https://github.com/mrmendoza-dev/offline-chatbot
ChatGPT style interface for working with LLMs offline locally using Ollama.
https://github.com/mrmendoza-dev/offline-chatbot
ai chatbot chatgpt llama3 mistral ollama react vite
Last synced: over 1 year ago
JSON representation
ChatGPT style interface for working with LLMs offline locally using Ollama.
- Host: GitHub
- URL: https://github.com/mrmendoza-dev/offline-chatbot
- Owner: mrmendoza-dev
- License: mit
- Created: 2024-07-28T00:17:49.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-02-14T01:20:04.000Z (over 1 year ago)
- Last Synced: 2025-02-14T02:28:21.724Z (over 1 year ago)
- Topics: ai, chatbot, chatgpt, llama3, mistral, ollama, react, vite
- Language: TypeScript
- Homepage: https://medium.com/@mrmendoza-dev/offline-chatbots-with-ollama-52dd18f97933
- Size: 645 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Offline AI Chatbot
A desktop application that provides a clean interface for interacting with Ollama's AI models locally. Chat with AI models without needing internet connectivity after initial setup.
## Features
* Fully offline AI chat capabilities
* Multiple AI model support through Ollama
* Support for basic text files, CSVs, and JSON
* Support for images compatible with select models
* LLaVa and Llama 3.2 for example
* Clean, modern interface
* Dark/Light mode support
* Real-time responses
* Local data storage
## Prerequisites
1. Install Ollama:
* Visit [Ollama's website](https://ollama.com/)
* Download and install for your system
* Open terminal and verify installation:
```bash
ollama --version
```
* Pull and run your first model:
```bash
ollama pull llama2
ollama run llama2
```
* Check out my [blog post](https://medium.com/@mrmendoza-dev/offline-chatbots-with-ollama-52dd18f97933) for more information on how to get started with Ollama.
## Setup
1. Clone the repository
```bash
git clone https://github.com/yourusername/offline-chatbot.git
cd offline-chatbot
```
2. Install dependencies
```bash
npm install
```
3. Create a `.env` file in the root directory:
```env
VITE_PORT=3030
```
## Running the Application
Start both frontend and backend servers:
```bash
npm start
```
This will run:
* Frontend: `http://localhost:5173`
* Backend: `http://localhost:3030`
## Development
Run frontend only:
```bash
npm run dev
```
Run backend only:
```bash
npm run server
```
## Project Structure
```
offline-chatbot/
├── src/ # Frontend source code
├── server/ # Backend server code
└── public/ # Static assets
```
## Environment Variables
| Variable | Description | Required |
|----------|-------------|----------|
| VITE_PORT | Backend server port | Yes |
## Tech Stack
* React + Vite
* Express.js
* Ollama API
* TailwindCSS
* Node.js
## Additional Resources
* [Offline Chatbots with Ollama - Blog Post](https://medium.com/@mrmendoza-dev/offline-chatbots-with-ollama-52dd18f97933)
* [Ollama JS Documentation](https://github.com/ollama/ollama-js)
* [Ollama Model Library](https://ollama.com/library)
## License
MIT