Preserve Oracle vector store metadata - #6702
Open
HuitaePark wants to merge 1 commit into
Open
Conversation
Serialize OracleJsonValue metadata when re-adding documents returned by OracleVectorStore. Add an integration test covering the metadata retrieve-and-add round trip. Fixes spring-projects#3838 Signed-off-by: HuitaePark <qkrgmlxo3174@gmail.com>
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #3838
Problem
OracleVectorStoredoes not preserve user-defined metadata when a document returned bysimilaritySearch()is added to the vector store again.When metadata is initially added, values such as strings are represented using standard Java types:
After the document is stored in Oracle and retrieved through
similaritySearch(), metadata values read from the Oracle JSON column are represented asOracleJsonValueimplementations.For example, a string metadata value is returned as an Oracle JSON string value rather than a standard Java
String.When the retrieved
Documentis added again,OracleVectorStore.toJson()only serializes a limited set of Java scalar types:StringIntegerFloatDoubleBooleanBecause
OracleJsonValuewas not handled, those metadata entries were silently skipped during serialization.As a result, the following round trip removed the original user-defined metadata:
Before this change, the second retrieval contained only generated metadata such as:
The original
conversationIdentry was no longer present.Changes
This change adds support for serializing
OracleJsonValueinstances directly throughOracleJsonGenerator.This allows metadata returned by Oracle to be written back without being silently discarded.
Testing
Added an integration test that:
similaritySearch().OracleJsonValue.OracleVectorStoreagain.The regression test fails before the fix because the metadata is removed, and passes after
OracleJsonValueserialization is supported.