forked from MCP/llm-fusion-mcp
Ryan Malloy
c335ba0e1e
- Unified access to 4 major LLM providers (Gemini, OpenAI, Anthropic, Grok) - Real-time streaming support across all providers - Multimodal capabilities (text, images, audio) - Intelligent document processing with smart chunking - Production-ready with health monitoring and error handling - Full OpenAI ecosystem integration (Assistants, DALL-E, Whisper) - Vector embeddings and semantic similarity - Session-based API key management - Built with FastMCP and modern Python tooling 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
76 lines
2.2 KiB
Plaintext
76 lines
2.2 KiB
Plaintext
# LLM Fusion MCP - Production Environment Configuration
|
|
# Copy this file to .env and configure your API keys
|
|
|
|
# =============================================================================
|
|
# LLM PROVIDER API KEYS
|
|
# =============================================================================
|
|
|
|
# Google Gemini (Required - Primary Provider)
|
|
GOOGLE_API_KEY=your_google_api_key_here
|
|
|
|
# OpenAI (Optional - GPT models, DALL-E, Whisper)
|
|
OPENAI_API_KEY=your_openai_api_key_here
|
|
|
|
# Anthropic (Optional - Claude models)
|
|
ANTHROPIC_API_KEY=your_anthropic_api_key_here
|
|
|
|
# xAI Grok (Optional - Grok models)
|
|
XAI_API_KEY=your_xai_api_key_here
|
|
|
|
# =============================================================================
|
|
# SERVER CONFIGURATION
|
|
# =============================================================================
|
|
|
|
# Server Mode (development, production)
|
|
SERVER_MODE=production
|
|
|
|
# Logging Level (DEBUG, INFO, WARNING, ERROR)
|
|
LOG_LEVEL=INFO
|
|
|
|
# Maximum file size for analysis (in MB)
|
|
MAX_FILE_SIZE_MB=50
|
|
|
|
# Request timeout (in seconds)
|
|
REQUEST_TIMEOUT=300
|
|
|
|
# =============================================================================
|
|
# PERFORMANCE SETTINGS
|
|
# =============================================================================
|
|
|
|
# Model cache timeout (in minutes)
|
|
MODEL_CACHE_TIMEOUT=5
|
|
|
|
# Maximum concurrent requests
|
|
MAX_CONCURRENT_REQUESTS=10
|
|
|
|
# Rate limiting (requests per minute per provider)
|
|
RATE_LIMIT_PER_MINUTE=60
|
|
|
|
# =============================================================================
|
|
# SECURITY SETTINGS
|
|
# =============================================================================
|
|
|
|
# Enable API key rotation (true/false)
|
|
ENABLE_KEY_ROTATION=false
|
|
|
|
# API key rotation interval (in hours)
|
|
KEY_ROTATION_INTERVAL=24
|
|
|
|
# Enable request logging (true/false)
|
|
ENABLE_REQUEST_LOGGING=true
|
|
|
|
# =============================================================================
|
|
# MONITORING & OBSERVABILITY
|
|
# =============================================================================
|
|
|
|
# Enable health checks (true/false)
|
|
ENABLE_HEALTH_CHECKS=true
|
|
|
|
# Health check interval (in seconds)
|
|
HEALTH_CHECK_INTERVAL=30
|
|
|
|
# Enable metrics collection (true/false)
|
|
ENABLE_METRICS=true
|
|
|
|
# Metrics port (for Prometheus scraping)
|
|
METRICS_PORT=9090 |