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 supported3 Subscribers
Add a CodeTriage badge to haystack
Help out
- Issues
- Feedback on naming of Tool parameters
- Feature Request: `pipeline.run()` Progress Bar
- Evaluation Metrics for Retrieval should have flexible comparison attributes to allow for consistent evaluation across different chunking strategies
- Reduce number of deepcopies in `Pipeline.run` to reduce latency
- Add another way to specify "unsafe" type routing without jinja to ConditionalRouter
- Add support for Pipeline breakpointing in `AsyncPipeline`
- Investigate `__hash__` implementation for `Document`, `Socket`, and `PipelineBase`
- Follow-Up: Schema-Based Serialization Improvements
- Handle Document ids consistently and enable custom `id_hash_keys`
- Extend image support to more components
- Docs
- Python not yet supported