Deploy FastAPIChat

Overview

FastAPIChat is a modern, high-performance application for benchmarking LLM models from different vendors. Built with FastAPI and Python 3.9+, it leverages the power of FastAPI's asynchronous capabilities and provides an extensive system for collecting user feedback.

Highlights

• Multi-LLM Benchmarking: Easily compare and evaluate the performance of LLM models from various vendors with different system prompts and temperature settings.
• Feedback Collection: Implement a robust feedback system to rate LLM outputs, enabling data collection for future fine-tuning and improvements.
• Streaming Responses: Integrated with FastAPI for real-time, non-blocking streaming responses, enhancing the user experience with immediate feedback.

Learn More

• Github