https://github.com/randyungaro/rust-chat-app
AI Chat Web App based on Rust
https://github.com/randyungaro/rust-chat-app
chatbot javascript ollama rust
Last synced: 2 months ago
JSON representation
AI Chat Web App based on Rust
- Host: GitHub
- URL: https://github.com/randyungaro/rust-chat-app
- Owner: randyungaro
- License: mit
- Created: 2025-03-04T09:53:37.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-11T12:27:39.000Z (about 1 year ago)
- Last Synced: 2026-04-30T07:50:01.389Z (2 months ago)
- Topics: chatbot, javascript, ollama, rust
- Language: Rust
- Homepage:
- Size: 27.3 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README

# Rust Chat App with Ollama Models
This is a simple web-based AI chat application built with Rust, leveraging Ollama to run large language models (LLMs).
It provides a user-friendly interface for interacting with AI models directly in your browser.
## Features
- **Rust Backend:** Built with Rust for performance and reliability.
- **Ollama Integration:** Uses Ollama to run and manage LLMs locally.
- **Web-based Interface:** Accessible through any modern web browser.
- **Real-time Chat:** Provides a seamless chat experience with the AI.
- **Easy Deployment:** Designed for straightforward setup and deployment.
## Prerequisites
Before you begin, ensure you have the following installed:
- **Rust and Cargo:** [Install Rust](https://www.rust-lang.org/tools/install)
- **Ollama:** [Install Ollama](https://ollama.ai/download)
- **A Compatible LLM:** Pull a model from Ollama, e.g., `ollama pull llama2` ( i use DeepSeek models)
## Getting Started
1. **Clone the repository:**
```bash
git clone https://github.com/randyungaro/rust-chat-app
2. **Build the Rust application:**
```bash
cargo run
3. **Access the application:**
Open your web browser and navigate to http://localhost:8080

## Configuration
You can configure the application through environment variables:
- OLLAMA_MODEL: Specifies the Ollama model to use (default: llama2).
- HOST: Specifies the host address to bind to (default: 0.0.0.0).
- PORT: Specifies the port to listen on (default: 8080).
## License
This project is licensed under MIT License