# OCR PDF MCP Server v1.0.0 - Environment Configuration Template
# Copy this file to .env and customize the values
# ============================================================================
# TESSERACT OCR CONFIGURATION
# ============================================================================
# Path to Tesseract executable (REQUIRED)
# Windows: TESSERACT_PATH=C:\Program Files\Tesseract-OCR\tesseract.exe
# macOS (Homebrew): TESSERACT_PATH=/usr/local/bin/tesseract
# macOS (MacPorts): TESSERACT_PATH=/opt/local/bin/tesseract
# Linux: TESSERACT_PATH=/usr/bin/tesseract
TESSERACT_PATH=C:\Program Files\Tesseract-OCR\tesseract.exe
# ============================================================================
# OCR PROCESSING SETTINGS
# ============================================================================
# Default OCR language(s) - use + to combine languages
# Examples: eng, ind, eng+ind, fra+eng, deu+eng
# See: https://github.com/tesseract-ocr/tessdata
OCR_LANGUAGE=eng+ind
# Maximum number of parallel OCR workers (1-8)
# Recommended: Number of CPU cores
MAX_WORKERS=4
# OCR timeout per page in seconds
OCR_TIMEOUT_SECONDS=300
# Maximum PDF file size in MB
PDF_MAX_SIZE_MB=100
# ============================================================================
# LOGGING CONFIGURATION
# ============================================================================
# Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL
LOG_LEVEL=INFO
# Log format string
LOG_FORMAT=%(asctime)s - %(name)s - %(levelname)s - %(message)s
# ============================================================================
# OPTIONAL: STANDALONE API SERVER SETTINGS
# ============================================================================
# These are only used if running the server in standalone HTTP mode
# (not typically needed for MCP usage)
# Server host (usually 0.0.0.0 for production, 127.0.0.1 for development)
HOST=0.0.0.0
# Server port
PORT=8000
# Enable debug mode (development only)
DEBUG=False
# ============================================================================
# ADVANCED SETTINGS
# ============================================================================
# Python path additions (usually not needed)
# PYTHONPATH=/path/to/additional/modules
# Custom temporary directory for processing
# TEMP_DIR=/tmp/ocr_processing
# Enable performance profiling (development only)
# ENABLE_PROFILING=False
# ============================================================================
# EXAMPLE CONFIGURATIONS
# ============================================================================
# Minimal configuration (Windows):
# TESSERACT_PATH=C:\Program Files\Tesseract-OCR\tesseract.exe
# High-performance configuration:
# TESSERACT_PATH=/usr/bin/tesseract
# OCR_LANGUAGE=eng
# MAX_WORKERS=8
# OCR_TIMEOUT_SECONDS=600
# PDF_MAX_SIZE_MB=200
# LOG_LEVEL=WARNING
# Development configuration:
# TESSERACT_PATH=/usr/local/bin/tesseract
# OCR_LANGUAGE=eng+ind
# MAX_WORKERS=2
# LOG_LEVEL=DEBUG
# DEBUG=True
# Multi-language configuration:
# TESSERACT_PATH=/usr/bin/tesseract
# OCR_LANGUAGE=eng+fra+deu+spa+ita
# MAX_WORKERS=6
# OCR_TIMEOUT_SECONDS=450
