refactor(examples): split OpenAI Slim workflows into separate example directories

README.md

@@ -46,37 +46,12 @@ make test
 `make dev` installs the project, syncs development dependencies, and sets up
 [`prek`](https://prek.j178.dev/) Git hooks.
 
-## Run the Example Workflow
+## Examples
 
-The repository includes a minimal runnable example at
-[`examples/graphon_openai_slim`](examples/graphon_openai_slim).
+Runnable examples live under [`examples/`](examples/).
 
-It builds and executes this workflow:
-
-```text
-start -> llm -> output
-```
-
-To run it:
-
-```bash
-make dev
-source .venv/bin/activate
-cd examples/graphon_openai_slim
-cp .env.example .env
-python3 workflow.py "Explain Graphon in one short sentence."
-```
-
-Before running the example, fill in the required values in `.env`.
-
-The example currently expects:
-
-- an `OPENAI_API_KEY`
-- a `SLIM_PLUGIN_ID`
-- a local `dify-plugin-daemon-slim` setup or equivalent Slim runtime
-
-For the exact environment variables and runtime notes, see
-[examples/graphon_openai_slim/README.md](examples/graphon_openai_slim/README.md).
+Each example is self-contained in its own subdirectory and includes its own
+setup instructions, environment template, and `workflow.py` entrypoint.
 
 ## How Graphon Fits Together
 
@@ -88,8 +63,8 @@ At a high level, Graphon usage looks like this:
 4. Run `GraphEngine` and consume emitted graph events.
 5. Read final outputs from runtime state.
 
-The bundled example follows exactly that path. The execution loop is centered
-around `GraphEngine.run()`:
+The examples under [`examples/`](examples/) follow exactly that path. The
+execution loop is centered around `GraphEngine.run()`:
 
 ```python
 engine = GraphEngine(
@@ -103,10 +78,8 @@ for event in engine.run():
     ...
 ```
 
-See
-[examples/graphon_openai_slim/workflow.py](examples/graphon_openai_slim/workflow.py)
-for the full example, including `SlimRuntime`, `SlimPreparedLLM`, graph
-construction, input seeding, and streamed output handling.
+See [`examples/`](examples/) for the current runnable workflows and their
+example-specific setup notes.
 
 ## Project Layout
 
@@ -126,8 +99,7 @@ construction, input seeding, and streamed output handling.
 ## Internal Docs
 
 - [CONTRIBUTING.md](CONTRIBUTING.md): contributor workflow, CI, commit/PR rules
-- [examples/graphon_openai_slim/README.md](examples/graphon_openai_slim/README.md):
-  runnable example setup
+- [examples/](examples/): runnable examples and per-example setup notes
 - [src/graphon/model_runtime/README.md](src/graphon/model_runtime/README.md):
   model runtime overview
 - [src/graphon/graph_engine/layers/README.md](src/graphon/graph_engine/layers/README.md):

examples/graphon_openai_slim/.env.example → examples/openai_slim_minimal/.env.example

@@ -1,7 +1,7 @@
-# Example configuration for `examples/graphon_openai_slim/workflow.py`.
+# Example configuration for `examples/openai_slim_minimal/workflow.py`.
 #
-# The example loads `examples/graphon_openai_slim/.env` automatically. Copy this file to `.env`
-# in the same directory and fill in the required values.
+# The example loads `.env` from this directory automatically. Copy this file to
+# `.env` in the same directory and fill in the required values.
 
 # Required: OpenAI API key used by the OpenAI Slim plugin.
 OPENAI_API_KEY=
@@ -13,17 +13,16 @@ OPENAI_API_KEY=
 SLIM_PLUGIN_ID=langgenius/openai:0.3.0@99770a45f77910fe0f64c985524f4fe2294fc6ea25cbf1053ba6bddd7604d850
 
 # Optional: path to the local `dify-plugin-daemon-slim` binary.
-# If empty, Graphon will look for `dify-plugin-daemon-slim` in `PATH`.
-SLIM_BINARY_PATH=
+# Recommended Unix default: a user-local install under `~/.local/bin`.
+SLIM_BINARY_PATH=~/.local/bin/dify-plugin-daemon-slim
 
 # Optional: provider name inside the plugin package.
 # For this example we only support OpenAI, so this should stay `openai`.
 SLIM_PROVIDER=openai
 
 # Optional: local folder where Slim stores downloaded/extracted plugins.
-# The default points at the repository-root `.slim/plugins` cache so this
-# example directory does not accumulate generated plugin code.
-SLIM_PLUGIN_FOLDER=../../.slim/plugins
+# Recommended Unix default: a user-local plugin cache under `~/.local/share`.
+SLIM_PLUGIN_FOLDER=~/.local/share/graphon/slim/plugins
 
 # Optional: path to an already unpacked local plugin directory.
 # If set, Slim uses this directory directly and skips marketplace download.

examples/openai_slim_minimal/README.md

@@ -0,0 +1,29 @@
+# OpenAI Slim Minimal Example
+
+A tiny Graphon workflow:
+
+`start -> llm -> output`
+
+## What You Need
+
+- `workflow.py`: runnable example
+- `.env.example`: template settings
+- `.env`: your local copy of the template
+
+## Run
+
+```bash
+cd examples/openai_slim_minimal
+cp .env.example .env
+python3 workflow.py
+```
+
+Fill in `.env` before running. The script reads `.env` from this directory.
+
+## Custom Prompt
+
+```bash
+python3 workflow.py "Explain graph sparsity in one sentence."
+```
+
+The example streams text to stdout as it arrives. If nothing is streamed, it prints the final answer at the end.

examples/openai_slim_minimal/__init__.py

@@ -0,0 +1 @@
+"""Minimal OpenAI Slim workflow example for Graphon."""