docs: updating DocumentSplitter docstring, adding supported DocumentSores

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

docs: updating DocumentSplitter docstring, adding supported DocumentSores #8270

Closed davidsbatista closed 1 month ago

davidsbatista commented 1 month ago

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

coveralls commented 1 month ago

Pull Request Test Coverage Report for Build 10527111686

Details

0 of 0 changed or added relevant lines in 0 files are covered.
1 unchanged line in 1 file lost coverage.
Overall coverage remained the same at 90.21%

Files with Coverage Reduction	New Missed Lines	%
components/preprocessors/document_splitter.py	1	98.96%
<!--	Total:	1		-->

Totals
Change from base Build 10522538514:	0.0%
Covered Lines:	6975
Relevant Lines:	7732

💛 - Coveralls

anakin87 commented 1 month ago

Sorry, we talked about it offline with David.

DocumentSplitter is and should be compatible with each Document Store we support.

Only some specific metadata produced by this component is not supported (and discarded) by some Document Stores. We should express this clearly.

davidsbatista commented 1 month ago

I've added a single disclaimer explaining that _split_overlap with Chroma is lost and added the same info to the docs. I would merge it now.