Docs

Torch Object Storage

Vector

GetVectors

Description

Batch query vectors by vector key from the vector index.

Request syntax

The endpoint must use the Bucket Endpoint.

POST /GetVectors HTTP/1.1​
Host: {VectorBucketName}-{AccountID}.tosvectors-cn-beijing.volces.com​
Authorization: authorization string​
Date: Mon, 10 Dec 2025 12:49:14 GMT​
​
​
{​
    "vectorBucketName": "test-vector-bucket",​
    "indexName":"test-index",​
    "keys": ["key0", "key1"],​
    "returnData": true,​
    "returnMetadata": true​
}​

Request parameters and headers

None.

Request body elements

Field name	Type	Required	Example value	Description
vectorBucketName	String	Yes	test-vector-bucket	Name of the vector bucket.
indexName	String	Yes	test-index	Name of the vector index.
keys	string[]	Yes	["key0", "key1"]	The list of vector names whose attributes you want to return. Array items: minimum 1 item, maximum 100 items. String length: minimum 1 character, maximum 1024 characters.
returnData	boolean	No	true	Indicates whether vector data is included in the response. Default: false.
returnMetadata	boolean	No	true	Indicates whether to include metadata in the response. Default: false.

Response headers

For common response headers, see Common parameters.

Response body elements

If the operation succeeds, the service returns an HTTP 200 response code along with the following response body elements.

If the operation fails, it returns the error code defined in the Response code.

Field name	Type	Example value	Description
vectors	GetOutputVector[]	See the table below	array of vector attributes.

Explanation of GetOutputVector struct parameters:

Field name	Type	Example value	Description
data	VectorData	"float32": [0.1, 0.1, 0.1, 0.1, 0.1]	Vector data. Ensure the query vector dimension matches the vector index dimension being queried.
key	String	key0	The unique identifier of the vector.
metadata	JSON value	{ "key_a": "va", "key_b": "vb", "key_c": "vc" }	Metadata associated with the vector.

The VectorData struct is a Union type with only one valid member (float32) currently, see the table below.

Field name	Type	Description
float32	float32[]	Vector data. The vector dimension must match the vector index dimension defined in CreateIndex.

Sample request

POST /GetVectors HTTP/1.1​
Host: test-vector-bucket-1111.tosvectors-cn-beijing.volces.com​
Authorization: authorization string​
Date: Mon, 10 Dec 2025 12:49:14 GMT​
​
{​
    "vectorBucketName": "test-vector-bucket",​
    "indexName":"test-index",​
    "keys": ["key0", "key1"],​
    "returnData": true,​
    "returnMetadata": true​
}​

Sample response

HTTP/1.1 200 OK​
x-tos-id-2: 797014003c90a9b694003c9-b15a995-1vV80n-CVB-cb-tos-1az-front-azd-vectors-2 ​
x-tos-request-id: 797014003c90a9b694003c9-b15a995-1vV80n-CVB-cb-tos-1az-front-azd-vectors-2          ​
Date: Mon, 10 Dec 2025 12:49:14 GMT​
server: TosServer​
Content-Length: 243​
Content-Type: application/json​
​
{​
    "vectors": [​
        {​
            "data": {​
                "float32": [​
                    0.1,​
                    0.1,​
                    0.1,​
                    0.1,​
                    0.1​
                ]​
            },​
            "key": "key0",​
            "metadata": {​
                "key_a": "va",​
                "key_b": "vb",​
                "key_c": "vc"​
            }​
        },​
        {​
            "data": {​
                "float32": [​
                    0.2,​
                    0.2,​
                    0.2,​
                    0.2,​
                    0.2​
                ]​
            },​
            "key": "key1",​
            "metadata": {​
                "key_a": "va",​
                "key_b": "vb",​
                "key_c": "vc1",​
                "key_d": "vd"​
            }​
        }​
    ]​
}​

Last updated: 2026.01.04 14:21:23