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: count literal special-token strings as ordinary text in TiktokenCounter
- Pipeline.run misclassifies dictionary-valued flat inputs as component inputs
- MetaFieldGroupingRanker groups documents with a None group_by value under "None"
- Log values inside lists and dicts skip the size bound from #12849
- Bigram tokenization for CJK BM25: per-character tokens fix recall but cost precision
- Async lifecycle fallbacks block the event loop for sync-only components
- fix: accept dictionary-valued flat pipeline inputs
- fix: avoid blocking QueryExpander lifecycle fallbacks
- fix: treat literal tiktoken special tokens as ordinary text in TiktokenCounter
- fix: count literal special-token strings in TiktokenCounter
- Docs
- Python not yet supported