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
Add a CodeTriage badge to langchain
Help out
- Issues
- RunnableWithMessageHistory deserializes constructor-shaped output into live SystemMessage and persists it to history
- `RunnableRetry` does not fire `on_retry` callback
- fix(langchain): avoid shared process-group kill in shell middleware
- Suggestion: Improve extensibility of _create_chat_result for custom metrics
- Improve BaseMessage.pretty_repr for multimodal content
- fix(openai): add support for logprobs when using the response api
- ShellToolMiddleware may kill caller process group when create_process_group=False
- Agents silently fail to deal with structured responses when models forget to make a tool call.
- docs(security): add initial threat model for langchain monorepo
- Expose Deep Agent Harness as Composable LangGraph Primitives
- Docs
- Python not yet supported