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 supported41 Subscribers
Add a CodeTriage badge to langchain
Help out
- Issues
- core: docstring examples import from nonexistent modules (output_parser, runnable, documents.Blob)
- langchain-classic: importing a moved agent from `agent_toolkits` raises `ValueError` instead of `ImportError`
- fix(openai,anthropic,groq): hide `default_headers` from serialization and `repr`
- fix(anthropic): redact MCP `authorization_token` from invocation params
- fix(core): exclude prefixed credential keys from `configurable` tracing metadata
- @wrap_tool_call loses custom ContextT and becomes incompatible with create_agent(context_schema=...)
- fix(openai): require an explicit model in `ChatOpenAI`
- fix(langchain): stop `jump_to="tools"` from bypassing HITL review
- PIIMiddleware `url` detector redacts version numbers, ratios and dotted identifiers ("Node.js/Express", "1.5/2.0", "python3.12/site-packages") as URLs
- [Feature] Security Docs: Add Runtime Security Middleware for Agents (Prompt/Command Injection)
- Docs
- Python not yet supported