Welcome to my Chat-Bot Portal, a full-featured Node.js-based web application that allows users to interact with a chatbot powered by OpenAI's GPT-4 API, including the latest Vision, Hearing, and Speaking capabilities with image-generation, file uploads, and superior Model Performance from advanced and editable Custom Instructions in the System Prompt.

GPTPortal now supports the Anthropic Claude and Mistral AI models, plus Google Gemini via free API. It also includes a native Code Environment via Assistants Mode to reuse files and instructions from OpenAI's Beta API! Explore all the additional features added, like customizable Chat History, Prompt Templates, easy Setup, and many more API Providers.

• Features
• Examples
• Structure
• Prerequisites
• Installation
• Usage
• Assistants
• Author Notes
• Further Explanations
• Basic Guide
• Google Gemini
• Mistral AI
• Anthropic Claude
• Meta LLaMA AI
• OpenRouter AI
• Relevant Links
• Author Links
• Research Papers
• FAQ
• Glossary
• Updates
• Tokens
• TODOs
• Quick-Start
• Docker
• Contributions
• License

• Interactive chat interface with support for text messages.
• Voice Conversations via Whisper transcriptions and spoken responses.
• Image Upload functionality for visual context in discussions.
• Server-side integration with SEVEN AI API providers and counting.
• Basic authentication for secure access.
• Customizable System-Defined Instructions and Model Parameters.
• Simple and intuitive UI with copy-to-clipboard features.
• Markdown rendering for chat messages in Marked styles.
• Export as HTML button for conversation history.
• Integrated shutdown functionality at "Bye!"
• Image Generation with DALL·E 3 at "Generate:".
• File Uploads via manual concatenation for large texts.
• Assistants API Mode for reusable files and custom instructions.
  • Includes Automatic Python Execution in stateful Jupyter Environment.
  • Retrieval Augmented Generation of uploaded files.
• New Anthropic Claude, Google Gemini, & Mistral Models.
• Keyboard Shortcuts to control various ChatGPT-like functions.
• Editable Custom Instructions via a frontend UI.
• Prompt Templates for the System via Sidebar.
• Conversation History with optimized context windows.
• Automatic Token-Cost Calculations and Summaries.
• Model Selector of various LLM APIs. Includes:
  • GPT-4: EVERY GPT Model Release
    • Includes 4o, Turbo, old v4, 3.5, etc.
  • Gemini: ALL Google Gemini Models
    • Includes Gemini-Pro and Flash
  • Claude Opus-Instant:
    • Seven New Anthropic High Performance Models
      • A Description can be found under Anthropic AI Setup.
  • Mistral: Tiny-Medium
    • Six New Mistral AI Models
      • Intelligence Varies by Size
      • A Description can be found under Mistral AI Setup.
  • LLaMA-3: FREE Llama Models via Qroq
  • Open Router: ANY Other Models you can imagine!

// TODO: Rewrite Documentation

IMPORTANT: To view the old documentation (which is still applicable to v2), please see the Old Documentation Here.