Add MultiVectorRetriever as a foundation for ParentDocumentRetriever #2349
+192
−0
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
seungy0
changed the title
Signed-off-by: Seunggyu Lee <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hello.
I noticed that there is an open issue requesting a ParentDocumentRetriever in Spring AI #63, and I’d like to contribute by implementing it.
Following the approach used in LangChain, I am introducing a MultiVectorRetriever that retrieves small document chunks from a vector store. The ParentDocumentRetriever will then extend this retriever to fetch the full parent documents based on the retrieved chunks.
As a first step, this PR introduces:
MultiVectorRetriever: Retrieves relevant small chunks from a VectorStore.
DocumentStore Interface: A key-value storage interface for retrieving full parent documents.
I’d love to get your feedback on this approach before proceeding with the ParentDocumentRetriever implementation. If this direction looks good, I’ll continue working on the next part.
Looking forward to your thoughts! Thanks!