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 supported4 Subscribers
Add a CodeTriage badge to haystack
Help out
- Issues
- fix(filters): raise FilterError when comparing naive and aware datetimes in ordering operators
- fix: divide DocumentMAPEvaluator average precision by all relevant documents
- fix: increasing telemetry event version to `Pipeline run (3.x)`
- docs: fix stale docs - pt.1
- fix: make strict datetime filter comparison opt-in
- Ordering and equality filters disagree on naive vs tz-aware datetimes
- fix: deep-copy document metadata in Markdown, CSV and hierarchical splitters
- Splitters share nested metadata between chunks and with the input document
- docs: sync Haystack API reference on Docusaurus
- docs: add Pixeltable to choosing a Document Store
- Docs
- Python not yet supported