haystack
https://github.com/deepset-ai/haystack
Python
:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited
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 supported5 Subscribers
Add a CodeTriage badge to haystack
Help out
- Issues
- build(deps): bump @vercel/node from 29.0.1 to 30.0.0 in /docs-website
- fix: let Pipeline.connect accept a Literal output for an input of its value type
- Agent: optional wall-clock time budget (max_agent_time_seconds) to complement max_agent_steps
- feat: Add SemanticResolver component for entity resolution using TEI (#10985)
- fix: name a tool output handler that has no __name__
- fix: raise FilterError for incomparable document values in range filters
- fix: keep subclasses in the remaining content part from_dict methods
- docs: clarify AutoMergingRetriever's two-store contract and parentless-document error
- [Bug]: DocumentJoiner in distribution_based_rank_fusion mode turns every score of a list into NaN when one score is not finite
- [Bug]: FallbackChatGenerator forwards a failed attempt's partial stream, so the streamed answer contains the abandoned prefix
- Docs
- Python not yet supported