{"id":17493,"date":"2024-06-04T20:23:08","date_gmt":"2024-06-05T03:23:08","guid":{"rendered":"https:\/\/www.pingcap.com\/?post_type=article&p=17493"},"modified":"2024-06-04T20:28:37","modified_gmt":"2024-06-05T03:28:37","slug":"managing-vectors-in-the-same-way-as-operating-on-mysql-data","status":"publish","type":"article","link":"https:\/\/www.pingcap.com\/ko\/article\/managing-vectors-in-the-same-way-as-operating-on-mysql-data\/","title":{"rendered":"Managing Vectors in the Same Way as Operating on MySQL Data"},"content":{"rendered":"\n

As the landscape of data management continues to evolve, the integration of vector search capabilities into traditional relational databases has emerged as a powerful advancement. TiDB Serverless<\/a>, now offers a vector search feature<\/a>, allowing users to manage vectors in a manner akin to operating on MySQL data. This seamless integration of vector search within a relational database framework not only simplifies complex data operations but also extends the versatility of database applications.<\/p>\n\n\n\n

<\/span>Understanding Vector Search<\/span><\/h2>\n\n\n\n

Vector search enables semantic and similarity searches across various data types, such as text, images, videos, and audio. Instead of searching the data itself, vector search focuses on the meanings of the data. This is achieved by representing data as points in a multidimensional space, where the spatial relationships between points indicate semantic similarities.<\/p>\n\n\n\n

In TiDB, vector embeddings are used to represent data. These embeddings can be stored alongside traditional data within the same database. This unique feature allows users to perform sophisticated searches and analyses while leveraging the robustness and scalability of a relational database.<\/p>\n\n\n\n

<\/span>Implementing Vector Search in TiDB<\/span><\/h2>\n\n\n\n

Setting Up TiDB for Vector Search<\/h3>\n\n\n\n

To get started with TiDB’s vector search feature, follow these steps:<\/p>\n\n\n\n

    \n
  1. Sign Up for TiDB Cloud<\/strong>: Create an account on TiDB Cloud<\/a> and sign up for the service.<\/li>\n\n\n\n
  2. Select the Appropriate Region<\/strong>: As of now, vector search is available only in the eu-central-1<\/code> region. Select this region when setting up your TiDB serverless cluster.<\/li>\n\n\n\n
  3. Create a TiDB Serverless Cluster<\/strong>: Follow the tutorial on TiDB Cloud<\/a> to create a cluster with vector search support enabled.<\/li>\n<\/ol>\n\n\n\n

    Basic Usage: Insert and Query Vectors<\/h3>\n\n\n\n

    Once your cluster is set up, you can start by creating tables and inserting data that includes vector embeddings. Here is an example of how to create a table with a 3-dimensional vector field and insert records:<\/p>\n\n\n\n

    CREATE TABLE vector_table (\n    id INT PRIMARY KEY, \n    doc TEXT, \n    embedding VECTOR(3)\n);\n\nINSERT INTO vector_table VALUES \n    (1, 'apple', '[1,1,1]'),\n    (2, 'banana', '[1,1,2]'),\n    (3, 'dog', '[2,2,2]');<\/code><\/pre>\n\n\n\n
    You can query the table to retrieve all records:<\/p>\n\n\n\n
    SELECT * FROM vector_table;<\/code><\/pre>\n\n\n\n
    To find the nearest neighbors to a given vector based on cosine distance, you can execute the following query:<\/p>\n\n\n\n
    SELECT * FROM vector_table \nORDER BY vec_cosine_distance(embedding, '[1,1,3]') \nLIMIT 3;<\/code><\/pre>\n\n\n\n
    This query orders the results by their cosine similarity to the vector [1,1,3]<\/code>, returning the closest matches.<\/p>\n\n\n\n
    Advanced Vector Operations<\/h3>\n\n\n\n
    TiDB also supports various vector distance functions, such as:<\/p>\n\n\n\n