PyGPT is an all-in-one Desktop AI Assistant that provides direct interaction with OpenAI language models, including o1, GPT-4o, GPT-4 Vision, and GPT-3.5, through the OpenAI API. The application also integrates with other LLMs, like Llama 3, Gemini, Mistral, Claude, Bielik, and more, by utilizing Langchain, Llama-index and Ollama.

Features

• Desktop AI Assistant for Linux, Windows, and Mac, written in Python.
• Works similarly to ChatGPT, but locally (on a desktop computer).
• 10 modes of operation: Chat, Vision, Completion, Assistant, Image Generation, Langchain, Chat with Files, Experts, Agent (Llama-index) and Agent (autonomous).
• Supports multiple models: o1, GPT-4o, GPT-4, GPT-3.5, and any model accessible through Langchain, Llama-index and Ollama like Llama 3, Gemini, Mistral, Claude, Bielik and more.
• Included support features for individuals with disabilities: customizable keyboard shortcuts, voice control, and translation of on-screen actions into audio via speech synthesis.
• Handles and stores the full context of conversations (short and long-term memory).
• Real-time video camera capture in Vision mode.
• Internet access via Google and Microsoft Bing.
• Speech synthesis via Microsoft Azure, Google, Eleven Labs, and OpenAI Text-To-Speech services.
• Speech recognition via OpenAI Whisper, Google, Google Cloud, and Microsoft Bing.
• Image analysis via GPT-4 Vision.
• Crontab / Task scheduler included.
• Integrated Langchain support (you can connect to any LLM, e.g., on HuggingFace).
• Integrated Llama-index support: chat with txt, pdf, csv, html, md, docx, json, epub, xlsx, xml, webpages, Google, GitHub, video/audio, images, and other data types, or use conversation history as additional context provided to the model.
• Integrated calendar, day notes, and search in contexts by selected date.
• Commands execution (via plugins: access to the local filesystem, Python code interpreter, system commands execution and many more).
• Custom command creation and execution.
• Custom external API calls creation and execution.
• Manages files and attachments with options to upload, download, and organize.
• Context history with the capability to revert to previous contexts (long-term memory).
• Easily manage prompts with handy editable presets.
• Intuitive operation and interface.
• Includes a notebook.
• Optional Autonomous Mode.
• Supports multiple languages.
• Enables the use of all the powerful features of o1, GPT-4, GPT-4V, and GPT-3.5.
• Requires no prior knowledge of using AI models.
• Simplifies image generation using DALL-E 3 and DALL-E 2.
• Potential to support future OpenAI models.
• Fully configurable.
• Themes support.
• Plugins support.
• Built-in token usage calculation.
• Open source; source code available on GitHub.
• Utilizes the user's own API key.

The application is free, open-source, and runs on PCs with Linux, Windows and Mac. The full Python source code is available on GitHub.

Project website: https://pygpt.net

GitHub: https://github.com/szczyglis-dev/py-gpt

PyPi: https://pypi.org/project/pygpt-net

Documentation: https://pygpt.readthedocs.io/en/latest

Changelog:

2.4.18 (2024-11-21)

• Refactored kernel status and state handling.
• Fixed: audio input execution.
• Improved output from tools in Agents.
• Added status loading animation indicator.
• Other fixes.