deepset-ai / haystack

:mag: AI 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 for building RAG, question answering, semantic search or conversational agent chatbots.
https://haystack.deepset.ai
Apache License 2.0
16.94k stars 1.85k forks source link

fix: deserialize Document Stores using specific `from_dict` class methods #8207

Closed anakin87 closed 1 month ago

anakin87 commented 1 month ago

Related Issues

Proposed Changes:

Make these generic components (SentenceWindowRetriever, ...) deserialize a Document Store using its specific from_dict class method (if available) instead of default_from_dict.

How did you test it?

CI

Checklist

coveralls commented 1 month ago

Pull Request Test Coverage Report for Build 10367813119

Details


Files with Coverage Reduction New Missed Lines %
components/caching/cache_checker.py 1 97.44%
components/retrievers/filter_retriever.py 1 85.29%
components/writers/document_writer.py 1 94.59%
components/retrievers/sentence_window_retriever.py 6 82.14%
<!-- Total: 9 -->
Totals Coverage Status
Change from base Build 10351241196: -0.04%
Covered Lines: 6958
Relevant Lines: 7725

💛 - Coveralls