langchain
https://github.com/langchain-ai/langchain
Python
⚡ Building applications with LLMs through composability ⚡
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported39 Subscribers
View all SubscribersAdd a CodeTriage badge to langchain
Help out
- Issues
- Add BuiltinToolsMiddleWare to support native llm builtin tools like web_search, code_execution, file_content, etc.
- In agent, there is no suitable reasoning_content for deepseek
- Streaming Output for Multi-Agent Systems
- chore(langchain): improve typing of agent decorators
- FilesystemMiddleware pass wrong type of data in wrap_model_call
- OpenAI payload fails with KeyError: 'role' when reasoning-enabled/Responses API path is used
- [Middleware] supports wrap_agent_call
- tool arg validation dumps injected args
- [Docs] Add security guide for RAG applications (prompt injection, data leakage)
- fix(langchain): add command validation to ShellToolMiddleware
- Docs
- Python not yet supported