: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.
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.
Proposed Changes:
Adds an extra key in the output of the
SentenceWindowRetriever
, returning aList[Document]
containing all the Document objects belonging to the context windowHow 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
fix:
,feat:
,build:
,chore:
,ci:
,docs:
,style:
,refactor:
,perf:
,test:
.