Object Storage Service:Create a vector index (Python SDK V2)

Permissions

An Alibaba Cloud account has all permissions by default. A Resource Access Management (RAM) user or RAM role has no permissions by default. The account owner or an administrator must grant permissions using a RAM policy or a bucket policy.

Prerequisites

Before you begin, ensure that you have:

• A vector bucket

• The oss:PutVectorIndex permission granted to your Alibaba Cloud account, RAM user, or RAM role

Method definition

put_vector_index(request: PutVectorIndexRequest, **kwargs) → PutVectorIndexResult

Sample code

The following example creates a vector index in a bucket. All configuration is passed through CLI arguments, and credentials are loaded from environment variables.

import argparse
import alibabacloud_oss_v2 as oss
import alibabacloud_oss_v2.vectors as oss_vectors

parser = argparse.ArgumentParser(description="vector put vector index sample")
parser.add_argument('--region', help='The region in which the bucket is located.', required=True)
parser.add_argument('--bucket', help='The name of the bucket.', required=True)
parser.add_argument('--endpoint', help='The domain names that other services can use to access OSS')
parser.add_argument('--index_name', help='The name of the vector index.', required=True)
parser.add_argument('--account_id', help='The account id.', required=True)

def main():
    args = parser.parse_args()

    # Load credentials from environment variables
    credentials_provider = oss.credentials.EnvironmentVariableCredentialsProvider()

    # Use the SDK's default configuration
    cfg = oss.config.load_default()
    cfg.credentials_provider = credentials_provider
    cfg.region = args.region
    cfg.account_id = args.account_id
    if args.endpoint is not None:
        cfg.endpoint = args.endpoint

    vector_client = oss_vectors.Client(cfg)

    result = vector_client.put_vector_index(oss_vectors.models.PutVectorIndexRequest(
        bucket=args.bucket,
        index_name=args.index_name,
        dimension=512,          # Set to match your embedding model's output dimension
        data_type='float32',
        distance_metric='euclidean',
        metadata={"nonFilterableMetadataKeys": ["key1", "key2"]}
    ))

    print(f'status code: {result.status_code},'
          f' request ID: {result.request_id},'
    )

if __name__ == "__main__":
    main()

References

For the complete sample code, see put_vector_index.py.