Vector dimensionality reduction service - OpenSearch - Alibaba Cloud Documentation Center

Service name	Service ID	Service description	QPS limit for API calls (Alibaba Cloud account and RAM users)
OpenSearch Vector Dimensionality Reduction Service-001	ops-embedding-dim-reduction-001	Provides vector dimensionality reduction service, supporting vector dimensionality reduction up to 4k. You can fine-tune the model based on your business needs.	50 Note To apply for higher QPS, submit a ticket.

Prerequisites

The authentication information is obtained.
When you call an AI Search Open Platform service by using an API, you need to authenticate the caller's identity.
The service access address is obtained.
You can call a service over the Internet or a virtual private cloud (VPC). For more information, see Get service registration address.

Request description

General description

The request body must not exceed 8MB.

HTTP request method

POST

URL

{host}/v3/openapi/workspaces/{workspace_name}/embedding-tuning/{service_id}

host: The address for calling the service, supports calling API services through both public network and VPC. For more information, see Query service endpoint.
workspace_name: The name of the workspace, such as 'default'.

service_id: The system built-in service ID, such as ops-embedding-dim-reduction-001.

Request parameters

Header parameters

API-KEY Authentication

Parameter	Type	Required	Description	Example value
Content-Type	String	Yes	Request type: application/json	application/json
Authorization	String	Yes	API-Key	Bearer OS-d1**2a

Body parameters

Parameter	Type	Required	Description	Example value
input	List<List<Float>>	Yes	Input vector collection.	[0.111,0.222,0.333]
parameters	Map	No	Adjustable request parameters. These parameters may vary based on different service IDs.
parameters.output_dimension	Integer	No	Output dimension. Default value: 512.	512
parameters.model_name	String	No	Name of the user-trained model. If it is a vector compression service, this is required.	xxxx-model

Response parameters

Parameter	Type	Description	Example value
result.output	List<List<Float>>	Fine-tuned vector results.
usage.doc_count	Int	The number of vector entries input in this request.	2

Curl request example

curl --location 'http://****-hangzhou.opensearch.aliyuncs.com/v3/openapi/workspaces/default/embedding-tuning/ops-embedding-dim-reduction-001/' \
--header 'Authorization: Bearer Your-API-KEY' \
--header 'Content-Type: application/json' \
--data '{  
  "input": [
    [0.111,0.222,0.333],
    [0.121,0.221,0.331]
  ],
  "parameters":{
    "output_dimension": "512",
    "model_name" : "xxxx"
  }
}'

Sample response

Normal sample response

{
  "request_id": "450fcb80-f796-46c1-8d69-e1e86d29aa9f",
  "latency": 564.903929,
  "usage": {
    "doc_count": 2
  }
  "result": {
    "output":[
      [0.111,0.222,0.333],
      [0.121,0.221,0.331]
    ]
  }
}

Sample error response

In the event of an access request error, the output will specify the error reason through the code and message.

{
    "request_id": "590A7EB8-AA84-****-AF31-8C35DC965972",
    "latency": 0.0,
    "code": "InvalidParameter",
    "http_code": 400,
    "message": "document.file_name required"
}

Status codes

HTTP status code	Error code	Description
200	-	Request succeeded. Including task failed scenarios. The actual task status needs to be determined from result.status
404	BadRequest.TaskNotExist	The error message returned because the specified task does not exist.
400	InvalidParameter	Invalid request
500	InternalServerError	Internal error

For more information, see Status codes.