Detailed Introduction
Gemini Balance is a Python FastAPI based application designed to act as a proxy and load balancer for the Google Gemini API. It enables users to manage multiple Gemini API keys and facilitates several advanced functionalities, including key polling, authentication, and status monitoring.
Key Features:
- Multi-Key Load Balancing: Supports configuration of multiple Gemini API keys with automatic polling for enhanced availability and concurrency.
- Real-time Configuration: Allows modifications to configurations via a management interface without needing to restart services.
- Dual-Protocol API Compatibility: Can forward requests in both Gemini and OpenAI API formats seamlessly.
- Key Status Monitoring: Offers a dedicated endpoint to monitor the status and usage of all configured keys in real time.
- Detailed Logging: Provides comprehensive error logs for easy troubleshooting.
- Docker Support: Facilitates easy deployment on both AMD and ARM architectures with simple Docker commands.
Benefits:
- Enhanced Flexibility: Supports extensive configuration options for managing API keys and functionalities.
- Robust Error Handling: Built-in retry and failure management for API calls ensures high reliability.
- Developer-Friendly: Instructions for local development and testing make the onboarding process seamless.
Gemini Balance aims to simplify the integration and utilization of the Gemini API, making it an indispensable tool for developers looking to leverage AI capabilities efficiently.