arcade-mcp/examples/langchain/studio/README.md at f23d80fdff1089875efcff8efe1819ae656d10e7

- **New Class Structure**: Introduced `ToolManager` and
`AsyncToolManager` classes (`ArcadeToolManager` is deprecated)
- **Async Support**: Full async implementation for modern LangChain
applications
- **Better Tool Management**: New methods for adding individual tools
and toolkits
- **CI/CD**: for langchain_arcade


## Upgrade Changes

```python
# Old pattern
manager = ArcadeToolManager(api_key="...")
tools = manager.get_tools(toolkits=["Google"])

# New pattern
manager = ToolManager(api_key="...")
manager.init_tools(toolkits=["Google"])
tools = manager.to_langchain()
```

Now supports underscores vs dots in tool names for better model
compatibility.

2025-03-10 18:52:06 -07:00

854 B

Raw Blame History

Setup

Environment

Copy the env.example file to .env and supply your API keys for at least OPENAI_API_KEY and ARCADE_API_KEY.

Arcade API key: ARCADE_API_KEY (instructions here)
OpenAI API key: OPENAI_API_KEY (instructions here)

Usage with LangGraph API

Local testing with LangGraph Studio

Download LangGraph Studio and open this directory in the Studio application.

The langgraph.json file in this directory specifies the graph that will be loaded in Studio.

Deploying to LangGraph Cloud

Follow these instructions to deploy your graph to LangGraph Cloud.

854 B Raw Blame History