POST
/
ai
/
async-prediction
/
rag
/
{MODEL_ID}
RAG use case
curl --request POST \
  --url https://application_id.applications.lucidworks.com/ai/async-prediction/rag/{MODEL_ID} \
  --header 'Content-Type: application/json' \
  --data '{
  "batch": [
    {
      "text": "What is RAG?",
      "documents": [
        {
          "body": "Retrieval Augmented Generation, known as RAG, a framework promising to optimize generative AI.",
          "source": "http://rag.com/22",
          "title": "What are the benefits of RAG?",
          "date": "2022-01-31T19:31:34Z"
        }
      ]
    }
  ],
  "useCaseConfig": {
    "memoryUuid": "27a887fe-3d7c-4ef0-9597-e2dfc054c20e",
    "extractRelevantContent": false,
    "answerNotFoundMessage": "Not possible to answer given this content."
  },
  "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

Example:

"application/json"

Path Parameters

MODEL_ID
string
required

Unique identifier for the model.

Example:

"6a092bd4-5098-466c-94aa-40bf6829430\""

Body

application/json

Response

200
application/json

OK

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