create_vector_index

Builds a vector index on a specified field within a table, enabling efficient vector-based searches. Supports HNSW, HNSWPQ, and HNSWSQ index types with L2, COSINE, or IP distance metrics for optimized query performance.

Instructions

Create a vector index on a vector type field in the Mochow instance.

Args:
    table_name (str): Name of the table.
    index_name (str): Name of the index.
    field_name (str): Name of the vector field.
    index_type (str): Type of vector index. Supported values are "HNSW", "HNSWPQ", "HNSWSQ".
    metric_type (str): Distance metric. Supported values are "L2", "COSINE", "IP".
    params (Optional[dict[str, Any]]): Additional vector index parameters.

Returns:
    str: A message indicating the success of index creation.

Input Schema

Name	Required	Default
`field_name`	Yes
`index_name`	Yes
`index_type`	No	HNSW
`metric_type`	No	L2
`params`	No
`table_name`	Yes

Input Schema (JSON Schema)

{
  "properties": {
    "field_name": {
      "title": "Field Name",
      "type": "string"
    },
    "index_name": {
      "title": "Index Name",
      "type": "string"
    },
    "index_type": {
      "default": "HNSW",
      "title": "Index Type",
      "type": "string"
    },
    "metric_type": {
      "default": "L2",
      "title": "Metric Type",
      "type": "string"
    },
    "params": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Params"
    },
    "table_name": {
      "title": "Table Name",
      "type": "string"
    }
  },
  "required": [
    "table_name",
    "index_name",
    "field_name"
  ],
  "title": "create_vector_indexArguments",
  "type": "object"
}

Baidu Vector Database MCP Server

create_vector_index

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from Baidu Vector Database MCP Server

Related Tools

MCP directory API