Backend for ChatGLM-6B prompt engineering
Top 56.0% on sourcepulse
This project provides a backend for the ChatGLM-6B large language model, offering a ChatGPT-like UI with streaming output for a more interactive user experience. It targets developers and researchers looking to build conversational AI applications with ChatGLM-6B, enabling features like context-aware dialogue and web search integration.
How It Works
The backend leverages a streaming API approach, inspired by existing projects, to deliver token-by-token responses, mimicking the animation of a live chat. It integrates with the ChatGLM-6B model and includes experimental support for features like web search (via WebGLM) and Markmap for mind map generation. The architecture is designed for extensibility, with a plugin system allowing custom prompt processing and response modification.
Quick Start & Requirements
pip install -r requirements.txt
yarn global add markmap-cli
for Markmap.python api.py
(Chat API), python front_end.py
(Backend), python gradio_demo.py
(Gradio Demo). Frontend requires npm install
and yarn dev
.Highlighted Details
Maintenance & Community
Licensing & Compatibility
Limitations & Caveats
1 year ago
1 day