v1

latestOpenAPI 3.0.32026-07-2659199427.5 KB

Create predictions

RAG use case

The rag use case uses candidate documents that are inserted into a LLM’s context to ground the generated response to those documents instead of generating an answer from details stored in the LLM’s trained weights. This type of search adds guardrails so the LLM can search private data collections.

The RAG search can perform queries against external documents passed in as part of the request.

The POST request obtains and indexes prediction information related to the specified use case, and returns a unique predictionId and status of the request. The predictionId can be used later in the GET request to retrieve the results.

post/ai/async-prediction/rag/{MODEL_ID}

Headers

Authorizationstring required

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

Content-Typestring

Example:application/json

application/json

Request body

Example request

{
  "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"
  },
  "modelConfig": {
    "vectorQuantizationMethod": "min-max",
    "dimReductionSize": 256
  }
}

Response

chunkingIdstring uuid

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

statusstring

The current status of the request. Allowed values are:

SUBMITTED - The POST request was successful and the response has returned the chunkingId 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 chunkingId are available and ready to be retrieved.
RETRIEVED - The results associated with the chunkingId are returned successfully when the GET request was sent.

Example response

{
  "chunkingId": "441eb3be-7de6-470a-8141-e416a15c7db1",
  "status": "SUBMITTED"
}