Metadata-Version: 2.4
Name: langgraph-gaussdb-fastapi
Version: 0.2.0
Summary: A FastAPI LangGraph-compatible server backed by GaussDB.
Classifier: Development Status :: 3 - Alpha
Classifier: Framework :: FastAPI
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: async-gaussdb>=0.1.0
Requires-Dist: croniter>=2.0.0
Requires-Dist: fastapi>=0.110.0
Requires-Dist: httpx>=0.27.0
Requires-Dist: langchain-core>=0.3.0
Requires-Dist: langchain-openai>=0.3.0
Requires-Dist: langgraph>=1.0.0
Requires-Dist: langgraph-checkpoint>=2.0.0
Requires-Dist: langgraph-sdk>=0.3.0
Requires-Dist: pydantic-settings>=2.0.0
Requires-Dist: uvicorn>=0.30.0
Provides-Extra: chainlit
Requires-Dist: chainlit>=2.0.0; extra == "chainlit"

# LangGraph GaussDB FastAPI

A FastAPI server that implements key LangGraph Platform-compatible endpoints with async GaussDB persistence.

## Install

```bash
python -m pip install langgraph-gaussdb-fastapi
```

To run the packaged Chainlit prototype too:

```bash
python -m pip install "langgraph-gaussdb-fastapi[chainlit]"
```

## Run

Set the database connection with environment variables, then start the server:

```bash
LG_DB_HOST=127.0.0.1 \
LG_DB_USER=remote_user \
LG_DB_PASSWORD=your-password \
LG_DB_NAME=langgraph \
langgraph-gaussdb-fastapi
```

The default graph config now comes from the packaged `server_config.json`. You can still override it with `LG_GRAPH_CONFIG`.

```json
{
  "dependencies": [],
  "graphs": {
    "echo": "graph.example_graph:graph",
    "qwen_tools": "graph.qwen_tools_graph:graph"
  }
}
```

Health checks are available at `/` and `/ok`.

## Chainlit

The distribution includes the Chainlit prototype under the package namespace plus a launcher script:

```bash
LANGGRAPH_SERVER_URL=http://127.0.0.1:2026 \
langgraph-gaussdb-chainlit --headless --host 0.0.0.0 --port 8010
```

You can also run the packaged smoke test directly:

```bash
python -m langgraph_gaussdb_fastapi.chainlit_app.smoke_test
```
