TextEmbedding - AnalyticDB - Alibaba Cloud Documentation Center

Generates text embeddings using an embedding model.

Debugging

You can run this interface directly in OpenAPI Explorer, saving you the trouble of calculating signatures. After running successfully, OpenAPI Explorer can automatically generate SDK code samples.

Debug

Authorization information

The following table shows the authorization information corresponding to the API. The authorization information can be used in the Action policy element to grant a RAM user or RAM role the permissions to call this API operation. Description:

Operation: the value that you can use in the Action element to specify the operation on a resource.
Access level: the access level of each operation. The levels are read, write, and list.
Resource type: the type of the resource on which you can authorize the RAM user or the RAM role to perform the operation. Take note of the following items:
- For mandatory resource types, indicate with a prefix of * .
- If the permissions cannot be granted at the resource level, All Resources is used in the Resource type column of the operation.
Condition Key: the condition key that is defined by the cloud service.
Associated operation: other operations that the RAM user or the RAM role must have permissions to perform to complete the operation. To complete the operation, the RAM user or the RAM role must have the permissions to perform the associated operations.

Operation	Access level	Resource type	Condition key	Associated operation
gpdb:TextEmbedding	none	*DBInstance `acs:gpdb:{#regionId}:{#accountId}:dbinstance/{#DBInstanceId}`	none	none

Request parameters

Parameter	Type	Required	Description	Example
DBInstanceId	string	Yes	The cluster ID.	gp-xxxxxxxxx
RegionId	string	Yes	The region ID of the cluster.	cn-hangzhou
Model	string	No	The text embedding model. Valid values: text-embedding-v1:1536 dimensions text-embedding-v2:1536 dimensions text-embedding-v3 (default):1024, 768, and 512 dimensions text2vec: 1024 dimensions m3e-base: 768 dimensions m3e-small: 512 dimensions	text-embedding-v2
Input	array	Yes	A list of text content to be embedded. The list length must not exceed 100.
	string	Yes	The content of the text to be embedded. The text length cannot exceed 2,048 tokens.
Dimension	integer	No	The number of embedding dimensions. The default value is the number of dimensions supported by the embedding algorithm. Note The text-embedding-v3 supports 1024, 768, and 512 dimensions. Default value: 1024.	1024

Response parameters

Parameter	Type	Description	Example
	object
RequestId	string	The unique ID of the request.	ABB39CC3-4488-4857-905D-2E4A051D0521
Message	string	The returned message.	Successful
Status	string	The status of the operation. Valid values: success fail	success
TextTokens	integer	The total number of tokens consumed.	1000
Results	array<object>	The embedding results.
Results	object	The embedding result.
Embedding	array	The embedding values.
Embedding	double	The embedding value.	0.1234
Index	integer	The number of the embedding in the Input request parameter, which starts from 0.	0

Examples

Sample success responses

JSONformat

{
  "RequestId": "ABB39CC3-4488-4857-905D-2E4A051D0521",
  "Message": "Successful",
  "Status": "success",
  "TextTokens": 1000,
  "Results": {
    "Results": [
      {
        "Embedding": {
          "Embedding": [
            0.1234
          ]
        },
        "Index": 0
      }
    ]
  }
}

Error codes

For a list of error codes, visit the Service error codes.