Skip to content

Installation

Basic Installation

Install unifex using pip:

pip install unifex

Or using uv:

uv add unifex

Optional Dependencies

unifex uses optional dependencies to keep the base installation lightweight. Install only what you need:

PDF Extraction

pip install unifex[pdf]

Local OCR Engines

# EasyOCR
pip install unifex[easyocr]

# Tesseract (requires system Tesseract installation)
pip install unifex[tesseract]

# PaddleOCR
pip install unifex[paddle]

Cloud OCR Services

# Azure Document Intelligence
pip install unifex[azure]

# Google Document AI
pip install unifex[google]

LLM Providers

# OpenAI
pip install unifex[llm-openai]

# Anthropic
pip install unifex[llm-anthropic]

# Google Gemini
pip install unifex[llm-google]

# All LLM providers
pip install unifex[llm-all]

Everything

pip install unifex[all]

System Requirements

Tesseract OCR

Tesseract requires system installation:

  • macOS: brew install tesseract
  • Ubuntu: apt-get install tesseract-ocr
  • Windows: Download from UB-Mannheim/tesseract

PaddleOCR

PaddleOCR works out of the box but may require additional setup for GPU acceleration.