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
- Range filters fill missing parts of partial dates with the current date
- Fix/python splitter inline docstring
- fix: keep literal N/A and NULL cells in CSVDocumentSplitter
- fix: support typing.Annotated in type serialization
- fix: validate complete arrays against explicit array schemas
- TextCleaner joins remove_regexps into one regex, breaking backreferences, repeated group names and inline flags
- fix: apply each TextCleaner remove_regexps pattern independently
- perf: reuse the embeddings matrix across InMemoryDocumentStore embedding queries (17x faster at 10k docs)
- Multi-vector retrieval - initial support
- fix: reject multi-label cross encoders in SASEvaluator
- Docs
- Python not yet supported