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
- Add parallel component execution to Pipeline using a thread pool executor
- Benchmark Haystack Pipeline
- Simple local token tracking for Pipelines
- Feature: GuardrailProvider interface for automated tool-call policy enforcement
- EU AI Act compliance scan results — Haystack scored #1, wanted to validate findings
- Connecting multiple `documents` outputs to `PromptBuilder.documents` is not possible
- Add references to related LLM framework projects (LangChain and LlamaIndex)
- Feature: Add link_format parameter to PDFMinerToDocument and PyPDFToDocument
- Ensure stable, low-effort integrations
- Make pipelines less complex
- Docs
- Python not yet supported