This project provides a feature-rich, multi-modal web portal for interacting with various Large Language Models (LLMs) including GPT-4, Claude, Gemini, and Mistral. It targets developers and power users seeking a unified interface for text, voice, and image-based AI conversations, offering advanced features like custom instructions, file uploads, and a native code environment.

How It Works

The portal is built on Node.js and integrates with multiple LLM APIs, including OpenAI's Assistants API. It supports voice input/output via Whisper, image uploads for visual context, and file uploads for Retrieval Augmented Generation (RAG). A key differentiator is its native code environment, enabling stateful Python execution within a Jupyter setup, directly leveraging the Assistants API's file and instruction management capabilities.

Quick Start & Requirements

• Installation: Primarily via Docker.
• Prerequisites: Node.js, API keys for supported LLM providers (OpenAI, Anthropic, Google Gemini, Mistral AI, OpenRouter).
• Setup: Docker setup is generally straightforward.
• Documentation: Old Documentation (for v2).

Highlighted Details

• Supports 7+ AI providers including GPT-4 variants, Gemini, Claude 3 family, Mistral models, and LLaMA-3.
• Features voice conversations, image generation (DALL-E 3), and file uploads with RAG.
• Includes a native code environment with Python execution and Assistants API integration.
• Offers customizable chat history, prompt templates, keyboard shortcuts, and automatic token cost calculation.

Maintenance & Community

The project appears to be actively developed, with recent updates and a comprehensive feature set. Links to community resources like Discord or Slack are not explicitly mentioned in the provided README.

Licensing & Compatibility

The README does not specify a license. This requires clarification for commercial use or integration into closed-source projects.

Limitations & Caveats

The documentation is noted as needing a rewrite, with a link provided to older documentation. The licensing status is unclear, which could be a significant blocker for adoption.