Sign in

v1

latestOpenAPI 3.0.32026-07-2659199427.5 KB
Get predictions

Model predictions by use case

This is an all-purpose prediction endpoint you can use by specifying a USE_CASE and MODEL_ID.

IMPORTANT: The available use cases are detailed in their own section in this specification.

post/ai/prediction/{USE_CASE}/{MODEL_ID}

Path parameters

USE_CASEstring required

The name of the use case for the model. Use the Use Case API to get the list of supported use cases.

MODEL_IDstring required

The unique identifier of the model.

Headers

Authorizationstring required

Bearer token used for authentication. Format: Authorization: Bearer ACCESS_TOKEN.

Content-Typestring

application/json

Request body

chunkerConfigobject

This parameter contains fields that determine how the text is split and the size of text chunks created.

IMPORTANT: Specific information is detailed in each use case.

Example request

{
  "batch": [
    {
      "text": "The content to be split into chunks. "
    }
  ],
  "modelConfig": {
    "vectorQuantizationMethod": "min-max",
    "dimReductionSize": 256
  },
  "useCaseConfig": {
    "dataType": "query"
  }
}

Response

OK

Example response

{
  "predictions": [
    {
      "response": "The response varies based on the use case of the request. For valid information, see the individual use case documentation. "
    }
  ]
}