OpenAI compatible text embedding - OpenSearch - Alibaba Cloud Documentation Center

This document describes the API parameter configuration for the OpenAI compatible text embedding service.

URL

{host}/compatible-mode/v1/embeddings

host: The endpoint for calling the service. You can call the API service through the Internet or VPC. For more information, see Query service endpoint.

AI apikey截图.png

Request parameters

Parameter

Type

Required

Description

Example value

model

String

Yes

The specified service ID.

System service ID starts with 'ops-'.

For a list of supported service IDs, see List of supported services.

ops-text-embedding-001

input

Array/String

Yes

Supports multiple text inputs, with a maximum of 32 per request; the length of each input depends on the selected model. Empty strings are not accepted.

["Science and technology are the primary productive forces", "OpenSearch product documentation"]

Response parameters

Parameter	Type	Description	Example value
data	List	Provides the data information.	-
data.embedding	Array[float]	The embedding processing result, returning an array of vectors.	[ 0.003143, 0.009750, ... (1536 floats in total for ops-text-embedding-001), -0.017395 ]
data.index	Int	The ordinal number corresponding to the index in the request input, starting from 0.	0
data.object	String	The static value 'embedding'.	embedding
object	String	The response type, static value 'list'.	list
model	String	The service ID specified in the request.	ops-text-embedding-001
usage	Object	Statistics on token usage for this model invocation.	-
usage.prompt_tokens	Int	The number of tokens generated from the user's request input.	5
usage.total_tokens	Int	The total number of tokens used, which is the sum of usage.prompt_tokens and usage.completion_tokens.	5

CURL example

curl http://xxxx-shanghai.opensearch.aliyuncs.com/compatible-mode/v1/chat/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer Your-API-Key" \
  -d '{
    "model": "ops-text-embedding-001",
    "input": "Search development platform"
  }'

Response example

{
  "id":"9085118afe14bee71d59c4a609fcf7c0",
  "object":"list",
  "data":
    [
        {
          "object":"embedding",
          "embedding":
              [
                  0.0021381378173828125,
                  0.12109375,
                  .......,
                  -0.0389404296875
               ],
             "index":0
            }
       ],
     "model":"ops-text-embedding-001",
     "usage":
         {
            "prompt_tokens":5,
            "total_tokens":5
          }
   }

Status codes

For more information, see Status code description in AI Search Open Platform.