Skip to content

v0.8.1 - Vector Store Source ID Fix

Choose a tag to compare

View all tags
@github-actions github-actions released this 13 Feb 19:38
· 43 commits to master since this release
v0.8.1
This tag was signed with the committer’s verified signature.
atharva-again Atharva Verma
SSH Key Fingerprint: EVkylvfg5YojWUpLRVgkS2oi25JQenGjBQEkSCTgJo4
Verified
Learn about vigilant mode.
2a79dfd
This commit was signed with the committer’s verified signature.
atharva-again Atharva Verma
SSH Key Fingerprint: EVkylvfg5YojWUpLRVgkS2oi25JQenGjBQEkSCTgJo4
Verified
Learn about vigilant mode.

Fixed

  • Leaky abstraction in vector stores: Vector store providers now use canonical source_id instead of raw source_url. This fixes issue #19 where backends had to parse Source IDs from URLs.
    • Added source_id to StageContext for pipeline-wide canonical ID
    • Renamed VectorStoreProvider.delete_by_source() to delete_by_source_id()
    • Updated all vector store implementations (ChromaDB, Pinecone, Weaviate, Supabase) to filter by source_id
    • Updated metadata to use source_id instead of source_url

Migration Note

⚠️ Existing vector stores with source_url metadata will need to be re-indexed for force=True deletion to work. Alternatively, users can manually delete via the vector store's native tools.

Assets 4
Loading