Built-in vector search capability in TiDB, a MySQL-compatible database, enabling seamless storage and search for vectors using SQL with HNSW indexes. Eliminates the need for separate vector databases by combining operational and vector data.
TiDB, a MySQL-compatible database, has introduced built-in vector search capabilities, enabling seamless storage and search for vectors directly using SQL. TiDB extends MySQL syntax to support Vector Search and introduces new Vector data types and several vector functions.
TiDB Serverless brings built-in vector search to the MySQL landscape. Developers can leverage the familiar SQL environment to effortlessly join, index, and query both operational and vector data. This capability enables advanced semantic searches, combining the power of vector search with the reliability and ease of MySQL.
The following Vector data types are currently available:
Note: Vector data types are TiDB specific, and are not supported in standard MySQL.
TiDB implements vector indexes using the Hierarchical Navigable Small World (HNSW) method for efficient nearest neighbor searches.
The built-in approach eliminates the need for separate databases for vector and operational data, thus avoiding data redundancy. Store vector embeddings directly alongside your MySQL data, simplifying your data architecture with the straightforwardness of SQL.
Everything runs within TiDB, eliminating the complexity of managing separate vector databases and keeping data synchronized.
Vector data types are available on:
For TiDB Self-Managed and TiDB Cloud Dedicated, the TiDB version must be v8.4.0 or later (v8.5.0 or later is recommended).
Varies by TiDB deployment option (Serverless, Dedicated, Self-Managed). Consult PingCAP pricing for details.
Loading more......