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
- fix(extractors): don't treat a generator's own "error" field as failure in LLMMetadataExtractor
- LinkContentFetcher mutates caller-provided client_kwargs
- OpenAIChatGenerator: tools in generation_kwargs silently drop the component's own tools
- Fix LinkContentFetcher mutates caller-provided client_kwargs #12828
- InMemoryDocumentStore's default BM25 tokenizer never splits a Korean noun from an attached particle — 0/10 recall in a same-structure EN/KO benchmark
- fix: default BM25 tokenizer splits CJK characters for bare-term retrieval
- FilterPolicy.MERGE unions OR/NOT filters instead of intersecting them, returning documents the init filter excludes
- fix: allow template variables in {% message %} name attribute
- ChatMessage._to_trace_dict() leaks raw base64 data for ImageContent and FileContent in ToolCallResult
- fix: keep both filters when FilterPolicy.MERGE combines OR/NOT filters
- Docs
- Python not yet supported