POST
/
ai
/
async-prediction
/
{USE_CASE}
/
{MODEL_ID}
Model predictions by use case
curl --request POST \
  --url https://application_id.applications.lucidworks.com/ai/async-prediction/{USE_CASE}/{MODEL_ID} \
  --header 'Content-Type: application/json' \
  --data '{
  "batch": [
    {
      "text": "The content the model analyzes."
    }
  ],
  "modelConfig": {
    "temperature": 0.8,
    "topP": 1,
    "topK": -1,
    "presencePenalty": 2,
    "frequencyPenalty": 1,
    "maxTokens": 1,
    "apiKey": "API key specific to use case and model",
    "azureDeployment": "DEPLOYMENT_NAME",
    "azureEndpoint": "https://azure.endpoint.com",
    "googleProjectId": "[GOOGLE_PROJECT_ID]",
    "googleRegion": "[GOOGLE_PROJECT_REGION_OF_MODEL_ACCESS]"
  }
}'
{
  "predictionId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "status": "SUBMITTED"
}

Headers

​
Authorization: Bearer ACCESS_TOKEN
string

The authentication and authorization access token.

​
Content-Type
string

application/json

Path Parameters

​
USE_CASE
string
required

The name of the use case for the model.

​
MODEL_ID
string
required

The unique identifier for the model.

Body

application/json

Request information varies based on the use case in the request. See the specific use case for valid information for that use case.

​
batch
object[]

The batch of key:value pairs used as inputs in the prediction. Up to 32 inputs per request are allowed.

Maximum length: 32
​
modelConfig
object

Provides fields and values that specify ranges for tokens. Fields used for specific use cases and models are specified. The default values are used if other values are not specified.

Response

OK

This is the response to the POST prediction request submitted for a specific useCase and modelId.

​
predictionId
string<uuid>

The universal unique identifier (UUID) returned in the POST request. This UUID is required in the GET request to retrieve results.

​
status
string

The current status of the prediction. Allowed values are:

  • SUBMITTED - The POST request was successful and the response has returned the predictionId and status that is used by the GET request.

  • ERROR - An error was generated when the GET request was sent.

  • READY - The results associated with the predictionId are available and ready to be retrieved.

  • RETRIEVED - The results associated with the predicitonId are returned successfully when the GET request was sent.

Example:

"SUBMITTED"