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
- Resuming a pipeline from a snapshot file turns int dict keys into strings
- fix: preserve non-string dict keys in pipeline snapshot serialization
- fix: keep literal NA and N/A cell values in XLSXToDocument #12945
- PythonCodeSplitter: secondary-split pieces all report the whole function's start_line/end_line
- docs: add VLLMSparseTextEmbedder and VLLMSparseDocumentEmbedder pages
- fix: match the LinkContentFetcher content type case-insensitively
- fix: report per-piece line ranges for PythonCodeSplitter secondary splits
- Title: FaithfulnessEvaluator accepts mismatched statement and score counts as evaluated results
- Proposal: opt-in retrieval report tracer for retriever spans (no pipeline-run record, no cost)
- fix: validate faithfulness statement-score alignment
- Docs
- Python not yet supported