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
- chore(model-profiles): refresh model profile data
- Inconsistent `generations` shape in chat model streaming `on_llm_error` callbacks: emits `[[]]` and `[[chunk], []]` where every other path emits `[]`
- Stale `xfail` markers in `langchain-core` tests: `test_convert_to_openai_function_nested_v2` and `test_sync_in_sync_lambdas` pass but are marked expected-to-fail
- Public API for safe message retention cutoff
- Responses API with streaming and a nested Pydantic schema results in invalid strict JSON schema (additionalProperties/required missing on $defs)
- ChatOpenRouter writes generation_info twice causing double strings as values
- init_chat_model fails to infer `openai` provider for `o4` models (e.g. o4-mini)
- count_tokens_approximately over-counts audio/video/file blocks by char-counting their base64 payload
- Silent quality degradation in multi-agent flat round-table: 34.3/100 without synthesis node vs 86.3/100 with it
- feat(openrouter): surface `parallel_tool_calls` on `bind_tools`
- Docs
- Python not yet supported