MENU
      Embedding
        • PDF

        Embedding

        • PDF

        Article summary

        Available in Classic and VPC

        Perform vectorization tasks to represent text as numbers.

        Request

        This section describes the request format. The method and URI are as follows:

        MethodURI
        POST/v1/api-tools/embedding/{modelName}

        Request headers

        The following describes the request headers.

        FieldRequiredDescription
        AuthorizationRequiredAPI key for authentication <e.g.,> Bearer nv-************
        X-NCP-CLOVASTUDIO-REQUEST-IDOptionalRequest ID
        Content-TypeRequiredRequest data format
        • application/json

        Request path parameters

        You can use the following path parameters with your request:

        FieldTypeRequiredDescription
        modelNameEnumRequiredModel for performing embedding
        • clir-emb-dolphin | clir-sts-dolphin
          • clir-emb-dolphin: highly generalizable model that can be applied to any domain (default)
          • clir-sts-dolphin: model specialized for precisely measuring the meaning of sentences

        Request body

        The following describes the body.

        FieldTypeRequiredDescription
        textStringRequiredText (tokens) to perform embedding
        • 1-500

        Request example

        The request example is as follows:

        curl --location --request POST 'https://clovastudio.stream.ntruss.com/testapp/v1/api-tools/embedding/{modelName}' \
        --header 'Authorization: Bearer {API Key}' \
        --header 'X-NCP-CLOVASTUDIO-REQUEST-ID: {Request ID}' \
        --header 'Content-Type: application/json' \
        --data '{
                  "text": "How's the weather today?"
        }'
        Shell

        Response

        This section describes the response format.

        Response body

        The response body includes the following data:

        FieldTypeRequiredDescription
        embeddingArray-Embedding performance results
        • Composed of a list of 1024 floats
        inputTokensInteger-Number of tokens in the text performing embedding

        Response example

        The response example is as follows:

        Succeeded

        The following is a sample response upon a successful call.

        {
            "status": {
              "code": "20000",
                "message": "OK"
              },
            "result": {
              "embedding": [ -0.3861295, -0.7903874, ... , 0.2994273, -0.7736456, -0.24933687 ]
              "inputTokens": 4
            }
          }
        JSON

        Failure

        The following is a sample response upon a failed call.


        Was this article helpful?

        What's Next
        Changing your password will log you out immediately. Use the new password to log back in.
        First name must have atleast 2 characters. Numbers and special characters are not allowed.
        Last name must have atleast 1 characters. Numbers and special characters are not allowed.
        Enter a valid email
        Enter a valid password
        Your profile has been successfully updated.