">command</span> <span class="o">=</span> <span class="s2">"vllm"</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">args</span> <span class="o">=</span> <span class="n">args</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">min_replicas</span> <span class="o">=</span> <span class="mi">1</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">max_replicas</span> <span class="o">=</span> <span class="mi">1</span>
+
+<div class="viewcode-block" id="VLLMModule.get_runtime">
+<a class="viewcode-back" href="documentation.html#vllm_module.vllm_module.VLLMModule.get_runtime">[docs]</a>
+    <span class="k">def</span><span class="w"> </span><span class="nf">get_runtime</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span></div>
+
+
+<div class="viewcode-block" id="VLLMModule.add_args">
+<a class="viewcode-back" href="documentation.html#vllm_module.vllm_module.VLLMModule.add_args">[docs]</a>
+    <span class="k">def</span><span class="w"> </span><span class="nf">add_args</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">extra_args</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
+        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">extra_args</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span> <span class="ow">or</span> <span class="ow">not</span> <span class="nb">all</span><span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">extra_args</span><span class="p">):</span>
+            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"extra_args must be a list of strings"</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">args</span> <span class="o">+=</span> <span class="n">extra_args</span></div>
+</div>
+
+
+</pre></div>
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/latest/src/item.yaml b/modules/development/vllm_module/latest/src/item.yaml
new file mode 100644
index 00000000..ca684340
--- /dev/null
+++ b/modules/development/vllm_module/latest/src/item.yaml
@@ -0,0 +1,16 @@
+apiVersion: v1
+categories:
+- genai
+description: Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.
+example: vllm_module.ipynb
+generationDate: 2025-12-17:12-25
+hidden: false
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0
+name: vllm_module
+spec:
+    filename: vllm_module.py
+    image: mlrun/mlrun
+    kind: generic
+version: 1.0.0
diff --git a/modules/development/vllm_module/latest/src/test_vllm_module.py b/modules/development/vllm_module/latest/src/test_vllm_module.py
new file mode 100644
index 00000000..3a5f422a
--- /dev/null
+++ b/modules/development/vllm_module/latest/src/test_vllm_module.py
@@ -0,0 +1,35 @@
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from vllm_module import VLLMModule
+import mlrun
+
+
+class TestVllmModule:
+    """Test suite for VLLMModule class."""
+
+    def setup_method(self):
+        project = mlrun.new_project("vllm", save=False)
+
+        # if your VLLMModule requires node_selector as keyword-only, keep it here
+        self.TestVllmModule = VLLMModule(
+            project,
+            node_selector={"alpha.eksctl.io/nodegroup-name": "added-gpu"},
+        )
+
+    def test_vllm_module(self):
+        assert (
+            type(self.TestVllmModule.vllm_app) == mlrun.runtimes.nuclio.application.application.ApplicationRuntime
+        )
diff --git a/modules/development/vllm_module/latest/src/vllm_module.ipynb b/modules/development/vllm_module/latest/src/vllm_module.ipynb
new file mode 100644
index 00000000..2452dbd2
--- /dev/null
+++ b/modules/development/vllm_module/latest/src/vllm_module.ipynb
@@ -0,0 +1,234 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7d551647-dfc2-47da-bc8a-3792af622073",
+   "metadata": {},
+   "source": [
+    "# vLLM Module with MLRun\n",
+    "\n",
+    "This notebook shows how to configure and deploy a vLLM OpenAI compatible server as an MLRun application runtime, then showcases how to send a chat request to it to the vLLM server."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7707b270-30cc-448a-a828-cb93aa28030d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import mlrun\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d5cff681-bfdf-4468-a1d1-2aeadb56065e",
+   "metadata": {},
+   "source": [
+    "## Prerequisite\n",
+    "* At lease one GPU is required for running this notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d5c84798-289f-4b4f-8c1b-f4dd12a3bda5",
+   "metadata": {},
+   "source": [
+    "## What this notebook does\n",
+    "\n",
+    "In this notebook we will:\n",
+    "\n",
+    "- Create or load an **MLRun project**\n",
+    "- Import a custom **vLLM module** from the MLRun Hub\n",
+    "- Deploy a **vLLM OpenAI-compatible server** as an MLRun application runtime\n",
+    "- Configure deployment parameters such as model, GPU count, memory, node selector, port, and log level\n",
+    "- Invoke the deployed service using the `/v1/chat/completions` endpoint\n",
+    "- Parse the response and extract only the assistant’s generated text\n",
+    "\n",
+    "By the end of this notebook, you will have a working vLLM deployment that can be queried directly from a Jupyter notebook using OpenAI-style APIs.\n",
+    "\n",
+    "For more information about [vLLM documentation](https://docs.vllm.ai/en/latest/serving/openai_compatible_server/)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "879ca641-ee35-4682-9995-4eb319d89090",
+   "metadata": {},
+   "source": [
+    "## 1. Create an MLRun project\n",
+    "\n",
+    "In this section we create or load an MLRun project that will own the deployed vLLM application runtime."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6eac263a-17d1-4454-9e19-459dfbe2f231",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "project = mlrun.get_or_create_project(name=\"vllm-module\", context=\"\", user_project=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "da49d335-b704-4fb6-801f-4d07b64f9be6",
+   "metadata": {},
+   "source": [
+    "## 2. Import the vLLM module from the MLRun Hub\n",
+    "\n",
+    "In this section we import the vLLM module from the MLRun Hub so we can instantiate `VLLMModule` and deploy it as an application runtime."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e6d89dee-db58-4c0c-8009-b37020c9599a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vllm = mlrun.import_module(\"hub://vllm-module\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1202ddd5-0ce7-4769-be29-8fc264c1f80e",
+   "metadata": {},
+   "source": [
+    "## 3. Deploy the vLLM application runtime\n",
+    "\n",
+    "Configure the vLLM deployment parameters and deploy the application.\n",
+    "\n",
+    "The returned address is the service URL for the application runtime."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e433123a-e64b-4a7a-8c7f-8165bcdcc6d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize the vLLM app\n",
+    "vllm_module = vllm.VLLMModule(\n",
+    "    project=project,\n",
+    "    node_selector={\"alpha.eksctl.io/nodegroup-name\": \"added-gpu\"},\n",
+    "    name=\"qwen-vllm\",\n",
+    "    image=\"vllm/vllm-openai:latest\",\n",
+    "    model=\"Qwen/Qwen2.5-Omni-3B\",\n",
+    "    gpus=1,\n",
+    "    mem=\"10G\",\n",
+    "    port=8000,\n",
+    "    dtype=\"auto\",\n",
+    "    uvicorn_log_level=\"info\",\n",
+    "    max_tokens = 501,\n",
+    ")\n",
+    "\n",
+    "# Deploy the vLLM app\n",
+    "addr = vllm_module.vllm_app.deploy(with_mlrun=True)\n",
+    "addr"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "06832de3-5c31-43bf-b07b-0e71fb2d072d",
+   "metadata": {},
+   "source": [
+    "## 4. Get the runtime handle\n",
+    "\n",
+    "Fetch the runtime object and invoke the service using `app.invoke(...)`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "102d3fd0-1ee6-49b8-8c86-df742ac1c559",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: get_runtime() method uses to get the MLRun application runtime\n",
+    "app = vllm_module.get_runtime()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "925730c1-0ac5-454b-8fb2-ab8cebb3f3ac",
+   "metadata": {},
+   "source": [
+    "## 5. Send a chat request for testing\n",
+    "\n",
+    "Call the OpenAI compatible endpoint `/v1/chat/completions`, parse the JSON response, and print only the assistant message text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "31bc78d4-1c6f-439c-b894-1522e3a6d3e6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "body = {\n",
+    "    \"model\": vllm_module.model,\n",
+    "    \"messages\": [{\"role\": \"user\", \"content\": \"what are the 3 countries with the most gpu as far as you know\"}],\n",
+    "    \"max_tokens\": vllm_module.max_tokens,     # start smaller for testing\n",
+    "}\n",
+    "\n",
+    "resp = app.invoke(path=\"/v1/chat/completions\", body=body)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "a459d5f8-dad0-4735-94c2-3801d4f94bb5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "assistant:\n",
+      "\n",
+      "As of the most commonly cited estimates, the three countries with the largest GPU capacity for AI workloads are the United States, China, and India.\n"
+     ]
+    }
+   ],
+   "source": [
+    "data = resp\n",
+    "assistant_text = data[\"choices\"][0][\"message\"][\"content\"]\n",
+    "\n",
+    "print(\"\\nassistant:\\n\")\n",
+    "print(assistant_text.strip())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "957b5d21-7ade-4131-9100-878652c477fc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "mlrun-base",
+   "language": "python",
+   "name": "conda-env-mlrun-base-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.22"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/modules/development/vllm_module/latest/src/vllm_module.py b/modules/development/vllm_module/latest/src/vllm_module.py
new file mode 100644
index 00000000..50bc9f03
--- /dev/null
+++ b/modules/development/vllm_module/latest/src/vllm_module.py
@@ -0,0 +1,131 @@
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+#This module acts as a lightweight gateway to OpenAI-compatible APIs.
+#You can send chat prompts, create embeddings, or get model responses without worrying about authentication or endpoint differences. 
+#It simplifies access so you can test, analyze, or integrate AI features directly into your projects or notebooks with minimal setup.
+
+
+from typing import Dict, Optional, List
+
+class VLLMModule:
+    """
+    VLLMModule
+    
+    This module provides a lightweight wrapper for deploying a vLLM
+    (OpenAI-compatible) large language model server as an MLRun application runtime.
+    
+    The VLLMModule is responsible for:
+    - Creating an MLRun application runtime based on a vLLM container image
+    - Configuring GPU resources, memory limits, and Kubernetes node selection
+    - Launching the model using `vllm serve` with configurable runtime flags
+    - Supporting multi-GPU inference via tensor parallelism
+    - Automatically configuring shared memory (/dev/shm) when using multiple GPUs
+    - Exposing an OpenAI-compatible API (e.g. /v1/chat/completions) for inference
+    - Providing a simple Python interface for deployment and invocation from Jupyter notebooks
+    
+    The module is designed to be used in Jupyter notebooks and MLRun pipelines,
+    allowing users to deploy and test large language models on Kubernetes
+    with minimal configuration.
+    """
+
+    def __init__(
+            self,
+            project: str,
+            *,
+            node_selector: Optional[Dict[str, str]] = None,
+            name: str = "vllm",
+            image: str = "vllm/vllm-openai:latest",
+            model: str = "Qwen/Qwen2.5-Omni-3B",
+            gpus: int = 1,
+            mem: str = "10G",
+            port: int = 8000,
+            dtype: str = "auto",
+            uvicorn_log_level: str = "info",
+            max_tokens: int = 500,
+    ):
+        if gpus < 1:
+            raise ValueError("gpus must be >= 1")
+
+        
+        
+        if node_selector is None:
+            node_selector = {"alpha.eksctl.io/nodegroup-name": "added-gpu"}
+        
+        if not isinstance(max_tokens, int):
+            raise TypeError("max_tokens must be an integer")
+
+        if max_tokens < 1:
+            raise ValueError("max_tokens must be >= 1")
+
+        self.project = project
+        self.name = name
+        self.image = image
+        self.model = model
+        self.gpus = gpus
+        self.mem = mem
+        self.node_selector = node_selector
+        self.port = port
+        self.dtype = dtype
+        self.uvicorn_log_level = uvicorn_log_level
+        self.max_tokens = max_tokens
+
+        self.vllm_app = self.project.set_function(
+            name=self.name,
+            kind="application",
+            image=self.image,
+        )
+
+        self.vllm_app.with_limits(gpus=self.gpus, mem=self.mem)
+
+        if self.node_selector:
+            self.vllm_app.with_node_selection(node_selector=self.node_selector)
+
+        self.vllm_app.set_internal_application_port(self.port)
+
+        args: List[str] = [
+            "serve",
+            self.model,
+            "--dtype",
+            self.dtype,
+            "--port",
+            str(self.port),
+        ]
+
+        if self.uvicorn_log_level:
+            args += ["--uvicorn-log-level", self.uvicorn_log_level]
+
+        if self.gpus > 1:
+            args += ["--tensor-parallel-size", str(gpus)]
+
+            # For more than one GPU you should create a share volume for the multiple GPUs
+            self.vllm_app.spec.volumes = [{"name": "dshm", "emptyDir": {"medium": "Memory"}}]
+            self.vllm_app.spec.volume_mounts = [{"name": "dshm", "mountPath": "/dev/shm"}]
+
+    
+
+        self.vllm_app.spec.command = "vllm"
+        self.vllm_app.spec.args = args
+
+        self.vllm_app.spec.min_replicas = 1
+        self.vllm_app.spec.max_replicas = 1
+
+    def get_runtime(self):
+        return self.vllm_app
+
+    def add_args(self, extra_args: List[str]):
+        if not isinstance(extra_args, list) or not all(isinstance(x, str) for x in extra_args):
+            raise ValueError("extra_args must be a list of strings")
+        self.vllm_app.spec.args += extra_args
+
diff --git a/modules/development/vllm_module/latest/static/documentation.html b/modules/development/vllm_module/latest/static/documentation.html
new file mode 100644
index 00000000..f6b121d8
--- /dev/null
+++ b/modules/development/vllm_module/latest/static/documentation.html
@@ -0,0 +1,270 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="./" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/><meta content="width=device-width, initial-scale=1" name="viewport"/>
+<title>vllm_module package</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = 'vllm_module';</script>
+<link href="genindex.html" rel="index" title="Index"/>
+<link href="search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<div class="dropdown dropdown-download-buttons">
+<button aria-expanded="false" aria-label="Download this page" class="btn dropdown-toggle" data-bs-toggle="dropdown" type="button">
+<i class="fas fa-download"></i>
+</button>
+<ul class="dropdown-menu">
+<li><a class="btn btn-sm btn-download-source-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" href="_sources/vllm_module.rst" target="_blank" title="Download source file">
+<span class="btn__icon-container">
+<i class="fas fa-file"></i>
+</span>
+<span class="btn__text-container">.rst</span>
+</a>
+</li>
+<li>
+<button class="btn btn-sm btn-download-pdf-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" onclick="window.print()" title="Print to PDF">
+<span class="btn__icon-container">
+<i class="fas fa-file-pdf"></i>
+</span>
+<span class="btn__text-container">.pdf</span>
+</button>
+</li>
+</ul>
+</div>
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+<button class="sidebar-toggle secondary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle secondary sidebar">
+<span class="fa-solid fa-list"></span>
+</button>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1>vllm_module package</h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+<div>
+<h2> Contents </h2>
+</div>
+<nav aria-label="Page">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#submodules">Submodules</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-vllm_module.vllm_module">vllm_module.vllm_module module</a><ul class="nav section-nav flex-column">
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule"><code class="docutils literal notranslate"><span class="pre">VLLMModule</span></code></a><ul class="nav section-nav flex-column">
+<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule.add_args"><code class="docutils literal notranslate"><span class="pre">VLLMModule.add_args()</span></code></a></li>
+<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule.get_runtime"><code class="docutils literal notranslate"><span class="pre">VLLMModule.get_runtime()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-vllm_module">Module contents</a></li>
+</ul>
+</nav>
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+<section id="vllm-module-package">
+<h1>vllm_module package<a class="headerlink" href="#vllm-module-package" title="Link to this heading">#</a></h1>
+<section id="submodules">
+<h2>Submodules<a class="headerlink" href="#submodules" title="Link to this heading">#</a></h2>
+</section>
+<section id="module-vllm_module.vllm_module">
+<span id="vllm-module-vllm-module-module"></span><h2>vllm_module.vllm_module module<a class="headerlink" href="#module-vllm_module.vllm_module" title="Link to this heading">#</a></h2>
+<dl class="py class">
+<dt class="sig sig-object py" id="vllm_module.vllm_module.VLLMModule">
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">vllm_module.vllm_module.</span></span><span class="sig-name descname"><span class="pre">VLLMModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">project</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">node_selector</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">None</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'vllm'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">image</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'vllm/vllm-openai:latest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'Qwen/Qwen2.5-Omni-3B'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gpus</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mem</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'10G'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">8000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">uvicorn_log_level</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'info'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_tokens</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">500</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="vllm_module.html#VLLMModule"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#vllm_module.vllm_module.VLLMModule" title="Link to this definition">#</a></dt>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
+<p>This module provides a lightweight wrapper for deploying a vLLM
+(OpenAI-compatible) large language model server as an MLRun application runtime.</p>
+<p>The VLLMModule is responsible for:
+- Creating an MLRun application runtime based on a vLLM container image
+- Configuring GPU resources, memory limits, and Kubernetes node selection
+- Launching the model using <cite>vllm serve</cite> with configurable runtime flags
+- Supporting multi-GPU inference via tensor parallelism
+- Automatically configuring shared memory (/dev/shm) when using multiple GPUs
+- Exposing an OpenAI-compatible API (e.g. /v1/chat/completions) for inference
+- Providing a simple Python interface for deployment and invocation from Jupyter notebooks</p>
+<p>The module is designed to be used in Jupyter notebooks and MLRun pipelines,
+allowing users to deploy and test large language models on Kubernetes
+with minimal configuration.</p>
+<dl class="py method">
+<dt class="sig sig-object py" id="vllm_module.vllm_module.VLLMModule.add_args">
+<span class="sig-name descname"><span class="pre">add_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">extra_args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference internal" href="vllm_module.html#VLLMModule.add_args"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#vllm_module.vllm_module.VLLMModule.add_args" title="Link to this definition">#</a></dt>
+<dd></dd></dl>
+<dl class="py method">
+<dt class="sig sig-object py" id="vllm_module.vllm_module.VLLMModule.get_runtime">
+<span class="sig-name descname"><span class="pre">get_runtime</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="vllm_module.html#VLLMModule.get_runtime"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#vllm_module.vllm_module.VLLMModule.get_runtime" title="Link to this definition">#</a></dt>
+<dd></dd></dl>
+</dd></dl>
+</section>
+<section id="module-vllm_module">
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-vllm_module" title="Link to this heading">#</a></h2>
+</section>
+</section>
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
+<div class="sidebar-secondary-item">
+<div class="page-toc tocsection onthispage">
+<i class="fa-solid fa-list"></i> Contents
+  </div>
+<nav class="bd-toc-nav page-toc">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#submodules">Submodules</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-vllm_module.vllm_module">vllm_module.vllm_module module</a><ul class="nav section-nav flex-column">
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule"><code class="docutils literal notranslate"><span class="pre">VLLMModule</span></code></a><ul class="nav section-nav flex-column">
+<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule.add_args"><code class="docutils literal notranslate"><span class="pre">VLLMModule.add_args()</span></code></a></li>
+<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#vllm_module.vllm_module.VLLMModule.get_runtime"><code class="docutils literal notranslate"><span class="pre">VLLMModule.get_runtime()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-vllm_module">Module contents</a></li>
+</ul>
+</nav></div>
+</div></div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/latest/static/example.html b/modules/development/vllm_module/latest/static/example.html
new file mode 100644
index 00000000..4c570c74
--- /dev/null
+++ b/modules/development/vllm_module/latest/static/example.html
@@ -0,0 +1,355 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="./" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/><meta content="width=device-width, initial-scale=1" name="viewport"/>
+<title>vLLM Module with MLRun</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = 'vllm_module_example';</script>
+<link href="genindex.html" rel="index" title="Index"/>
+<link href="search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<div class="dropdown dropdown-download-buttons">
+<button aria-expanded="false" aria-label="Download this page" class="btn dropdown-toggle" data-bs-toggle="dropdown" type="button">
+<i class="fas fa-download"></i>
+</button>
+<ul class="dropdown-menu">
+<li><a class="btn btn-sm btn-download-source-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" href="../src/vllm_module.ipynb" target="_blank" title="Download source file">
+<span class="btn__icon-container">
+<i class="fas fa-file"></i>
+</span>
+<span class="btn__text-container">.ipynb</span>
+</a>
+</li>
+<li>
+<button class="btn btn-sm btn-download-pdf-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" onclick="window.print()" title="Print to PDF">
+<span class="btn__icon-container">
+<i class="fas fa-file-pdf"></i>
+</span>
+<span class="btn__text-container">.pdf</span>
+</button>
+</li>
+</ul>
+</div>
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+<button class="sidebar-toggle secondary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle secondary sidebar">
+<span class="fa-solid fa-list"></span>
+</button>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1>vLLM Module with MLRun</h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+<div>
+<h2> Contents </h2>
+</div>
+<nav aria-label="Page">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#prerequisite">Prerequisite</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#what-this-notebook-does">What this notebook does</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#create-an-mlrun-project">1. Create an MLRun project</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#import-the-vllm-module-from-the-mlrun-hub">2. Import the vLLM module from the MLRun Hub</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#deploy-the-vllm-application-runtime">3. Deploy the vLLM application runtime</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#get-the-runtime-handle">4. Get the runtime handle</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#send-a-chat-request-for-testing">5. Send a chat request for testing</a></li>
+</ul>
+</nav>
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+<section id="vllm-module-with-mlrun">
+<h1>vLLM Module with MLRun<a class="headerlink" href="#vllm-module-with-mlrun" title="Link to this heading">#</a></h1>
+<p>This notebook shows how to configure and deploy a vLLM OpenAI compatible server as an MLRun application runtime, then showcases how to send a chat request to it to the vLLM server.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">mlrun</span>
+</pre></div>
+</div>
+</div>
+</div>
+<section id="prerequisite">
+<h2>Prerequisite<a class="headerlink" href="#prerequisite" title="Link to this heading">#</a></h2>
+<ul class="simple">
+<li><p>At lease one GPU is required for running this notebook.</p></li>
+</ul>
+</section>
+<section id="what-this-notebook-does">
+<h2>What this notebook does<a class="headerlink" href="#what-this-notebook-does" title="Link to this heading">#</a></h2>
+<p>In this notebook we will:</p>
+<ul class="simple">
+<li><p>Create or load an <strong>MLRun project</strong></p></li>
+<li><p>Import a custom <strong>vLLM module</strong> from the MLRun Hub</p></li>
+<li><p>Deploy a <strong>vLLM OpenAI-compatible server</strong> as an MLRun application runtime</p></li>
+<li><p>Configure deployment parameters such as model, GPU count, memory, node selector, port, and log level</p></li>
+<li><p>Invoke the deployed service using the <code class="docutils literal notranslate"><span class="pre">/v1/chat/completions</span></code> endpoint</p></li>
+<li><p>Parse the response and extract only the assistant’s generated text</p></li>
+</ul>
+<p>By the end of this notebook, you will have a working vLLM deployment that can be queried directly from a Jupyter notebook using OpenAI-style APIs.</p>
+<p>For more information about <a class="reference external" href="https://docs.vllm.ai/en/latest/serving/openai_compatible_server/">vLLM documentation</a></p>
+</section>
+<section id="create-an-mlrun-project">
+<h2>1. Create an MLRun project<a class="headerlink" href="#create-an-mlrun-project" title="Link to this heading">#</a></h2>
+<p>In this section we create or load an MLRun project that will own the deployed vLLM application runtime.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">project</span> <span class="o">=</span> <span class="n">mlrun</span><span class="o">.</span><span class="n">get_or_create_project</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">"vllm-module"</span><span class="p">,</span> <span class="n">context</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span> <span class="n">user_project</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+<section id="import-the-vllm-module-from-the-mlrun-hub">
+<h2>2. Import the vLLM module from the MLRun Hub<a class="headerlink" href="#import-the-vllm-module-from-the-mlrun-hub" title="Link to this heading">#</a></h2>
+<p>In this section we import the vLLM module from the MLRun Hub so we can instantiate <code class="docutils literal notranslate"><span class="pre">VLLMModule</span></code> and deploy it as an application runtime.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">vllm</span> <span class="o">=</span> <span class="n">mlrun</span><span class="o">.</span><span class="n">import_module</span><span class="p">(</span><span class="s2">"hub://vllm-module"</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+<section id="deploy-the-vllm-application-runtime">
+<h2>3. Deploy the vLLM application runtime<a class="headerlink" href="#deploy-the-vllm-application-runtime" title="Link to this heading">#</a></h2>
+<p>Configure the vLLM deployment parameters and deploy the application.</p>
+<p>The returned address is the service URL for the application runtime.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Initialize the vLLM app</span>
+<span class="n">vllm_module</span> <span class="o">=</span> <span class="n">vllm</span><span class="o">.</span><span class="n">VLLMModule</span><span class="p">(</span>
+    <span class="n">project</span><span class="o">=</span><span class="n">project</span><span class="p">,</span>
+    <span class="n">node_selector</span><span class="o">=</span><span class="p">{</span><span class="s2">"alpha.eksctl.io/nodegroup-name"</span><span class="p">:</span> <span class="s2">"added-gpu"</span><span class="p">},</span>
+    <span class="n">name</span><span class="o">=</span><span class="s2">"qwen-vllm"</span><span class="p">,</span>
+    <span class="n">image</span><span class="o">=</span><span class="s2">"vllm/vllm-openai:latest"</span><span class="p">,</span>
+    <span class="n">model</span><span class="o">=</span><span class="s2">"Qwen/Qwen2.5-Omni-3B"</span><span class="p">,</span>
+    <span class="n">gpus</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
+    <span class="n">mem</span><span class="o">=</span><span class="s2">"10G"</span><span class="p">,</span>
+    <span class="n">port</span><span class="o">=</span><span class="mi">8000</span><span class="p">,</span>
+    <span class="n">dtype</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">,</span>
+    <span class="n">uvicorn_log_level</span><span class="o">=</span><span class="s2">"info"</span><span class="p">,</span>
+    <span class="n">max_tokens</span> <span class="o">=</span> <span class="mi">501</span><span class="p">,</span>
+<span class="p">)</span>
+
+<span class="c1"># Deploy the vLLM app</span>
+<span class="n">addr</span> <span class="o">=</span> <span class="n">vllm_module</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">deploy</span><span class="p">(</span><span class="n">with_mlrun</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<span class="n">addr</span>
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+<section id="get-the-runtime-handle">
+<h2>4. Get the runtime handle<a class="headerlink" href="#get-the-runtime-handle" title="Link to this heading">#</a></h2>
+<p>Fetch the runtime object and invoke the service using <code class="docutils literal notranslate"><span class="pre">app.invoke(...)</span></code>.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Optional: get_runtime() method uses to get the MLRun application runtime</span>
+<span class="n">app</span> <span class="o">=</span> <span class="n">vllm_module</span><span class="o">.</span><span class="n">get_runtime</span><span class="p">()</span>
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+<section id="send-a-chat-request-for-testing">
+<h2>5. Send a chat request for testing<a class="headerlink" href="#send-a-chat-request-for-testing" title="Link to this heading">#</a></h2>
+<p>Call the OpenAI compatible endpoint <code class="docutils literal notranslate"><span class="pre">/v1/chat/completions</span></code>, parse the JSON response, and print only the assistant message text.</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">body</span> <span class="o">=</span> <span class="p">{</span>
+    <span class="s2">"model"</span><span class="p">:</span> <span class="n">vllm_module</span><span class="o">.</span><span class="n">model</span><span class="p">,</span>
+    <span class="s2">"messages"</span><span class="p">:</span> <span class="p">[{</span><span class="s2">"role"</span><span class="p">:</span> <span class="s2">"user"</span><span class="p">,</span> <span class="s2">"content"</span><span class="p">:</span> <span class="s2">"what are the 3 countries with the most gpu as far as you know"</span><span class="p">}],</span>
+    <span class="s2">"max_tokens"</span><span class="p">:</span> <span class="n">vllm_module</span><span class="o">.</span><span class="n">max_tokens</span><span class="p">,</span>     <span class="c1"># start smaller for testing</span>
+<span class="p">}</span>
+
+<span class="n">resp</span> <span class="o">=</span> <span class="n">app</span><span class="o">.</span><span class="n">invoke</span><span class="p">(</span><span class="n">path</span><span class="o">=</span><span class="s2">"/v1/chat/completions"</span><span class="p">,</span> <span class="n">body</span><span class="o">=</span><span class="n">body</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+</div>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">data</span> <span class="o">=</span> <span class="n">resp</span>
+<span class="n">assistant_text</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="s2">"choices"</span><span class="p">][</span><span class="mi">0</span><span class="p">][</span><span class="s2">"message"</span><span class="p">][</span><span class="s2">"content"</span><span class="p">]</span>
+
+<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">assistant:</span><span class="se">\n</span><span class="s2">"</span><span class="p">)</span>
+<span class="nb">print</span><span class="p">(</span><span class="n">assistant_text</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span>
+</pre></div>
+</div>
+</div>
+<div class="cell_output docutils container">
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>assistant:
+
+As of the most commonly cited estimates, the three countries with the largest GPU capacity for AI workloads are the United States, China, and India.
+</pre></div>
+</div>
+</div>
+</div>
+</section>
+</section>
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
+<div class="sidebar-secondary-item">
+<div class="page-toc tocsection onthispage">
+<i class="fa-solid fa-list"></i> Contents
+  </div>
+<nav class="bd-toc-nav page-toc">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#prerequisite">Prerequisite</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#what-this-notebook-does">What this notebook does</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#create-an-mlrun-project">1. Create an MLRun project</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#import-the-vllm-module-from-the-mlrun-hub">2. Import the vLLM module from the MLRun Hub</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#deploy-the-vllm-application-runtime">3. Deploy the vLLM application runtime</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#get-the-runtime-handle">4. Get the runtime handle</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#send-a-chat-request-for-testing">5. Send a chat request for testing</a></li>
+</ul>
+</nav></div>
+</div></div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/latest/static/item.html b/modules/development/vllm_module/latest/static/item.html
new file mode 100644
index 00000000..9c7a1da0
--- /dev/null
+++ b/modules/development/vllm_module/latest/static/item.html
@@ -0,0 +1,51 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta content="IE=edge" http-equiv="X-UA-Compatible">
+    <meta content="width=device-width, initial-scale=1.0" name="viewport">
+    <link
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/styles/atom-one-dark.min.css"
+            rel="stylesheet"
+            integrity="sha384-oaMLBGEzBOJx3UHwac0cVndtX5fxGQIfnAeFZ35RTgqPcYlbprH9o9PUV/F8Le07"
+            crossorigin="anonymous"
+    />
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/highlight.min.js"
+            integrity="sha384-RH2xi4eIQ/gjtbs9fUXM68sLSi99C7ZWBRX1vDrVv6GQXRibxXLbwO2NGZB74MbU"
+            crossorigin="anonymous"
+    ></script>
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/languages/yaml.min.js"
+            integrity="sha384-A/iMReLA0Bo3tLydBIoOQXQzYnrwL90jkHYUubrtERUGCbIuU7U0EHge0Xd2s5sr"
+            crossorigin="anonymous"
+    ></script>
+    <title>Source</title>
+    <script>hljs.highlightAll();</script>
+</head>
+
+<body style="background-color:darkgray; margin: 0 0 0 0;">
+    <pre style="margin: 0 1em;">
+        <code class="yaml">
+apiVersion: v1
+categories:
+- genai
+description: Deploys a vLLM OpenAI-compatible LLM server as an MLRun application runtime, with configurable GPU usage, node selection, tensor parallelism, and runtime flags.
+example: vllm_module.ipynb
+generationDate: 2025-12-17:12-25
+hidden: false
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0
+name: vllm_module
+spec:
+    filename: vllm_module.py
+    image: mlrun/mlrun
+    kind: generic
+version: 1.0.0
+
+        </code>
+    </pre>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/latest/static/source.html b/modules/development/vllm_module/latest/static/source.html
new file mode 100644
index 00000000..4c6299ad
--- /dev/null
+++ b/modules/development/vllm_module/latest/static/source.html
@@ -0,0 +1,166 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta content="IE=edge" http-equiv="X-UA-Compatible">
+    <meta content="width=device-width, initial-scale=1.0" name="viewport">
+    <link
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/styles/atom-one-dark.min.css"
+            rel="stylesheet"
+            integrity="sha384-oaMLBGEzBOJx3UHwac0cVndtX5fxGQIfnAeFZ35RTgqPcYlbprH9o9PUV/F8Le07"
+            crossorigin="anonymous"
+    />
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/highlight.min.js"
+            integrity="sha384-RH2xi4eIQ/gjtbs9fUXM68sLSi99C7ZWBRX1vDrVv6GQXRibxXLbwO2NGZB74MbU"
+            crossorigin="anonymous"
+    ></script>
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/languages/python.min.js"
+            integrity="sha384-eXRt+aAa2ig1yFVDQCLis8k9s/1dikTcigj+/R07yNdIxc8BAG/b1uHDyEW3of17"
+            crossorigin="anonymous"
+    ></script>
+    <title>Source</title>
+    <script>hljs.highlightAll();</script>
+</head>
+
+<body style="background-color:darkgray; margin: 0 0 0 0;">
+    <pre style="margin: 0 1em;">
+        <code class="python">
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+#This module acts as a lightweight gateway to OpenAI-compatible APIs.
+#You can send chat prompts, create embeddings, or get model responses without worrying about authentication or endpoint differences. 
+#It simplifies access so you can test, analyze, or integrate AI features directly into your projects or notebooks with minimal setup.
+
+
+from typing import Dict, Optional, List
+
+class VLLMModule:
+    """
+    VLLMModule
+    
+    This module provides a lightweight wrapper for deploying a vLLM
+    (OpenAI-compatible) large language model server as an MLRun application runtime.
+    
+    The VLLMModule is responsible for:
+    - Creating an MLRun application runtime based on a vLLM container image
+    - Configuring GPU resources, memory limits, and Kubernetes node selection
+    - Launching the model using `vllm serve` with configurable runtime flags
+    - Supporting multi-GPU inference via tensor parallelism
+    - Automatically configuring shared memory (/dev/shm) when using multiple GPUs
+    - Exposing an OpenAI-compatible API (e.g. /v1/chat/completions) for inference
+    - Providing a simple Python interface for deployment and invocation from Jupyter notebooks
+    
+    The module is designed to be used in Jupyter notebooks and MLRun pipelines,
+    allowing users to deploy and test large language models on Kubernetes
+    with minimal configuration.
+    """
+
+    def __init__(
+            self,
+            project: str,
+            *,
+            node_selector: Optional[Dict[str, str]] = None,
+            name: str = "vllm",
+            image: str = "vllm/vllm-openai:latest",
+            model: str = "Qwen/Qwen2.5-Omni-3B",
+            gpus: int = 1,
+            mem: str = "10G",
+            port: int = 8000,
+            dtype: str = "auto",
+            uvicorn_log_level: str = "info",
+            max_tokens: int = 500,
+    ):
+        if gpus < 1:
+            raise ValueError("gpus must be >= 1")
+
+        
+        
+        if node_selector is None:
+            node_selector = {"alpha.eksctl.io/nodegroup-name": "added-gpu"}
+        
+        if not isinstance(max_tokens, int):
+            raise TypeError("max_tokens must be an integer")
+
+        if max_tokens < 1:
+            raise ValueError("max_tokens must be >= 1")
+
+        self.project = project
+        self.name = name
+        self.image = image
+        self.model = model
+        self.gpus = gpus
+        self.mem = mem
+        self.node_selector = node_selector
+        self.port = port
+        self.dtype = dtype
+        self.uvicorn_log_level = uvicorn_log_level
+        self.max_tokens = max_tokens
+
+        self.vllm_app = self.project.set_function(
+            name=self.name,
+            kind="application",
+            image=self.image,
+        )
+
+        self.vllm_app.with_limits(gpus=self.gpus, mem=self.mem)
+
+        if self.node_selector:
+            self.vllm_app.with_node_selection(node_selector=self.node_selector)
+
+        self.vllm_app.set_internal_application_port(self.port)
+
+        args: List[str] = [
+            "serve",
+            self.model,
+            "--dtype",
+            self.dtype,
+            "--port",
+            str(self.port),
+        ]
+
+        if self.uvicorn_log_level:
+            args += ["--uvicorn-log-level", self.uvicorn_log_level]
+
+        if self.gpus > 1:
+            args += ["--tensor-parallel-size", str(gpus)]
+
+            # For more than one GPU you should create a share volume for the multiple GPUs
+            self.vllm_app.spec.volumes = [{"name": "dshm", "emptyDir": {"medium": "Memory"}}]
+            self.vllm_app.spec.volume_mounts = [{"name": "dshm", "mountPath": "/dev/shm"}]
+
+    
+
+        self.vllm_app.spec.command = "vllm"
+        self.vllm_app.spec.args = args
+
+        self.vllm_app.spec.min_replicas = 1
+        self.vllm_app.spec.max_replicas = 1
+
+    def get_runtime(self):
+        return self.vllm_app
+
+    def add_args(self, extra_args: List[str]):
+        if not isinstance(extra_args, list) or not all(isinstance(x, str) for x in extra_args):
+            raise ValueError("extra_args must be a list of strings")
+        self.vllm_app.spec.args += extra_args
+
+
+        </code>
+    </pre>
+</body>
+</html>
\ No newline at end of file
diff --git a/modules/development/vllm_module/latest/static/vllm_module.html b/modules/development/vllm_module/latest/static/vllm_module.html
new file mode 100644
index 00000000..7b22280c
--- /dev/null
+++ b/modules/development/vllm_module/latest/static/vllm_module.html
@@ -0,0 +1,312 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="../../" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/>
+<title>vllm_module.vllm_module</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = '_modules/vllm_module/vllm_module';</script>
+<link href="../../genindex.html" rel="index" title="Index"/>
+<link href="../../search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="../../search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="../../index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1></h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+<h1>Source code for vllm_module.vllm_module</h1><div class="highlight"><pre>
+<span></span><span class="c1"># Copyright 2025 Iguazio</span>
+<span class="c1">#</span>
+<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
+<span class="c1"># you may not use this file except in compliance with the License.</span>
+<span class="c1"># You may obtain a copy of the License at</span>
+<span class="c1">#</span>
+<span class="c1">#     http://www.apache.org/licenses/LICENSE-2.0</span>
+<span class="c1">#</span>
+<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
+<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
+<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
+<span class="c1"># See the License for the specific language governing permissions and</span>
+<span class="c1"># limitations under the License.</span>
+<span class="c1">#</span>
+<span class="c1">#This module acts as a lightweight gateway to OpenAI-compatible APIs.</span>
+<span class="c1">#You can send chat prompts, create embeddings, or get model responses without worrying about authentication or endpoint differences. </span>
+<span class="c1">#It simplifies access so you can test, analyze, or integrate AI features directly into your projects or notebooks with minimal setup.</span>
+
+
+<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">List</span>
+
+<div class="viewcode-block" id="VLLMModule">
+<a class="viewcode-back" href="documentation.html#vllm_module.vllm_module.VLLMModule">[docs]</a>
+<span class="k">class</span><span class="w"> </span><span class="nc">VLLMModule</span><span class="p">:</span>
+<span class="w">    </span><span class="sd">"""</span>
+<span class="sd">    VLLMModule</span>
+<span class="sd">    </span>
+<span class="sd">    This module provides a lightweight wrapper for deploying a vLLM</span>
+<span class="sd">    (OpenAI-compatible) large language model server as an MLRun application runtime.</span>
+<span class="sd">    </span>
+<span class="sd">    The VLLMModule is responsible for:</span>
+<span class="sd">    - Creating an MLRun application runtime based on a vLLM container image</span>
+<span class="sd">    - Configuring GPU resources, memory limits, and Kubernetes node selection</span>
+<span class="sd">    - Launching the model using `vllm serve` with configurable runtime flags</span>
+<span class="sd">    - Supporting multi-GPU inference via tensor parallelism</span>
+<span class="sd">    - Automatically configuring shared memory (/dev/shm) when using multiple GPUs</span>
+<span class="sd">    - Exposing an OpenAI-compatible API (e.g. /v1/chat/completions) for inference</span>
+<span class="sd">    - Providing a simple Python interface for deployment and invocation from Jupyter notebooks</span>
+<span class="sd">    </span>
+<span class="sd">    The module is designed to be used in Jupyter notebooks and MLRun pipelines,</span>
+<span class="sd">    allowing users to deploy and test large language models on Kubernetes</span>
+<span class="sd">    with minimal configuration.</span>
+<span class="sd">    """</span>
+
+    <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span>
+            <span class="bp">self</span><span class="p">,</span>
+            <span class="n">project</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
+            <span class="o">*</span><span class="p">,</span>
+            <span class="n">node_selector</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
+            <span class="n">name</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"vllm"</span><span class="p">,</span>
+            <span class="n">image</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"vllm/vllm-openai:latest"</span><span class="p">,</span>
+            <span class="n">model</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"Qwen/Qwen2.5-Omni-3B"</span><span class="p">,</span>
+            <span class="n">gpus</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
+            <span class="n">mem</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"10G"</span><span class="p">,</span>
+            <span class="n">port</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">8000</span><span class="p">,</span>
+            <span class="n">dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"auto"</span><span class="p">,</span>
+            <span class="n">uvicorn_log_level</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"info"</span><span class="p">,</span>
+            <span class="n">max_tokens</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">500</span><span class="p">,</span>
+    <span class="p">):</span>
+        <span class="k">if</span> <span class="n">gpus</span> <span class="o">&lt;</span> <span class="mi">1</span><span class="p">:</span>
+            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"gpus must be &gt;= 1"</span><span class="p">)</span>
+
+        
+        
+        <span class="k">if</span> <span class="n">node_selector</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+            <span class="n">node_selector</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"alpha.eksctl.io/nodegroup-name"</span><span class="p">:</span> <span class="s2">"added-gpu"</span><span class="p">}</span>
+        
+        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">max_tokens</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
+            <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"max_tokens must be an integer"</span><span class="p">)</span>
+
+        <span class="k">if</span> <span class="n">max_tokens</span> <span class="o">&lt;</span> <span class="mi">1</span><span class="p">:</span>
+            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"max_tokens must be &gt;= 1"</span><span class="p">)</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">project</span> <span class="o">=</span> <span class="n">project</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">name</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">image</span> <span class="o">=</span> <span class="n">image</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">gpus</span> <span class="o">=</span> <span class="n">gpus</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">mem</span> <span class="o">=</span> <span class="n">mem</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">node_selector</span> <span class="o">=</span> <span class="n">node_selector</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">port</span> <span class="o">=</span> <span class="n">port</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">dtype</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">uvicorn_log_level</span> <span class="o">=</span> <span class="n">uvicorn_log_level</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">max_tokens</span> <span class="o">=</span> <span class="n">max_tokens</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="o">.</span><span class="n">set_function</span><span class="p">(</span>
+            <span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">,</span>
+            <span class="n">kind</span><span class="o">=</span><span class="s2">"application"</span><span class="p">,</span>
+            <span class="n">image</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">image</span><span class="p">,</span>
+        <span class="p">)</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">with_limits</span><span class="p">(</span><span class="n">gpus</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gpus</span><span class="p">,</span> <span class="n">mem</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mem</span><span class="p">)</span>
+
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">node_selector</span><span class="p">:</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">with_node_selection</span><span class="p">(</span><span class="n">node_selector</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">node_selector</span><span class="p">)</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">set_internal_application_port</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="p">)</span>
+
+        <span class="n">args</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span>
+            <span class="s2">"serve"</span><span class="p">,</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">,</span>
+            <span class="s2">"--dtype"</span><span class="p">,</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
+            <span class="s2">"--port"</span><span class="p">,</span>
+            <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="p">),</span>
+        <span class="p">]</span>
+
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">uvicorn_log_level</span><span class="p">:</span>
+            <span class="n">args</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--uvicorn-log-level"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uvicorn_log_level</span><span class="p">]</span>
+
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">gpus</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
+            <span class="n">args</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--tensor-parallel-size"</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">gpus</span><span class="p">)]</span>
+
+            <span class="c1"># For more than one GPU you should create a share volume for the multiple GPUs</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">volumes</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"dshm"</span><span class="p">,</span> <span class="s2">"emptyDir"</span><span class="p">:</span> <span class="p">{</span><span class="s2">"medium"</span><span class="p">:</span> <span class="s2">"Memory"</span><span class="p">}}]</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">volume_mounts</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"dshm"</span><span class="p">,</span> <span class="s2">"mountPath"</span><span class="p">:</span> <span class="s2">"/dev/shm"</span><span class="p">}]</span>
+
+    
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">command</span> <span class="o">=</span> <span class="s2">"vllm"</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">args</span> <span class="o">=</span> <span class="n">args</span>
+
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">min_replicas</span> <span class="o">=</span> <span class="mi">1</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">max_replicas</span> <span class="o">=</span> <span class="mi">1</span>
+
+<div class="viewcode-block" id="VLLMModule.get_runtime">
+<a class="viewcode-back" href="documentation.html#vllm_module.vllm_module.VLLMModule.get_runtime">[docs]</a>
+    <span class="k">def</span><span class="w"> </span><span class="nf">get_runtime</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span></div>
+
+
+<div class="viewcode-block" id="VLLMModule.add_args">
+<a class="viewcode-back" href="documentation.html#vllm_module.vllm_module.VLLMModule.add_args">[docs]</a>
+    <span class="k">def</span><span class="w"> </span><span class="nf">add_args</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">extra_args</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
+        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">extra_args</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span> <span class="ow">or</span> <span class="ow">not</span> <span class="nb">all</span><span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">extra_args</span><span class="p">):</span>
+            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"extra_args must be a list of strings"</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">vllm_app</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">args</span> <span class="o">+=</span> <span class="n">extra_args</span></div>
+</div>
+
+
+</pre></div>
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/steps/development/catalog.json b/steps/development/catalog.json
index 9e26dfee..46c55c64 100644
--- a/steps/development/catalog.json
+++ b/steps/development/catalog.json
@@ -1 +1 @@
-{}
\ No newline at end of file
+{"verify_schema": {"latest": {"apiVersion": "v1", "categories": ["data-preparation", "model-serving", "utilities"], "description": "Verifies the event is aligned with the provided schema", "example": "verify_schema.ipynb", "generationDate": "2025-12-29:11-59", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "verify_schema", "className": "VerifySchema", "defaultHandler": null, "spec": {"filename": "verify_schema.py", "image": "mlrun/mlrun", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/verify_schema.ipynb", "source": "src/verify_schema.py", "docs": "static/documentation.html"}}, "1.0.0": {"apiVersion": "v1", "categories": ["data-preparation", "model-serving", "utilities"], "description": "Verifies the event is aligned with the provided schema", "example": "verify_schema.ipynb", "generationDate": "2025-12-29:11-59", "hidden": false, "labels": {"author": "Iguazio"}, "mlrunVersion": "1.10.0", "name": "verify_schema", "className": "VerifySchema", "defaultHandler": null, "spec": {"filename": "verify_schema.py", "image": "mlrun/mlrun", "requirements": null}, "version": "1.0.0", "assets": {"example": "src/verify_schema.ipynb", "source": "src/verify_schema.py", "docs": "static/documentation.html"}}}}
\ No newline at end of file
diff --git a/steps/development/tags.json b/steps/development/tags.json
index 42383339..8262034e 100644
--- a/steps/development/tags.json
+++ b/steps/development/tags.json
@@ -1 +1 @@
-{"categories": [], "kind": []}
\ No newline at end of file
+{"categories": ["utilities", "data-preparation", "model-serving"], "kind": []}
\ No newline at end of file
diff --git a/steps/development/verify_schema/1.0.0/src/item.yaml b/steps/development/verify_schema/1.0.0/src/item.yaml
new file mode 100644
index 00000000..eca91c6a
--- /dev/null
+++ b/steps/development/verify_schema/1.0.0/src/item.yaml
@@ -0,0 +1,20 @@
+apiVersion: v1
+categories:
+  - data-preparation
+  - model-serving
+  - utilities
+description: Verifies the event is aligned with the provided schema
+example: verify_schema.ipynb
+generationDate: 2025-12-29:11-59    
+hidden: false                                       
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0
+name: verify_schema                        
+className: VerifySchema
+defaultHandler:     
+spec:
+  filename: verify_schema.py              
+  image: mlrun/mlrun                                
+  requirements:
+version: 1.0.0                                      
\ No newline at end of file
diff --git a/steps/development/verify_schema/1.0.0/src/test_verify_schema.py b/steps/development/verify_schema/1.0.0/src/test_verify_schema.py
new file mode 100644
index 00000000..5a7e08b5
--- /dev/null
+++ b/steps/development/verify_schema/1.0.0/src/test_verify_schema.py
@@ -0,0 +1,66 @@
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from verify_schema import VerifySchema
+
+class TestVerifySchema:
+    def test_verify_schema(self):
+        schema = ["id", "name", "active"]
+        verifier = VerifySchema(schema=schema, allow_unexpected_keys=False)
+
+        # Test with valid event
+        event = {
+            "id": 1,
+            "name": "Test Event",
+            "active": True
+        }
+        result = verifier.do(event)
+        assert result == event
+
+        # Test with missing key
+        event_missing_key = {
+            "id": 1,
+            "name": "Test Event"
+        }
+        try:
+            verifier.do(event_missing_key)
+        except KeyError as e:
+            assert "missing keys {'active'} in event" in str(e)
+
+        # Test with unexpected key
+        event_unexpected_key = {
+            "id": 1,
+            "name": "Test Event",
+            "active": True,
+            "extra": "unexpected"
+        }
+        try:
+            verifier.do(event_unexpected_key)
+        except KeyError as e:
+            assert "unexpected keys {'extra'} in event" in str(e)
+
+    def test_verify_schema_allow_unexpected(self):
+        schema = ["id", "name", "active"]
+        verifier = VerifySchema(schema=schema, allow_unexpected_keys=True)
+
+        # Test with valid event and unexpected key
+        event = {
+            "id": 1,
+            "name": "Test Event",
+            "active": True,
+            "extra": "unexpected"
+        }
+        result = verifier.do(event)
+        assert result == event
\ No newline at end of file
diff --git a/steps/development/verify_schema/1.0.0/src/verify_schema.ipynb b/steps/development/verify_schema/1.0.0/src/verify_schema.ipynb
new file mode 100644
index 00000000..954e80cb
--- /dev/null
+++ b/steps/development/verify_schema/1.0.0/src/verify_schema.ipynb
@@ -0,0 +1,33 @@
+{
+ "cells": [
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "556b36b9b89d0515"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/steps/development/verify_schema/1.0.0/src/verify_schema.py b/steps/development/verify_schema/1.0.0/src/verify_schema.py
new file mode 100644
index 00000000..80a37956
--- /dev/null
+++ b/steps/development/verify_schema/1.0.0/src/verify_schema.py
@@ -0,0 +1,40 @@
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+class VerifySchema:
+    """
+    This step validates that an event dictionary contains exactly the keys defined in the schema,
+    raising a KeyError if any are missing or unexpected.
+    """
+
+    def __init__(self, schema: list, allow_unexpected_keys: bool = False):
+        self.schema = schema
+        self.allow_unexpected_keys = allow_unexpected_keys
+
+    def do(self, event: dict):
+        # Check if all keys in the expected schema are present in the event
+        missing = set(self.schema) - set(event)
+        if missing:
+            raise KeyError(f"Schema verification failed: missing keys {missing} in event: {event}")
+
+        if self.allow_unexpected_keys:
+            return event
+
+        # Check if there are any unexpected keys in the event
+        unexpected = set(event) - set(self.schema)
+        if unexpected:
+            raise KeyError(f"Schema verification failed: unexpected keys {unexpected} in event: {event}")
+
+        return event
diff --git a/steps/development/verify_schema/1.0.0/static/documentation.html b/steps/development/verify_schema/1.0.0/static/documentation.html
new file mode 100644
index 00000000..0939bbaa
--- /dev/null
+++ b/steps/development/verify_schema/1.0.0/static/documentation.html
@@ -0,0 +1,230 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="./" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/><meta content="width=device-width, initial-scale=1" name="viewport"/>
+<title>verify_schema package</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = 'verify_schema';</script>
+<link href="genindex.html" rel="index" title="Index"/>
+<link href="search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<div class="dropdown dropdown-download-buttons">
+<button aria-expanded="false" aria-label="Download this page" class="btn dropdown-toggle" data-bs-toggle="dropdown" type="button">
+<i class="fas fa-download"></i>
+</button>
+<ul class="dropdown-menu">
+<li><a class="btn btn-sm btn-download-source-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" href="_sources/verify_schema.rst" target="_blank" title="Download source file">
+<span class="btn__icon-container">
+<i class="fas fa-file"></i>
+</span>
+<span class="btn__text-container">.rst</span>
+</a>
+</li>
+<li>
+<button class="btn btn-sm btn-download-pdf-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" onclick="window.print()" title="Print to PDF">
+<span class="btn__icon-container">
+<i class="fas fa-file-pdf"></i>
+</span>
+<span class="btn__text-container">.pdf</span>
+</button>
+</li>
+</ul>
+</div>
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+<button class="sidebar-toggle secondary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle secondary sidebar">
+<span class="fa-solid fa-list"></span>
+</button>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1>verify_schema package</h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+<div>
+<h2> Contents </h2>
+</div>
+<nav aria-label="Page">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#submodules">Submodules</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#verify-schema-verify-schema-module">verify_schema.verify_schema module</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-contents">Module contents</a></li>
+</ul>
+</nav>
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+<section id="verify-schema-package">
+<h1>verify_schema package<a class="headerlink" href="#verify-schema-package" title="Link to this heading">#</a></h1>
+<section id="submodules">
+<h2>Submodules<a class="headerlink" href="#submodules" title="Link to this heading">#</a></h2>
+</section>
+<section id="verify-schema-verify-schema-module">
+<h2>verify_schema.verify_schema module<a class="headerlink" href="#verify-schema-verify-schema-module" title="Link to this heading">#</a></h2>
+</section>
+<section id="module-contents">
+<h2>Module contents<a class="headerlink" href="#module-contents" title="Link to this heading">#</a></h2>
+</section>
+</section>
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
+<div class="sidebar-secondary-item">
+<div class="page-toc tocsection onthispage">
+<i class="fa-solid fa-list"></i> Contents
+  </div>
+<nav class="bd-toc-nav page-toc">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#submodules">Submodules</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#verify-schema-verify-schema-module">verify_schema.verify_schema module</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-contents">Module contents</a></li>
+</ul>
+</nav></div>
+</div></div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/steps/development/verify_schema/1.0.0/static/example.html b/steps/development/verify_schema/1.0.0/static/example.html
new file mode 100644
index 00000000..7c7e9cfa
--- /dev/null
+++ b/steps/development/verify_schema/1.0.0/static/example.html
@@ -0,0 +1,212 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="./" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/><meta content="width=device-width, initial-scale=1" name="viewport"/>
+<title>&lt;no title&gt;</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = 'verify_schema_example';</script>
+<link href="genindex.html" rel="index" title="Index"/>
+<link href="search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<div class="dropdown dropdown-download-buttons">
+<button aria-expanded="false" aria-label="Download this page" class="btn dropdown-toggle" data-bs-toggle="dropdown" type="button">
+<i class="fas fa-download"></i>
+</button>
+<ul class="dropdown-menu">
+<li><a class="btn btn-sm btn-download-source-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" href="../src/verify_schema.ipynb" target="_blank" title="Download source file">
+<span class="btn__icon-container">
+<i class="fas fa-file"></i>
+</span>
+<span class="btn__text-container">.ipynb</span>
+</a>
+</li>
+<li>
+<button class="btn btn-sm btn-download-pdf-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" onclick="window.print()" title="Print to PDF">
+<span class="btn__icon-container">
+<i class="fas fa-file-pdf"></i>
+</span>
+<span class="btn__text-container">.pdf</span>
+</button>
+</li>
+</ul>
+</div>
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+<button class="sidebar-toggle secondary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle secondary sidebar">
+<span class="fa-solid fa-list"></span>
+</button>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1><no title=""></no></h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+<div>
+<h2> Contents </h2>
+</div>
+<nav aria-label="Page">
+<ul class="simple visible nav section-nav flex-column">
+</ul>
+</nav>
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
+<div class="sidebar-secondary-item">
+<div class="page-toc tocsection onthispage">
+<i class="fa-solid fa-list"></i> Contents
+  </div>
+<nav class="bd-toc-nav page-toc">
+<ul class="simple visible nav section-nav flex-column">
+</ul>
+</nav></div>
+</div></div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/steps/development/verify_schema/1.0.0/static/item.html b/steps/development/verify_schema/1.0.0/static/item.html
new file mode 100644
index 00000000..91d6c7e9
--- /dev/null
+++ b/steps/development/verify_schema/1.0.0/static/item.html
@@ -0,0 +1,54 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta content="IE=edge" http-equiv="X-UA-Compatible">
+    <meta content="width=device-width, initial-scale=1.0" name="viewport">
+    <link
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/styles/atom-one-dark.min.css"
+            rel="stylesheet"
+            integrity="sha384-oaMLBGEzBOJx3UHwac0cVndtX5fxGQIfnAeFZ35RTgqPcYlbprH9o9PUV/F8Le07"
+            crossorigin="anonymous"
+    />
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/highlight.min.js"
+            integrity="sha384-RH2xi4eIQ/gjtbs9fUXM68sLSi99C7ZWBRX1vDrVv6GQXRibxXLbwO2NGZB74MbU"
+            crossorigin="anonymous"
+    ></script>
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/languages/yaml.min.js"
+            integrity="sha384-A/iMReLA0Bo3tLydBIoOQXQzYnrwL90jkHYUubrtERUGCbIuU7U0EHge0Xd2s5sr"
+            crossorigin="anonymous"
+    ></script>
+    <title>Source</title>
+    <script>hljs.highlightAll();</script>
+</head>
+
+<body style="background-color:darkgray; margin: 0 0 0 0;">
+    <pre style="margin: 0 1em;">
+        <code class="yaml">
+apiVersion: v1
+categories:
+  - data-preparation
+  - model-serving
+  - utilities
+description: Verifies the event is aligned with the provided schema
+example: verify_schema.ipynb
+generationDate: 2025-12-29:11-59    
+hidden: false                                       
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0
+name: verify_schema                        
+className: VerifySchema
+defaultHandler:     
+spec:
+  filename: verify_schema.py              
+  image: mlrun/mlrun                                
+  requirements:
+version: 1.0.0                                      
+        </code>
+    </pre>
+</body>
+</html>
\ No newline at end of file
diff --git a/steps/development/verify_schema/1.0.0/static/source.html b/steps/development/verify_schema/1.0.0/static/source.html
new file mode 100644
index 00000000..5b0ba35e
--- /dev/null
+++ b/steps/development/verify_schema/1.0.0/static/source.html
@@ -0,0 +1,75 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta content="IE=edge" http-equiv="X-UA-Compatible">
+    <meta content="width=device-width, initial-scale=1.0" name="viewport">
+    <link
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/styles/atom-one-dark.min.css"
+            rel="stylesheet"
+            integrity="sha384-oaMLBGEzBOJx3UHwac0cVndtX5fxGQIfnAeFZ35RTgqPcYlbprH9o9PUV/F8Le07"
+            crossorigin="anonymous"
+    />
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/highlight.min.js"
+            integrity="sha384-RH2xi4eIQ/gjtbs9fUXM68sLSi99C7ZWBRX1vDrVv6GQXRibxXLbwO2NGZB74MbU"
+            crossorigin="anonymous"
+    ></script>
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/languages/python.min.js"
+            integrity="sha384-eXRt+aAa2ig1yFVDQCLis8k9s/1dikTcigj+/R07yNdIxc8BAG/b1uHDyEW3of17"
+            crossorigin="anonymous"
+    ></script>
+    <title>Source</title>
+    <script>hljs.highlightAll();</script>
+</head>
+
+<body style="background-color:darkgray; margin: 0 0 0 0;">
+    <pre style="margin: 0 1em;">
+        <code class="python">
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+class VerifySchema:
+    """
+    This step validates that an event dictionary contains exactly the keys defined in the schema,
+    raising a KeyError if any are missing or unexpected.
+    """
+
+    def __init__(self, schema: list, allow_unexpected_keys: bool = False):
+        self.schema = schema
+        self.allow_unexpected_keys = allow_unexpected_keys
+
+    def do(self, event: dict):
+        # Check if all keys in the expected schema are present in the event
+        missing = set(self.schema) - set(event)
+        if missing:
+            raise KeyError(f"Schema verification failed: missing keys {missing} in event: {event}")
+
+        if self.allow_unexpected_keys:
+            return event
+
+        # Check if there are any unexpected keys in the event
+        unexpected = set(event) - set(self.schema)
+        if unexpected:
+            raise KeyError(f"Schema verification failed: unexpected keys {unexpected} in event: {event}")
+
+        return event
+
+        </code>
+    </pre>
+</body>
+</html>
\ No newline at end of file
diff --git a/steps/development/verify_schema/latest/src/item.yaml b/steps/development/verify_schema/latest/src/item.yaml
new file mode 100644
index 00000000..eca91c6a
--- /dev/null
+++ b/steps/development/verify_schema/latest/src/item.yaml
@@ -0,0 +1,20 @@
+apiVersion: v1
+categories:
+  - data-preparation
+  - model-serving
+  - utilities
+description: Verifies the event is aligned with the provided schema
+example: verify_schema.ipynb
+generationDate: 2025-12-29:11-59    
+hidden: false                                       
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0
+name: verify_schema                        
+className: VerifySchema
+defaultHandler:     
+spec:
+  filename: verify_schema.py              
+  image: mlrun/mlrun                                
+  requirements:
+version: 1.0.0                                      
\ No newline at end of file
diff --git a/steps/development/verify_schema/latest/src/test_verify_schema.py b/steps/development/verify_schema/latest/src/test_verify_schema.py
new file mode 100644
index 00000000..5a7e08b5
--- /dev/null
+++ b/steps/development/verify_schema/latest/src/test_verify_schema.py
@@ -0,0 +1,66 @@
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from verify_schema import VerifySchema
+
+class TestVerifySchema:
+    def test_verify_schema(self):
+        schema = ["id", "name", "active"]
+        verifier = VerifySchema(schema=schema, allow_unexpected_keys=False)
+
+        # Test with valid event
+        event = {
+            "id": 1,
+            "name": "Test Event",
+            "active": True
+        }
+        result = verifier.do(event)
+        assert result == event
+
+        # Test with missing key
+        event_missing_key = {
+            "id": 1,
+            "name": "Test Event"
+        }
+        try:
+            verifier.do(event_missing_key)
+        except KeyError as e:
+            assert "missing keys {'active'} in event" in str(e)
+
+        # Test with unexpected key
+        event_unexpected_key = {
+            "id": 1,
+            "name": "Test Event",
+            "active": True,
+            "extra": "unexpected"
+        }
+        try:
+            verifier.do(event_unexpected_key)
+        except KeyError as e:
+            assert "unexpected keys {'extra'} in event" in str(e)
+
+    def test_verify_schema_allow_unexpected(self):
+        schema = ["id", "name", "active"]
+        verifier = VerifySchema(schema=schema, allow_unexpected_keys=True)
+
+        # Test with valid event and unexpected key
+        event = {
+            "id": 1,
+            "name": "Test Event",
+            "active": True,
+            "extra": "unexpected"
+        }
+        result = verifier.do(event)
+        assert result == event
\ No newline at end of file
diff --git a/steps/development/verify_schema/latest/src/verify_schema.ipynb b/steps/development/verify_schema/latest/src/verify_schema.ipynb
new file mode 100644
index 00000000..954e80cb
--- /dev/null
+++ b/steps/development/verify_schema/latest/src/verify_schema.ipynb
@@ -0,0 +1,33 @@
+{
+ "cells": [
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "556b36b9b89d0515"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/steps/development/verify_schema/latest/src/verify_schema.py b/steps/development/verify_schema/latest/src/verify_schema.py
new file mode 100644
index 00000000..80a37956
--- /dev/null
+++ b/steps/development/verify_schema/latest/src/verify_schema.py
@@ -0,0 +1,40 @@
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+class VerifySchema:
+    """
+    This step validates that an event dictionary contains exactly the keys defined in the schema,
+    raising a KeyError if any are missing or unexpected.
+    """
+
+    def __init__(self, schema: list, allow_unexpected_keys: bool = False):
+        self.schema = schema
+        self.allow_unexpected_keys = allow_unexpected_keys
+
+    def do(self, event: dict):
+        # Check if all keys in the expected schema are present in the event
+        missing = set(self.schema) - set(event)
+        if missing:
+            raise KeyError(f"Schema verification failed: missing keys {missing} in event: {event}")
+
+        if self.allow_unexpected_keys:
+            return event
+
+        # Check if there are any unexpected keys in the event
+        unexpected = set(event) - set(self.schema)
+        if unexpected:
+            raise KeyError(f"Schema verification failed: unexpected keys {unexpected} in event: {event}")
+
+        return event
diff --git a/steps/development/verify_schema/latest/static/documentation.html b/steps/development/verify_schema/latest/static/documentation.html
new file mode 100644
index 00000000..0939bbaa
--- /dev/null
+++ b/steps/development/verify_schema/latest/static/documentation.html
@@ -0,0 +1,230 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="./" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/><meta content="width=device-width, initial-scale=1" name="viewport"/>
+<title>verify_schema package</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = 'verify_schema';</script>
+<link href="genindex.html" rel="index" title="Index"/>
+<link href="search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<div class="dropdown dropdown-download-buttons">
+<button aria-expanded="false" aria-label="Download this page" class="btn dropdown-toggle" data-bs-toggle="dropdown" type="button">
+<i class="fas fa-download"></i>
+</button>
+<ul class="dropdown-menu">
+<li><a class="btn btn-sm btn-download-source-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" href="_sources/verify_schema.rst" target="_blank" title="Download source file">
+<span class="btn__icon-container">
+<i class="fas fa-file"></i>
+</span>
+<span class="btn__text-container">.rst</span>
+</a>
+</li>
+<li>
+<button class="btn btn-sm btn-download-pdf-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" onclick="window.print()" title="Print to PDF">
+<span class="btn__icon-container">
+<i class="fas fa-file-pdf"></i>
+</span>
+<span class="btn__text-container">.pdf</span>
+</button>
+</li>
+</ul>
+</div>
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+<button class="sidebar-toggle secondary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle secondary sidebar">
+<span class="fa-solid fa-list"></span>
+</button>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1>verify_schema package</h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+<div>
+<h2> Contents </h2>
+</div>
+<nav aria-label="Page">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#submodules">Submodules</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#verify-schema-verify-schema-module">verify_schema.verify_schema module</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-contents">Module contents</a></li>
+</ul>
+</nav>
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+<section id="verify-schema-package">
+<h1>verify_schema package<a class="headerlink" href="#verify-schema-package" title="Link to this heading">#</a></h1>
+<section id="submodules">
+<h2>Submodules<a class="headerlink" href="#submodules" title="Link to this heading">#</a></h2>
+</section>
+<section id="verify-schema-verify-schema-module">
+<h2>verify_schema.verify_schema module<a class="headerlink" href="#verify-schema-verify-schema-module" title="Link to this heading">#</a></h2>
+</section>
+<section id="module-contents">
+<h2>Module contents<a class="headerlink" href="#module-contents" title="Link to this heading">#</a></h2>
+</section>
+</section>
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
+<div class="sidebar-secondary-item">
+<div class="page-toc tocsection onthispage">
+<i class="fa-solid fa-list"></i> Contents
+  </div>
+<nav class="bd-toc-nav page-toc">
+<ul class="visible nav section-nav flex-column">
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#submodules">Submodules</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#verify-schema-verify-schema-module">verify_schema.verify_schema module</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#module-contents">Module contents</a></li>
+</ul>
+</nav></div>
+</div></div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/steps/development/verify_schema/latest/static/example.html b/steps/development/verify_schema/latest/static/example.html
new file mode 100644
index 00000000..7c7e9cfa
--- /dev/null
+++ b/steps/development/verify_schema/latest/static/example.html
@@ -0,0 +1,212 @@
+
+<!DOCTYPE html>
+
+<html data-content_root="./" data-theme="light" lang="en">
+<head>
+<meta charset="utf-8"/>
+<meta content="width=device-width, initial-scale=1.0" name="viewport"/><meta content="width=device-width, initial-scale=1" name="viewport"/>
+<title>&lt;no title&gt;</title>
+<script data-cfasync="false">
+    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
+    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
+  </script>
+<!-- Loaded before other Sphinx assets -->
+<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" rel="preload" type="font/woff2"/>
+<link as="font" crossorigin="" href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" rel="preload" type="font/woff2"/>
+<link href="../../../_static/pygments.css?v=8f2a1f02" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/styles/sphinx-book-theme.css?v=eba8b062" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/mystnb.8ecb98da25f57f5357bf6f572d296f466b2cfe2517ffebfabe82451661e28f02.css" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/togglebutton.css?v=13237357" rel="stylesheet" type="text/css"/>
+<link href="../../../_static/css/custom.css?v=a569c0df" rel="stylesheet" type="text/css"/>
+<!-- Pre-loaded scripts that we'll load fully later -->
+<link as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<link as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" rel="preload"/>
+<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/documentation_options.js?v=9eb32ce0"></script>
+<script src="../../../_static/doctools.js?v=9bcbadda"></script>
+<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
+<script>let toggleHintShow = 'Click to show';</script>
+<script>let toggleHintHide = 'Click to hide';</script>
+<script>let toggleOpenOnPrint = 'true';</script>
+<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
+<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
+<script>DOCUMENTATION_OPTIONS.pagename = 'verify_schema_example';</script>
+<link href="genindex.html" rel="index" title="Index"/>
+<link href="search.html" rel="search" title="Search"/>
+<meta content="width=device-width, initial-scale=1" name="viewport"/>
+<meta content="en" name="docsearch:language"/>
+</head>
+<body data-bs-root-margin="0px 0px -60%" data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-default-mode="light" data-offset="180">
+<div class="skip-link d-print-none" id="pst-skip-link"><a href="#main-content">Skip to main content</a></div>
+<div id="pst-scroll-pixel-helper"></div>
+<button class="btn rounded-pill" id="pst-back-to-top" type="button">
+<i class="fa-solid fa-arrow-up"></i>Back to top</button>
+<input class="sidebar-toggle" id="pst-primary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
+<input class="sidebar-toggle" id="pst-secondary-sidebar-checkbox" type="checkbox"/>
+<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
+<div class="search-button__wrapper">
+<div class="search-button__overlay"></div>
+<div class="search-button__search-container">
+<form action="search.html" class="bd-search d-flex align-items-center" method="get">
+<i class="fa-solid fa-magnifying-glass"></i>
+<input aria-label="" autocapitalize="off" autocomplete="off" autocorrect="off" class="form-control" id="search-input" name="q" placeholder="" spellcheck="false" type="search"/>
+<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
+</form></div>
+</div>
+<div class="pst-async-banner-revealer d-none">
+<aside aria-label="Version warning" class="d-none d-print-none" id="bd-header-version-warning"></aside>
+</div>
+<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
+</header>
+<div class="bd-container">
+<div class="bd-container__inner bd-page-width">
+<div class="bd-sidebar-primary bd-sidebar">
+<div class="sidebar-header-items sidebar-primary__section">
+</div>
+<div class="sidebar-primary-items__start sidebar-primary__section">
+<div class="sidebar-primary-item">
+<a class="navbar-brand logo" href="index.html">
+<p class="title logo__title"></p>
+</a></div>
+<div class="sidebar-primary-item">
+<script>
+ document.write(`
+   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass"></i>
+    <span class="search-button__default-text">Search</span>
+    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
+   </button>
+ `);
+ </script></div>
+<div class="sidebar-primary-item"><nav aria-label="Main" class="bd-links bd-docs-nav">
+<div class="bd-toc-item navbar-nav active">
+</div>
+</nav></div>
+</div>
+<div class="sidebar-primary-items__end sidebar-primary__section">
+</div>
+<div id="rtd-footer-container"></div>
+</div>
+<main class="bd-main" id="main-content" role="main">
+<div class="sbt-scroll-pixel-helper"></div>
+<div class="bd-content">
+<div class="bd-article-container">
+<div class="bd-header-article d-print-none">
+<div class="header-article-items header-article__inner">
+<div class="header-article-items__start">
+<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle primary sidebar">
+<span class="fa-solid fa-bars"></span>
+</button></div>
+</div>
+<div class="header-article-items__end">
+<div class="header-article-item">
+<div class="article-header-buttons">
+<div class="dropdown dropdown-download-buttons">
+<button aria-expanded="false" aria-label="Download this page" class="btn dropdown-toggle" data-bs-toggle="dropdown" type="button">
+<i class="fas fa-download"></i>
+</button>
+<ul class="dropdown-menu">
+<li><a class="btn btn-sm btn-download-source-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" href="../src/verify_schema.ipynb" target="_blank" title="Download source file">
+<span class="btn__icon-container">
+<i class="fas fa-file"></i>
+</span>
+<span class="btn__text-container">.ipynb</span>
+</a>
+</li>
+<li>
+<button class="btn btn-sm btn-download-pdf-button dropdown-item" data-bs-placement="left" data-bs-toggle="tooltip" onclick="window.print()" title="Print to PDF">
+<span class="btn__icon-container">
+<i class="fas fa-file-pdf"></i>
+</span>
+<span class="btn__text-container">.pdf</span>
+</button>
+</li>
+</ul>
+</div>
+<script>
+document.write(`
+  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
+    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
+    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
+  </button>
+`);
+</script>
+<script>
+document.write(`
+  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
+    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
+  </button>
+`);
+</script>
+<button class="sidebar-toggle secondary-toggle btn btn-sm" data-bs-placement="bottom" data-bs-toggle="tooltip" title="Toggle secondary sidebar">
+<span class="fa-solid fa-list"></span>
+</button>
+</div></div>
+</div>
+</div>
+</div>
+<div class="onlyprint" id="jb-print-docs-body">
+<h1><no title=""></no></h1>
+<!-- Table of contents -->
+<div id="print-main-content">
+<div id="jb-print-toc">
+<div>
+<h2> Contents </h2>
+</div>
+<nav aria-label="Page">
+<ul class="simple visible nav section-nav flex-column">
+</ul>
+</nav>
+</div>
+</div>
+</div>
+<div id="searchbox"></div>
+<article class="bd-article">
+</article>
+<footer class="prev-next-footer d-print-none">
+<div class="prev-next-area">
+</div>
+</footer>
+</div>
+<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
+<div class="sidebar-secondary-item">
+<div class="page-toc tocsection onthispage">
+<i class="fa-solid fa-list"></i> Contents
+  </div>
+<nav class="bd-toc-nav page-toc">
+<ul class="simple visible nav section-nav flex-column">
+</ul>
+</nav></div>
+</div></div>
+</div>
+<footer class="bd-footer-content">
+<div class="bd-footer-content__inner container">
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+<div class="footer-item">
+</div>
+</div>
+</footer>
+</main>
+</div>
+</div>
+<!-- Scripts loaded after <body> so the DOM is not blocked -->
+<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
+<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
+<footer class="bd-footer">
+</footer>
+</body>
+</html>
\ No newline at end of file
diff --git a/steps/development/verify_schema/latest/static/item.html b/steps/development/verify_schema/latest/static/item.html
new file mode 100644
index 00000000..91d6c7e9
--- /dev/null
+++ b/steps/development/verify_schema/latest/static/item.html
@@ -0,0 +1,54 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta content="IE=edge" http-equiv="X-UA-Compatible">
+    <meta content="width=device-width, initial-scale=1.0" name="viewport">
+    <link
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/styles/atom-one-dark.min.css"
+            rel="stylesheet"
+            integrity="sha384-oaMLBGEzBOJx3UHwac0cVndtX5fxGQIfnAeFZ35RTgqPcYlbprH9o9PUV/F8Le07"
+            crossorigin="anonymous"
+    />
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/highlight.min.js"
+            integrity="sha384-RH2xi4eIQ/gjtbs9fUXM68sLSi99C7ZWBRX1vDrVv6GQXRibxXLbwO2NGZB74MbU"
+            crossorigin="anonymous"
+    ></script>
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/languages/yaml.min.js"
+            integrity="sha384-A/iMReLA0Bo3tLydBIoOQXQzYnrwL90jkHYUubrtERUGCbIuU7U0EHge0Xd2s5sr"
+            crossorigin="anonymous"
+    ></script>
+    <title>Source</title>
+    <script>hljs.highlightAll();</script>
+</head>
+
+<body style="background-color:darkgray; margin: 0 0 0 0;">
+    <pre style="margin: 0 1em;">
+        <code class="yaml">
+apiVersion: v1
+categories:
+  - data-preparation
+  - model-serving
+  - utilities
+description: Verifies the event is aligned with the provided schema
+example: verify_schema.ipynb
+generationDate: 2025-12-29:11-59    
+hidden: false                                       
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0
+name: verify_schema                        
+className: VerifySchema
+defaultHandler:     
+spec:
+  filename: verify_schema.py              
+  image: mlrun/mlrun                                
+  requirements:
+version: 1.0.0                                      
+        </code>
+    </pre>
+</body>
+</html>
\ No newline at end of file
diff --git a/steps/development/verify_schema/latest/static/source.html b/steps/development/verify_schema/latest/static/source.html
new file mode 100644
index 00000000..5b0ba35e
--- /dev/null
+++ b/steps/development/verify_schema/latest/static/source.html
@@ -0,0 +1,75 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta content="IE=edge" http-equiv="X-UA-Compatible">
+    <meta content="width=device-width, initial-scale=1.0" name="viewport">
+    <link
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/styles/atom-one-dark.min.css"
+            rel="stylesheet"
+            integrity="sha384-oaMLBGEzBOJx3UHwac0cVndtX5fxGQIfnAeFZ35RTgqPcYlbprH9o9PUV/F8Le07"
+            crossorigin="anonymous"
+    />
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/highlight.min.js"
+            integrity="sha384-RH2xi4eIQ/gjtbs9fUXM68sLSi99C7ZWBRX1vDrVv6GQXRibxXLbwO2NGZB74MbU"
+            crossorigin="anonymous"
+    ></script>
+    <script
+            src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.11.1/languages/python.min.js"
+            integrity="sha384-eXRt+aAa2ig1yFVDQCLis8k9s/1dikTcigj+/R07yNdIxc8BAG/b1uHDyEW3of17"
+            crossorigin="anonymous"
+    ></script>
+    <title>Source</title>
+    <script>hljs.highlightAll();</script>
+</head>
+
+<body style="background-color:darkgray; margin: 0 0 0 0;">
+    <pre style="margin: 0 1em;">
+        <code class="python">
+# Copyright 2025 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+class VerifySchema:
+    """
+    This step validates that an event dictionary contains exactly the keys defined in the schema,
+    raising a KeyError if any are missing or unexpected.
+    """
+
+    def __init__(self, schema: list, allow_unexpected_keys: bool = False):
+        self.schema = schema
+        self.allow_unexpected_keys = allow_unexpected_keys
+
+    def do(self, event: dict):
+        # Check if all keys in the expected schema are present in the event
+        missing = set(self.schema) - set(event)
+        if missing:
+            raise KeyError(f"Schema verification failed: missing keys {missing} in event: {event}")
+
+        if self.allow_unexpected_keys:
+            return event
+
+        # Check if there are any unexpected keys in the event
+        unexpected = set(event) - set(self.schema)
+        if unexpected:
+            raise KeyError(f"Schema verification failed: unexpected keys {unexpected} in event: {event}")
+
+        return event
+
+        </code>
+    </pre>
+</body>
+</html>
\ No newline at end of file