Vector Search

Weaviate v1.37.1 introduces an MCP server integrated into the database, enabling efficient codebase ingestion and hybrid search for coding assistants like Claude Code, Cursor, or VS Code. This feature addresses context window limitations and improves code query handling.

Hybrid search combines vector search and BM25 techniques to handle both semantic matching and exact term queries, improving retrieval accuracy; Milvus supports hybrid search setup in three steps without manual sparse vector insertion.

Milvus proposes a method to convert raw conversation history into readable, editable long-term memory using Markdown and semantic search.

MongoDB serves as core infrastructure for enterprise AI Agents by leveraging its document model for unstructured data, native vector search, and hybrid search, particularly excelling in large-scale training data and RAG scenarios.

Qdrant 宣布今日将举行办公室时间活动，主题为“使用 Qdrant 进行威胁情报”，由 Kevin 主持，讨论向量搜索在网络安全运营中的应用，包括威胁建模、攻击面分析和大规模安全数据关联。活动时间为 CEST 时间下午 6 点，地点在 Qdrant Discord，提供链接供参与。