- ignore line length errors globally - migrate knowledge/memory and crew query_knowledge to `SearchResult` - remove legacy chromadb utils; fix empty metadata handling - restore openai as default embedding provider; support instance-specific clients - update and fix tests for `SearchResult` migration and rag changes
feat: add RAG system foundation with generic vector store support - Add BaseClient protocol for vector stores - Move BaseRAGStorage to rag/core - Centralize embedding types in embeddings/types.py - Remove unused storage models
