Skip to main content
Hero Light

​
What is Document Converter?

Document Converter is a production-ready API that transforms various document formats into structured Markdown or JSON. Built for scalability and reliability, it handles everything from PDFs and Word documents to images and spreadsheets.

Multi-Format Support

Convert PDF, DOCX, PPTX, XLSX, images, and more into structured data

OCR Processing

Extract text from images using PaddleOCR, EasyOCR, or Mistral AI

Async Processing

Queue-based processing with real-time progress tracking and webhooks

Production Ready

Docker support, health checks, monitoring, and horizontal scaling

​
Key Features

  • Documents: PDF, Microsoft Word (.docx), Rich Text Format (.rtf)
  • Presentations: Microsoft PowerPoint (.pptx, .pptm, .potx, .potm)
  • Spreadsheets: Microsoft Excel (.xlsx, .xlsm, .xls)
  • Images: PNG, JPEG, GIF, BMP, WebP, ICO, TIFF
  • Text: Plain text (.txt), Markdown (.md), Log files
  • Other: HTML, CSV, JSON, XML
  • Markdown (.md): Human-readable markdown with embedded base64 images
  • Structured JSON (.json): Hierarchical data preserving document organization
  • PaddleOCR: High-accuracy OCR with support for 80+ languages
  • EasyOCR: Simple and effective OCR with good performance
  • Mistral AI: AI-powered OCR with advanced text understanding

​
Architecture Overview

The Document Converter follows a modern microservices architecture:
  1. API Layer: FastAPI server handles REST requests
  2. Queue System: Redis-based message queue for async processing
  3. Workers: Celery workers process conversion tasks
  4. Converters: Modular converter system for different file types
  5. Storage: Abstracted file storage for uploads and results
  6. Notifications: Webhook system for real-time updates

​
Quick Example

curl -X POST "http://localhost:8000/api/v1/jobs" \
  -H "Content-Type: multipart/form-data" \
  -F "[email protected]" \
  -F "output_format=json" \
  -F "webhook_url=https://your-site.com/webhook"
Ready to get started? Check out the Quickstart Guide to set up the Document Converter in minutes.

​
Use Cases

Content Management

Convert legacy documents to searchable, structured formats

Data Extraction

Extract structured data from invoices, reports, and forms

Document Digitization

Convert scanned documents and images to editable text

Knowledge Base

Build searchable knowledge bases from document collections

Compliance

Archive documents in standardized formats for compliance

Automation

Integrate with workflows for automated document processing

​
Getting Help

Community Support

Join our community for questions and discussions

GitHub Issues

Report bugs and request features