This Group Chat + AI application enables users to have real-time interactive conversations with a bot in a group chat setting. It provides features like:
- Personalized Usernames: Set your name and chat with others.
- File Sharing: Share files with others in the chat.
- Intelligent Responses: The bot gives intelligent responses powered by external APIs like Gemini and Ollama.
- Code Generation: The bot can generate code snippets based on user queries.
The user interface is simple and intuitive, making it easy to start chatting and sharing files. It's a fun and helpful tool for quick answers, casual conversations, and collaborative chatting.
Before you begin, ensure you have the following:
- Ollama (with
llama3model) - Node.js v18 to v22
- Gemini Api Key
For Windows users:
- Download the Ollama installer from the Ollama official website and follow the installation instructions.
For macOS and Linux users:
- You can install Ollama using Homebrew on macOS or follow the relevant installation guides on the Ollama GitHub repository for Linux.
To interact with the model in your application, you'll need to download one of Ollama’s models.
-
View available models:
ollama models
-
Download the llama3 model:
ollama pull llama3
-
Start the model server (only if you need to run it offline):
ollama serve
-
Ollama Server Status After running the ollama serve command, the server should start locally. You should see an output like this:
Ollama server started at http://localhost:11434
- Frontend: HTML, CSS, JavaScript (Vanilla)
- Backend: Node.js, Express.js
- Real-time Communication: Socket.IO
- External APIs: Google Gemini API, Ollama API (for intelligent responses)
- File Handling: Upload and download files directly in the chat
- Web Scokets: For effective Real-time Communication