Β
Β
Monadic Chat is a framework designed to create and use intelligent chatbots. By providing a full-fledged Linux environment on Docker to GPT-4 and other LLMs, it allows the chatbots to perform advanced tasks that require external tools. It also supports voice interaction, image and video recognition and generation, and AI-to-AI chat, suitable not only for using AI but also for developing and researching various applications.
- Recent Updates
- [Sep, 2024] 0.8.14
- Many under-the-hood improvements
- [Aug, 2024] 0.8.11
- App authoring format changed
- Claude Jupyter Notebook app added
- Math rendering improved
- Second Opinion app added
- PDF Document import/export feature
- [Jul, 2024]
- Mistral AI (Chat and Code Interpreter) app added
- Multiple images can be uploaded for image recognition
- Continue button introduced
- Jupyter Notebook app added
- Browser auto open
- Linux (Ubuntu/Debian) installer released
- App file name changed from monadic-chat to Monadic Chat
- Settings menu added
- [Jun, 2024]
- Speech Draft Helper app added (with TTS audio file generation)
- Menu bar items added; Shared Folder asccessible on Windows
- Better uninstallation of containers
- Monadic Chat Console UI improved
- AI-User feature introduced
- Automatic Docker image rebuild feature
- Source code block copy button added
- Video Describer app added
- Full Change Log
- [Sep, 2024] 0.8.14
- Download installer for macOS (Apple Silicon/Intel)
- Download installer for Windows
- Download installer for Linux (Ubuntu/Debian)
There is another version of Monadic Chat, which is a command line app provided as a RubyGem.
- π€ Chat functionality powered by GPT-4 via OpenAI's Chat API
- π©βπ» Installable as a GUI application on Mac and Windows using Electron
- π Usable as a web application in browsers
- π©π¬ π€π¬ Both human
βοΈ AI chat and AIβοΈ AI chat are supported
- π§ Provides a Linux environment (Ubuntu) freely accessible by AI
- π³ Tools for LLMs via Docker containers
- Python (+ pip) for tool/function calls
- Ruby (+ gem) for tool/function calls
- PGVector (+ PostgreSQL) for DAG using vector representation
- Selenium (+ Chrome/Chromium) for web scraping
- π¦ Each container can be managed via SSH
- π Python container can launch Jupyter Notebook
- πΎ Export/import conversation data
- π¬ Specify the number of recent messages (active messages) to send to the API
- π’ Generate text embeddings from data in PDF files
- π Local data folders are synchronized with Docker containers for seamless interaction
- ποΈ Automatic transcription of microphone input using OpenAI's Whisper API
- π Text-to-speech functionality for AI assistant responses
- πΊοΈ Automatic language detection for appropriate text-to-speech playback
- π£οΈ Choose the language and voice for text-to-speech
- π Enable interactive conversations with the AI agent using speech recognition and text-to-speech
- π§ Text data can be spoken by the AI agent and saved as an MP3 audio file
- πΌοΈ Generate images from text prompts using OpenAI's DALLΒ·E 3 API
- π Analyze and describe the content of uploaded images
- π Multiple images can be uploaded for recognition
- π₯ Recognize and describe the content and audio of uploaded video
- π‘ Customize the AI agent's behavior by specifying API parameters and the system prompt
- π Extend functionality using the Ruby programming language
- π Extend functionality using the Python programming language
- π Perform web scraping using Selenium
- π Edit previous messages
- ποΈ Delete specific messages
- π Set roles (user, assistant, system) for new messages
-
π₯ Multiple LLM APIs are supported:
- OpenAI GPT-4
- Google Gemini
- Anthropic Claude
- Cohere Command R
- Mistral AI
-
π€π¬π€ AI
βοΈ AI Chat is available:AI-Assistant AI-User OpenAI GPT-4 βοΈ OpenAI GPT-4 or GPT4o Google Gemini βοΈ OpenAI GPT-4 or GPT4o Anthropic Claude βοΈ OpenAI GPT-4 or GPT4o Cohere Command R βοΈ OpenAI GPT-4 or GPT4o Mistral AI βοΈ OpenAI GPT-4 or GPT4o
- β»οΈ Manage (invisible) conversation state by obtaining additional responses from LLM and updating values in a predefined JSON object
Yoichiro HASEBE
yohasebe@gmail.com
The gem is available as open source under the terms of the MIT License.