Sign in

v1

latestOpenAPI 3.0.32026-07-2659199427.5 KB
Split content into chunks

Chunk using semantic chunker

The semantic chunker (chunking strategy) creates chunks based on semantic similarity.

Using the model defined in the URL request, the semantic chunker splits text into sentences, encodes the sentences, and then compares the sentence to the building chunk to determine if they are similar enough to group together.

After merging two semantically-similar sentences into a pre-chunk, the semantic chunker needs to encode it to get its vector to compare with the next sentence vector.

This chunker is the slowest of all of the chunkers even if you set the approximate field to true.

post/ai/async-chunking/semantic/{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": "The content to be split into chunks. "
    }
  ],
  "modelConfig": {
    "vectorQuantizationMethod": "min-max",
    "dimReductionSize": 256
  },
  "useCaseConfig": {
    "dataType": "query"
  },
  "chunkerConfig": {
    "cosineThreshold": 0.567
  }
}

Response

OK

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"
}