feat: The SentenceWindowRetriever has now an extra output key containing all the documents belonging to the context window

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.

Apache License 2.0

16.93k stars 1.85k forks source link

Proposed Changes:

Adds an extra key in the output of the SentenceWindowRetriever, returning a List[Document] containing all the Document objects belonging to the context window

How did you test it?

unit tests, integration tests, manual verification

Notes for the reviewer

I've decided for a extra output key so that there are no breaking changes.

Checklist

I have read the contributors guidelines and the code of conduct
I have updated the related issue with new insights and changes
I added unit tests and updated the docstrings
I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test:.
I documented my code
I ran pre-commit hooks and fixed any issue

Pull Request Test Coverage Report for Build 10574185228

Details

0 of 0 changed or added relevant lines in 0 files are covered.

10 unchanged lines in 1 file lost coverage.

Overall coverage decreased (-0.02%) to 90.186%

Files with Coverage Reduction	New Missed Lines	%
components/retrievers/sentence_window_retriever.py	10	76.09%
<!--	Total:	10		-->

Files with Coverage Reduction

New Missed Lines

components/retrievers/sentence_window_retriever.py

76.09%

<!--

Total:

-->

Totals
Change from base Build 10528666835:	-0.02%
Covered Lines:	6975
Relevant Lines:	7734

Totals

Change from base Build 10528666835:

-0.02%

Covered Lines:

6975

Relevant Lines:

7734

deepset-ai / haystack