---
title: "Deploy Docling - OCR anything"
description: "Get any document AI / LLM Ready"
category: "AI/ML"
url: https://railway.com/deploy/docling-ocr-anything
---

# Deploy Docling - OCR anything

Get any document AI / LLM Ready

**[Deploy Docling - OCR anything on Railway](https://railway.com/template/docling-ocr-anything)**

- **Creator:** SuperSlowSloth
- **Category:** AI/ML
- **Total deploys:** 109

## Template content

### caddy

- **Source:** bon5co/docling-railway-template
- **Public domain:** Yes

### docling

- **Image:** quay.io/docling-project/docling-serve-cpu:latest
- **Start command:** `docling-serve run --host "::"`

## Documentation

[![Deploy on Railway](https://railway.com/button.svg)](https://railway.com/new/template/docling-ocr-anything?referralCode=Z1xivh)

# Usage
## Production
Call API with Header: `Authorization: Bearer  CADDY.CADDY_AUTHORIZATION`  
The CADDY_AUTHORIZATION is randomly generated, get it from the Caddy's environment variable.   
Visit documentation `/docs` or `/scalar`
## Using included UI
Configure `DOCLING_SERVE_ENABLE_UI=1` in Docling
Try it out with Gradio UI at `/ui`


# Deploy and Host Docling - OCR anything on Railway
Docling is a powerful document processing tool that parses diverse formats including PDF, DOCX, PPTX, images, and audio files. It features advanced PDF understanding with layout analysis, table extraction, and formula recognition, while offering seamless integrations with popular AI frameworks and local execution for sensitive data.


## About Hosting Docling - OCR anything
Hosting Docling provides a comprehensive document processing service capable of handling multiple file formats through advanced parsing techniques. The deployment includes OCR capabilities for scanned documents, Visual Language Model support, and ASR for audio transcription. With its unified DoclingDocument format and various export options (Markdown, HTML, JSON), Docling serves as a versatile document intelligence solution. The service can run locally for air-gapped environments or be deployed as a scalable API, making it ideal for enterprise document processing workflows and AI-powered applications.

## Common Use Cases
- **Document Intelligence Pipeline**: Extract structured data from PDFs, invoices, reports, and forms for automated processing and analysis
- **Multi-format Content Ingestion**: Convert diverse document types (PDFs, Office files, images, audio) into AI-ready formats for RAG systems and chatbots
- **Enterprise Document Processing**: Parse complex technical documents, research papers, and legal contracts while preserving tables, formulas, and formatting

## Dependencies for Docling - OCR anything Hosting
None

### Deployment Dependencies
None

## Why Deploy Docling - OCR anything on Railway?
Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Docling - OCR anything on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.

## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/docling-ocr-anything