Retrieves a list of tasks

Example usage:
`GET /api/v1/tasks?page=1&limit=10&include_chunks=false`

Get Tasks

Controls the processing and generation for the segment.
- `crop_image` controls whether to crop the file's images to the segment's bounding box.
  The cropped image will be stored in the segment's `image` field. Use `All` to always crop,
  or `Auto` to only crop when needed for post-processing.
- `html` is the HTML output for the segment, generated either through heuristic (`Auto`) or using Chunkr fine-tuned models (`LLM`)
- `llm` is the LLM-generated output for the segment, this uses off-the-shelf models to generate a custom output for the segment
- `markdown` is the Markdown output for the segment, generated either through heuristic (`Auto`) or using Chunkr fine-tuned models (`LLM`)
- `embed_sources` defines which content sources will be included in the chunk's embed field and counted towards the chunk length.
  The array's order determines the sequence in which content appears in the embed field (e.g., [Markdown, LLM] means Markdown content
  is followed by LLM content). This directly affects what content is available for embedding and retrieval.

Use the full page image as context for LLM generation

Bounding box for an item. It is used for chunks, segments and OCR results.

The total number of tokens in the chunk. Calculated by the `tokenizer`.

Suggested text to be embedded for the chunk. This text is generated by combining the embed content
from each segment according to the configured embed sources (HTML, Markdown, LLM, or Content).
Can be configured using `embed_sources` in the `SegmentProcessing` configuration.

Collection of document segments that form this chunk.
When `target_chunk_length` > 0, contains the maximum number of segments
that fit within that length (segments remain intact).
Otherwise, contains exactly one segment.

Controls the setting for the chunking and post-processing of each chunk.

Whether to ignore headers and footers in the chunking process.
This is recommended as headers and footers break reading order across pages.

The target number of words in each chunk. If 0, each chunk will contain a single segment.

The tokenizer to use for the chunking process.

The number of seconds until task is deleted.
Expired tasks can **not** be updated, polled or accessed via web interface.

Whether to use high-resolution images for cropping and post-processing.

Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
- `All` crops all images in the item
- `Auto` crops images only if required for post-processing

Controls how errors are handled during processing:
- `Fail`: Stops processing and fails the task when any error occurs
- `Continue`: Attempts to continue processing despite non-critical errors (eg. LLM refusals etc.)

Specifies the fallback strategy for LLM processing

This can be:
1. None - No fallback will be used
2. Default - The system default fallback model will be used
3. Model - A specific model ID will be used as fallback (check the documentation for the models.)

Controls the processing and generation for the segment.
- `crop_image` controls whether to crop the file's images to the segment's bounding box.
  The cropped image will be stored in the segment's `image` field. Use `All` to always crop,
  or `Auto` to only crop when needed for post-processing.
- `html` is the HTML output for the segment, generated either through huerstics (`Auto`) or using Chunkr fine-tuned models (`LLM`)
- `llm` is the LLM-generated output for the segment, this uses off-the-shelf models to generate a custom output for the segment
- `markdown` is the Markdown output for the segment, generated either through huerstics (`Auto`) or using Chunkr fine-tuned models (`LLM`)
- `embed_sources` defines which content sources will be included in the chunk's embed field and counted towards the chunk length.
  The array's order determines the sequence in which content appears in the embed field (e.g., [Markdown, LLM] means Markdown content
  is followed by LLM content). This directly affects what content is available for embedding and retrieval.

The fallback strategy to use for the LLMs in the task.

The maximum number of tokens to generate.

The ID of the model to use for the task. If not provided, the default model will be used.
Please check the documentation for the model you want to use.

The confidence score of the recognized text.

Controls the Optical Character Recognition (OCR) strategy.
- `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page)
- `Auto`: Selectively applies OCR only to pages with missing or low-quality text. When text layer is present the bounding boxes from the text layer are used.

The processed results of a document analysis task

Collection of document chunks, where each chunk contains one or more segments

Confidence score of the layout analysis model

Text content of the segment. Calculated by the OCR results.

Presigned URL to the image of the segment.

Height of the page containing the segment.

Width of the page containing the segment.

Controls the post-processing of each segment type.
Allows you to generate HTML and Markdown from chunkr models for each segment type.
By default, the HTML and Markdown are generated manually using the segmentation information except for `Table`, `Formula` and `Picture`.
You can optionally configure custom LLM prompts and models to generate an additional `llm` field with LLM-processed content for each segment type.

The configuration of which content sources (HTML, Markdown, LLM, Content) of the segment
should be included in the chunk's `embed` field and counted towards the chunk length can be configured through the `embed_sources` setting.

All the possible types for a segment.
Note: Different configurations will produce different types.
Please refer to the documentation for more information.

Controls the segmentation strategy:
- `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`, `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained segmentation and better chunking. (Latency penalty: ~TBD seconds per page).
- `Page`: Treats each page as a single segment. Faster processing, but without layout element detection and only simple chunking.

The date and time when the task was created and queued.

The date and time when the task will expire.

The date and time when the task was finished.

A message describing the task's status or any errors that occurred.

The date and time when the task was started.

Common tokenizers used for text processing.

These values represent standard tokenization approaches and popular pre-trained
tokenizers from the Hugging Face ecosystem.

Specifies which tokenizer to use for the chunking process.

This type supports two ways of specifying a tokenizer:
1. Using a predefined tokenizer from the `Tokenizer` enum
2. Using any Hugging Face tokenizer by providing its model ID as a string
   (e.g. "facebook/bart-large", "Qwen/Qwen-tokenizer", etc.)

When using a string, any valid Hugging Face tokenizer ID can be specified,
which will be loaded using the Hugging Face tokenizers library.

Use one of the predefined tokenizer types

Use any Hugging Face tokenizer by specifying its model ID
Examples: "Qwen/Qwen-tokenizer", "facebook/bart-large"

api key

Internal server error related to getting the task

Chunkr

Overview

Chunkr AI

Learn how to get started with Chunkr AI API

Quickstart

Developer Quickstart

LLM Docs

LLM Documentation

Changelog

Configuration

Chunking

Optical Character Recognition (OCR)

LLM Processing

Segment Processing

Choose providers to process your documents

Pipeline

Error Handling

Optimize Chunkr configuration for your use case

Usage Patterns

Learn how to efficiently process multiple files with Chunkr AI

Bulk Upload

Docker compose

Kubernetes

Installation

Usage

Using Chunkr AI SDK

Learn how to upload files and create processing tasks with Chunkr AI

Creating Tasks

Learn how to retrieve and read task information from Chunkr AI

Getting Tasks

Learn how to update existing tasks in Chunkr AI

Updating Tasks

Deleting Tasks

Learn how to cancel queued tasks in Chunkr AI

Canceling Tasks

Learn how to configure tasks in Chunkr AI

Polling

Polling the TaskResponse

Export

Export to different formats

Queues a document for processing and returns a TaskResponse containing:
- Task ID for status polling
- Initial configuration
- File metadata
- Processing status
- Creation timestamp
- Presigned URLs for file access

The returned task will typically be in a `Starting` or `Processing` state.
Use the `GET /task/{task_id}` endpoint to poll for completion.

Create Task

Retrieves detailed information about a task by its ID, including:
- Processing status
- Task configuration
- Output data (if processing is complete)
- File metadata (name, page count)
- Timestamps (created, started, finished)
- Presigned URLs for accessing files

This endpoint can be used to:
1. Poll the task status during processing
2. Retrieve the final output once processing is complete
3. Access task metadata and configuration

Get Task

Delete a task by its ID.

Requirements:
- Task must have status `Succeeded` or `Failed`

Delete Task

Cancel a task that hasn't started processing yet:
- For new tasks: Status will be updated to `Cancelled`
- For updating tasks: Task will revert to the previous state

Requirements:
- Task must have status `Starting`

Cancel Task

Updates an existing task's configuration and reprocesses the document.
The original configuration will be used for all values that are not provided in the update.

Requirements:
- Task must have status `Succeeded` or `Failed`
- New configuration must be different from the current one

The returned task will typically be in a `Starting` or `Processing` state.
Use the `GET /task/{task_id}` endpoint to poll for completion.

Task

Tasks

Health

Get Tasks

Authorizations

Query Parameters

Response