2 Commits

Author	SHA1	Message	Date
Mai Development	b9aba97086	feat(04-02): create semantic search with embedding-based retrieval ... - Added sentence-transformers to requirements.txt for semantic embeddings - Created src/memory/retrieval/ module with search capabilities - Implemented SemanticSearch class with embedding generation and vector similarity - Added SearchResult and SearchQuery dataclasses for structured search results - Included hybrid search combining semantic and keyword matching - Added conversation indexing for semantic search - Followed lazy loading pattern for embedding model performance Files created: - src/memory/retrieval/__init__.py - src/memory/retrieval/search_types.py - src/memory/retrieval/semantic_search.py - Updated src/memory/__init__.py with enhanced MemoryManager Note: sentence-transformers installation requires proper venv setup in production	2026-01-27 23:22:50 -05:00
Mai Development	bdba17773c	feat(04-01): create memory module structure and SQLite manager ... - Created src/memory module with MemoryManager stub - Created src/memory/storage subpackage - Implemented SQLiteManager with connection management and thread safety - Database schema supports conversations, messages, and metadata - Includes proper indexing and error handling Schema: - conversations table: id, title, timestamps, metadata, session stats - messages table: id, conversation_id, role, content, importance, embedding_ref - Foreign key constraints and performance indexes - Thread-local connections with WAL mode for concurrency	2026-01-27 22:50:02 -05:00