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
- `trim_messages` breaks when `token_counter` is a per-message callable (lambda, subclass annotation, or postponed annotations)
- fix(openai): omit timeout from client_params when not set by user
- fix(anthropic): omit timeout from client_params when not set by user
- docs(core): clarify supported formats for multimodal inputs in ModelProfile
- fix(core): fix `trim_messages` misclassification of per-message token_counter
- ChatOpenAI/ChatAnthropic: request_timeout=None (default) disables SDK timeout, causing infinite hangs
- fix(core): prevent inflated token counts when merging streaming usage_metadata
- count_tokens_approximately: missing handler for tool_use content blocks causes ~2.4x overcounting
- MCP Header Forwarding Failure (Discovery Phase)
- fix(langchain)!: default to `google_genai` instead of `google_vertexai`
- Docs
- Python not yet supported