feat(database): Implement PgVectorStore abstraction (Resolves #287) - #1389
Open
parastejpal987-cmyk wants to merge 1 commit into
Open
feat(database): Implement PgVectorStore abstraction (Resolves #287)#1389parastejpal987-cmyk wants to merge 1 commit into
parastejpal987-cmyk wants to merge 1 commit into
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR introduces the
PgVectorStoreclass to provide a standardized, clean abstraction layer for managing and querying vector embeddings in PostgreSQL.It directly resolves Issue #287 by encapsulating vector operations while remaining completely non-disruptive to the existing core engine.
Changes Made
src/khoj/database/adapters/vector_store.pywith thePgVectorStoreimplementation.pgvector.django.CosineDistancemetric and Khoj's nativeUserMemorymodel to ensure seamless integration without requiring new, invasive database migrations.add,search, anddeletemethods with proper type hinting and owner-based filtering to safely segregate user and agent data namespaces.Motivation
This abstraction makes it significantly easier to interact with
pgvectoracross the codebase, reducing raw query repetition and paving the way for easier maintenance and future search optimizations.