env.example

# AI Provider Configuration
AI_PROVIDER=openai
# Options: "openai" or "transformers"

# AI Configuration
OPENAI_API_KEY=your_openai_api_key
OPENAI_API_BASE=https://api.openai.com/v1
# For Ollama: OPENAI_API_BASE=http://localhost:11434/v1
# For OpenAI: OPENAI_API_BASE=https://api.openai.com/v1

# Model Configuration
MODEL_NAME=gpt-4o-mini
# For OpenAI: gpt-4o-mini, gpt-3.5-turbo, etc.
# For Transformers (Qwen3): Qwen/Qwen3-8B, Qwen/Qwen3-4B, etc.
# Note: Use exact model names from https://huggingface.co/collections/Qwen/qwen3-67dd247413f0e2e4f653967f

# GPU/CPU Configuration (for Transformers provider)
USE_GPU=true
# Options: "true" (default, use GPU if available) or "false" (force CPU)
# Note: If GPU is not available, will automatically fall back to CPU

# Memory Optimization (for GPU with limited memory)
# Set to "false" if you have limited GPU memory (like 6GB or less)
USE_MEMORY_OPTIMIZATION=true

# App Configuration
APP_HOST=0.0.0.0
APP_PORT=8000
APP_DEBUG=true