Chunking by chunker and modelId

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:

"gte-small"

CHUNKER

enum<string>

required

Chunking strategy for the way text is split.

Available options:

dynamic-newline,

dynamic-sentence,

regex-splitter,

semantic,

sentence

Body

application/json

batch

object[]

The batch of key:value pairs used in the chunking request.

Show child attributes

batch.text

string

The content to be split into chunks based on the chunking strategy (chunker) sent in the request.

The maximum text size allowed for input is approximately 1 MB.

Example:

"The content to be split into chunks. "

modelConfig

ModelConfig · object

Provides fields and values that specify ranges for tokens.

Show child attributes

modelConfig.vectorQuantizationMethod

string

Vector quantization compresses data size, as well as reducing memory usage.

The methods are:

min-max - Creates tensors of the text and converts it to uint8 by normalizing it to the range [0, 255].
max-scale - Finds the maximum absolute value for the encoded text, normalizes it by scaling the text to a range of -127 to 127, and then returns the quantized text as an 8-bit integer tensor.

Example:

"min-max or max-scale"

modelConfig.dimReductionSize

integer

Used to reduce vector size while maintaining good quality.

This field allows any integer above 0, but less than or equal to the vector dimension of the model.

If you send a vector dimension larger than the model, a 400 Bad Request error is returned.

Not every model is designed to support this parameter. In this scenario, a warning message is generated that indicates quality can decrease.

Required range: x >= 1

Example:

256

useCaseConfig

UseCaseConfigChunking · object

Show child attributes

useCaseConfig.dataType

string

This optional parameter enables model-specific handling in the Async Chunking API to help improve model accuracy. Use the most applicable fields based on available dataTypes and the dataType value that best aligns with the text sent to the Async Chunking API.

The string values to use are:

"dataType": "query" for the query.

"dataType": "passage" for fields searched at query time.

Example:

"query"

chunkerConfig

object

This parameter contains fields that determine how the text is split and the size of text chunks created.

IMPORTANT: Specific information is detailed in each use case.

Response

This is the response to the POST chunking request submitted for a specific chunker and modelId.

chunkingId

string<uuid>

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

Example:

"441eb3be-7de6-470a-8141-e416a15c7db1"

status

string

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:

"SUBMITTED"

Models

Authentication

Use Case

Predict

Async Chunking

Async Predict

Prompt Preview

Signals

Tokenization

Headers

Path Parameters

Body

Response