This project provides a web-based chat application for teams, offering user management, rate limiting, and support for multiple large language models including OpenAI (ChatGPT), Claude, Gemini, and Ollama. It aims to streamline team collaboration with AI by enabling shared conversations, searchable history, and prompt management.

How It Works

The application supports multiple LLM backends, allowing users to switch between OpenAI, Claude, Gemini, and local Ollama models. It includes features like context management (defaulting to the last 4 messages), conversation snapshots with full-text search (English), and the ability to generate shareable static pages from conversations. An optional feature uses Gemini to auto-generate conversation titles.

Quick Start & Requirements

• Install/Run: Deployment instructions are available in the Deployment Guide.
• Prerequisites: Requires configuration for API keys for supported models. Ollama host models require separate setup.
• Links: Adding New Models Guide, Snapshots vs ChatBots, Using Local Ollama, Community Discussions.

Highlighted Details

• Supports OpenAI, Claude, Gemini, and Ollama models.
• Conversation snapshots with English full-text search.
• Rate limiting (default 100 calls/10 min for ChatGPT).
• Shareable static conversation pages.

Maintenance & Community

• Active community discussions available via GitHub Discussions.
• Development guide and deployment guides are provided.

Licensing & Compatibility

• MIT License. Permissive for commercial use and integration with closed-source projects.

Limitations & Caveats

The project's web frontend is noted as being copied from Chanzhaoyu/chatgpt-web. Full-text search is currently limited to English. Auto-generated conversation titles require a specific Gemini model configuration.