Chunkr | Open Source Document Intelligence API

Production-ready API service for document layout analysis, OCR, and semantic chunking.
Convert PDFs, PPTs, Word docs & images into RAG/LLM-ready chunks.

Layout Analysis | OCR + Bounding Boxes | Structured HTML and markdown | VLM Processing controls

Try it out! · Report Bug · Contact · Discord

• Table of Contents
• (Super) Quick Start
• Documentation
• Self-Hosted Deployment Options
  • Quick Start with Docker Compose
  • Deployment with Kubernetes
• LLM Configuration
  • OpenAI Configuration
  • Google AI Studio Configuration
  • OpenRouter Configuration
  • Self-Hosted Configuration
• Licensing
• Connect With Us

1. Go to chunkr.ai
2. Make an account and copy your API key
3. Install our Python SDK:

pip install chunkr-ai

4. Use the SDK to process your documents:

from chunkr_ai import Chunkr

# Initialize with your API key from chunkr.ai
chunkr = Chunkr(api_key="your_api_key")

# Upload a document (URL or local file path)
url = "https://chunkr-web.s3.us-east-1.amazonaws.com/landing_page/input/science.pdf"
task = chunkr.upload(url)

# Export results in various formats
html = task.html(output_file="output.html")
markdown = task.markdown(output_file="output.md")
content = task.content(output_file="output.txt")
task.json(output_file="output.json")

# Clean up
chunkr.close()

Visit our docs for more information and examples.

1. Prerequisites:

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

2. Clone the repo:

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

3. Set up environment variables:

# Copy the example environment file
cp .env.example .env

# Configure your environment variables
# Required: LLM__KEY as your OpenAI API key

For more information on how to set up LLMs, see here.

4. Start the services:

With GPU:

docker compose up -d

Access the services:

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

Important:

• Requires an NVIDIA CUDA GPU
• CPU-only deployment via compose-cpu.yaml is currently in development and not recommended for use
• To use a CPU version run docker compose -f compose-cpu.yaml up -d

1. Stop the services when done:

docker compose down

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.

You can use any OpenAI API compatible endpoint by setting the following variables in your .env file:

LLM__KEY:
LLM__MODEL:
LLM__URL:

LLM__KEY=your_openai_api_key
LLM__MODEL=gpt-4o
LLM__URL=https://api.openai.com/v1/chat/completions

For getting a Google AI Studio API key, see here.

LLM__KEY=your_google_ai_studio_api_key
LLM__MODEL=gemini-2.0-flash-lite
LLM__URL=https://generativelanguage.googleapis.com/v1beta/openai/chat/completions

Check here for available models.

LLM__KEY=your_open_router_api_key
LLM__MODEL=google/gemini-pro-1.5
LLM__URL=https://openrouter.ai/api/v1/chat/completions

You can use any OpenAI API compatible endpoint. To host your own LLM you can use VLLM or Ollama.

LLM__KEY=your_api_key
LLM__MODEL=model_name
LLM__URL=http://localhost:8000/v1

The core of 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.

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