import requests

url = "https://application_id.applications.lucidworks.com/ai/prediction/rag/{MODEL_ID}"

payload = {
    "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]"
    }
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.json())

{
  "predictions": [
    {
      "response": "ANSWER: \\\"Retrieval Augmented Generation, known as RAG, a framework promising to optimize generative AI.\"\\nSOURCES: [\\\"http://example.com/112\\\"]",
      "tokensUsed": {
        "promptTokens": 148,
        "completionTokens": 27,
        "totalTokens": 175
      },
      "answer": "Retrieval Augmented Generation, known as RAG, a framework promising to optimize generative AI.",
      "sources": "http://example.com/112",
      "memoryUuid": "27a887fe-3d7c-4ef0-9597-e2dfc054c20e",
      "answerNotFoundMessage": "Not possible to answer given this content.",
      "answerFound": true
    }
  ]
}