Skip to content

feat: add matching retrieval utilities and model integration#123

Merged
zerolovesea merged 1 commit into
mainfrom
dev
Jun 1, 2026
Merged

feat: add matching retrieval utilities and model integration#123
zerolovesea merged 1 commit into
mainfrom
dev

Conversation

@zerolovesea

Copy link
Copy Markdown
Owner
  • Introduced EmbeddingTable and FaissVectorIndex for managing embeddings and similarity searches.
  • Implemented methods for saving/loading embedding tables in CSV and Parquet formats.
  • Enhanced compute_pair_scores function to utilize feature data loaders for batch processing.
  • Added tests for embedding table functionality, including roundtrip serialization and model integration.
  • Developed tests for FAISS index operations, ensuring correct behavior for search and streaming exports.
  • Integrated new matching models with existing prediction APIs and added relevant tests for their functionality.

- Introduced EmbeddingTable and FaissVectorIndex for managing embeddings and similarity searches.
- Implemented methods for saving/loading embedding tables in CSV and Parquet formats.
- Enhanced compute_pair_scores function to utilize feature data loaders for batch processing.
- Added tests for embedding table functionality, including roundtrip serialization and model integration.
- Developed tests for FAISS index operations, ensuring correct behavior for search and streaming exports.
- Integrated new matching models with existing prediction APIs and added relevant tests for their functionality.
@zerolovesea zerolovesea merged commit d6270a4 into main Jun 1, 2026
15 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant