Docker compose

Chunkr

Overview

Chunkr AI

Learn how to get started with Chunkr AI API

Quickstart

Developer Quickstart

Changelog

Configuration

Segment Processing

Optical Character Recognition (OCR)

Intelligent chunking

Choose providers to process your documents

Pipeline

Learn how to efficiently process multiple files with Chunkr AI

Bulk Upload

Optimize Chunkr configuration for your use case

Usage Patterns

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

**This endpoint is deprecated**

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 Multipart

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

**This endpoint is deprecated**

Updates an existing task's configuration and reprocesses the document.

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.

Update Task Multipart

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.

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.

Update Task

Retrieves a list of tasks

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

Get Started

Features

Use Cases

Self Hosting

Docker compose