| # ============================================================================= | |
| # Research AI Assistant API - Environment Configuration | |
| # ============================================================================= | |
| # Copy this content to a file named .env and fill in your actual values | |
| # Never commit .env to version control! | |
| # ============================================================================= | |
| # ZeroGPU Chat API Configuration (REQUIRED) | |
| # ============================================================================= | |
| # Base URL for your ZeroGPU Chat API endpoint (RunPod) | |
| # Format: http://your-pod-ip:8000 or https://your-domain.com | |
| # Example: http://bm9njt1ypzvuqw-8000.proxy.runpod.net | |
| ZEROGPU_BASE_URL=http://your-pod-ip:8000 | |
| # Email for authentication (register first via /register endpoint) | |
| ZEROGPU_EMAIL=your-email@example.com | |
| # Password for authentication | |
| ZEROGPU_PASSWORD=your_secure_password_here | |
| # ============================================================================= | |
| # Token Allocation Configuration | |
| # ============================================================================= | |
| # Maximum tokens dedicated for user input (prioritized over context) | |
| # Recommended: 32000 tokens for DeepSeek R1 (128K context window) | |
| USER_INPUT_MAX_TOKENS=32000 | |
| # Maximum tokens for context preparation (includes user input + context) | |
| # Recommended: 115000 tokens for DeepSeek R1 (leaves ~13K for output) | |
| CONTEXT_PREPARATION_BUDGET=115000 | |
| # Context pruning threshold (should match context_preparation_budget) | |
| CONTEXT_PRUNING_THRESHOLD=115000 | |
| # Always prioritize user input over historical context | |
| PRIORITIZE_USER_INPUT=True | |
| # Model context window (actual limit for your deployed model) | |
| # Default: 8192 tokens (adjust based on your model) | |
| # This is the maximum total tokens (input + output) the model can handle | |
| # Common values: 4096, 8192, 16384, 32768, etc. | |
| ZEROGPU_MODEL_CONTEXT_WINDOW=8192 | |
| # ============================================================================= | |
| # Database Configuration | |
| # ============================================================================= | |
| # SQLite database path (default: sessions.db) | |
| # Use /tmp/ for Docker/containerized environments | |
| DB_PATH=sessions.db | |
| # FAISS index path for embeddings (default: embeddings.faiss) | |
| FAISS_INDEX_PATH=embeddings.faiss | |
| # ============================================================================= | |
| # Cache Configuration | |
| # ============================================================================= | |
| # HuggingFace cache directory (for any remaining model downloads) | |
| HF_HOME=~/.cache/huggingface | |
| TRANSFORMERS_CACHE=~/.cache/huggingface | |
| # HuggingFace token (optional - only needed if using gated models) | |
| HF_TOKEN= | |
| # Cache TTL in seconds (default: 3600 = 1 hour) | |
| CACHE_TTL=3600 | |
| # ============================================================================= | |
| # Session Configuration | |
| # ============================================================================= | |
| # Session timeout in seconds (default: 3600 = 1 hour) | |
| SESSION_TIMEOUT=3600 | |
| # Maximum session size in megabytes (default: 10 MB) | |
| MAX_SESSION_SIZE_MB=10 | |
| # ============================================================================= | |
| # Performance Configuration | |
| # ============================================================================= | |
| # Maximum worker threads for parallel processing (default: 4) | |
| MAX_WORKERS=4 | |
| # ============================================================================= | |
| # Mobile Optimization | |
| # ============================================================================= | |
| # Maximum tokens for mobile responses (default: 1200) | |
| # Increased from 800 to allow better responses on mobile | |
| MOBILE_MAX_TOKENS=1200 | |
| # Mobile request timeout in milliseconds (default: 15000) | |
| MOBILE_TIMEOUT=15000 | |
| # ============================================================================= | |
| # API Configuration | |
| # ============================================================================= | |
| # Flask/Gradio server port (default: 7860) | |
| GRADIO_PORT=7860 | |
| # Server host (default: 0.0.0.0 for all interfaces) | |
| GRADIO_HOST=0.0.0.0 | |
| # ============================================================================= | |
| # Logging Configuration | |
| # ============================================================================= | |
| # Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL (default: INFO) | |
| LOG_LEVEL=INFO | |
| # Log format: json or text (default: json) | |
| LOG_FORMAT=json | |
| # Log directory (default: /tmp/logs) | |
| LOG_DIR=/tmp/logs | |
| # ============================================================================= | |
| # Context Configuration | |
| # ============================================================================= | |
| # Maximum context tokens (default: 4000) | |
| # Note: This is overridden by CONTEXT_PREPARATION_BUDGET if set | |
| MAX_CONTEXT_TOKENS=4000 | |
| # Cache TTL for context in seconds (default: 300 = 5 minutes) | |
| CACHE_TTL_SECONDS=300 | |
| # Maximum cache size (default: 100) | |
| MAX_CACHE_SIZE=100 | |
| # Enable parallel processing (default: True) | |
| PARALLEL_PROCESSING=True | |
| # Context decay factor (default: 0.8) | |
| CONTEXT_DECAY_FACTOR=0.8 | |
| # Maximum interactions to keep in context (default: 10) | |
| MAX_INTERACTIONS_TO_KEEP=10 | |
| # Enable metrics collection (default: True) | |
| ENABLE_METRICS=True | |
| # Enable context compression (default: True) | |
| COMPRESSION_ENABLED=True | |
| # Summarization threshold in tokens (default: 2000) | |
| SUMMARIZATION_THRESHOLD=2000 | |
| # ============================================================================= | |
| # Model Selection (for context operations - if still using local models) | |
| # ============================================================================= | |
| # These are optional and only used if local models are still needed | |
| # for context summarization or other operations | |
| CONTEXT_SUMMARIZATION_MODEL=Qwen/Qwen2.5-7B-Instruct | |
| CONTEXT_INTENT_MODEL=Qwen/Qwen2.5-7B-Instruct | |
| CONTEXT_SYNTHESIS_MODEL=Qwen/Qwen2.5-7B-Instruct | |
| # ============================================================================= | |
| # Security Notes | |
| # ============================================================================= | |
| # - Never commit .env file to version control | |
| # - Keep API keys secret and rotate them regularly | |
| # - Use environment variables in production (not .env files) | |
| # - Set proper file permissions: chmod 600 .env | |