Dev

[csmangum]

This pull request introduces several improvements and updates across multiple areas, including enhanced handling of Redis index checks, improved filtering logic for memory metadata, updates to embedding generation and storage workflows, and refinements to similarity search functionality. Additionally, test cases and debugging utilities have been updated to reflect these changes.

Enhancements to Redis and Metadata Handling

• Improved Redis index check to ensure compatibility by converting both the index name and list items to strings for comparison in _ensure_index (memory/embeddings/vector_store.py).
• Enhanced filtering logic in find_similar_memories to support nested metadata structures, enabling more flexible and accurate filtering (memory/embeddings/vector_store.py).

Embedding Workflow Updates

• Updated load_memory_system_from_json to directly create Redis connection parameters instead of relying on a connection_params attribute. Added logic to generate embeddings if missing, ensuring all memories have embeddings stored (memory/utils/serialization.py). [1] [2]

Similarity Search Improvements

• Refactored the SimilaritySearchStrategy to use the memory_system directly, simplifying the interface and removing redundant dependencies (validation/search/similarity/debug_similarity_scores.py). [1] [2]
• Added a new debug script (debug_similarity_search.py) for interactive testing of the similarity search strategy (validation/search/similarity/debug_similarity_search.py).

Test Suite Updates

• Updated test data to include embeddings and adjusted test cases to verify embedding storage and generation logic (tests/utils/test_serialization.py). [1] [2] [3]
• Lowered the minimum similarity score threshold in the similarity test suite to improve test coverage and flexibility (validation/search/similarity/similarity_test_suite.py). [1] [2]

[Copilot]

Pull Request Overview

This pull request refines several memory search and storage functionalities, particularly enhancing Redis index handling, metadata filtering logic, embedding generation workflows, and similarity search debugging.

• Updated test thresholds and expected memory IDs in the similarity test suite.
• Introduced a new debug script and refactored the similarity search strategy instantiation.
• Improved Redis connection handling and embedding generation logic in the serialization workflow, with enhanced handling of nested metadata in the vector store.

Reviewed Changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
validation/search/similarity/similarity_test_suite.py	Adjusted test thresholds and expected memory IDs for improved flexibility.
validation/search/similarity/debug_similarity_search.py	Added a new interactive debug script for similarity search strategy testing.
validation/search/similarity/debug_similarity_scores.py	Refactored SimilaritySearchStrategy instantiation to use the memory_system directly.
tests/utils/test_serialization.py	Updated test data to include embeddings and verified store call counts.
memory/utils/serialization.py	Revised Redis connection setup and embedding generation logic with additional logging.
memory/embeddings/vector_store.py	Enhanced Redis index checks and extended metadata filtering to support nested fields.