README.md

Chunkr

Chunkr is a self-hostable API for converting pdf, pptx, docx, and excel files into RAG/LLM ready data
11 semantic tags for layout analysis | OCR + Bounding Boxes | Structured HTML and markdown

Try it out! · Report Bug · Contact

Watch our 1-minute demo video

Table of Contents

• Table of Contents
• Docs
• (Super) Quick Start
  • Production Deployment with Kubernetes
• Licensing
• Connect With Us

Docs

https://docs.chunkr.ai

(Super) Quick Start

1. Go to chunkr.ai
2. Make an account and copy your API key
3. Create a task:

   curl -X POST https://api.chunkr.ai/api/v1/task \
      -H "Content-Type: multipart/form-data" \
      -H "Authorization: ${YOUR_API_KEY}" \
      -F "file=@/path/to/your/file" \
      -F "model=HighQuality" \
      -F "target_chunk_length=512" \
      -F "ocr_strategy=Auto"

4. Poll your created task:

   curl -X GET https://api.chunkr.ai/api/v1/task/${TASK_ID} \
     -H "Authorization: ${YOUR_API_KEY}"

Self-Hosted Deployment Options

Quick Start with Docker Compose

1. Prerequisites:

   • Docker and Docker Compose
   • NVIDIA Container Toolkit (for GPU support)

2. Clone the repo:

   git clone https://github.com/lumina-ai-inc/chunkr
   cd chunkr

3. Copy the example env file

   cp .env.example .env

4. Start the services

   docker compose up -d

5. Access the services:

   • Web UI: http://localhost:5173
   • API: http://localhost:8000

Note: Requires an NVIDIA CUDA GPU to run.

6. Stop the services

   docker compose down

Production Deployment with Kubernetes

For production environments, we provide a Helm chart and detailed deployment instructions:

1. See our detailed guide at kube/README.md
2. Includes configurations for high availability and scaling

For enterprise support and deployment assistance, contact us.

Licensing

This project is dual-licensed:

1. GNU Affero General Public License v3.0 (AGPL-3.0)
2. Commercial License

To use Chunkr without complying with the AGPL-3.0 license terms you can contact us or visit our website.

Connect With Us

• 📧 Email: [email protected]
• 📅 Schedule a call: Book a 30-minute meeting
• 🌐 Visit our website: chunkr.ai