https://github.com/wazeerc/illama
A UI built with Nuxt for interacting with anny Ollama models locally.
https://github.com/wazeerc/illama
ai aichatbot nuxt ollama
Last synced: 8 months ago
JSON representation
A UI built with Nuxt for interacting with anny Ollama models locally.
- Host: GitHub
- URL: https://github.com/wazeerc/illama
- Owner: wazeerc
- Created: 2025-01-31T14:43:25.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-02-18T19:37:41.000Z (8 months ago)
- Last Synced: 2025-02-18T20:35:08.520Z (8 months ago)
- Topics: ai, aichatbot, nuxt, ollama
- Language: Vue
- Homepage:
- Size: 200 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# iLlama - A web app built with Nuxt for Llama Models
A web interface built with Nuxt for interacting with any OLlama language model locally.
## Prerequisites
- Docker
- Docker Compose
- Node.js (for local development)
- pnpm
- oLlama (for local development)
## Environment Setup
1. Create a `.env` file in the root directory:
```bash
cp .env.example .env
```
2. Configure your model in the `.env` file:
```bash
# Model Configuration
NUXT_PUBLIC_LLAMA_MODEL="deepseek-r1:1.5b"
LLAMA_MODEL="deepseek-r1:1.5b"
```
Note: Both environment variables should typically use the same model name.
## Docker Setup
1. Clone the repository:
```bash
git clone
cd iLlama
```
2. Start the application using Docker Compose:
```bash
docker compose up -d
```
3. Stop the application using Docker Compose:
```bash
docker compose down
```
The application will be available at `http://localhost:3000`
## Local Development Setup
1. Install dependencies and start dev server:
```bash
pnpm install
pnpm dev
```
2. Install [oLlama](https://ollama.com)
3. Pull and run your desired model:
```bash
ollama run deepseek-r1:1.5b # Replace 'deepseek-r1:1.5b' with your actual model name
```
The development server will be available at `http://localhost:3000`
## Available Models
You can use any model supported by oLlama. Some popular options include:
- deepseek
- codellama
- mistral
- llama2
The model name in your `.env` file must match exactly with the model name from oLlama's library.
For example: `deepseek-r1:1.5b` not just `deepseek`.
Check [oLlama's model library](https://ollama.com/library) for more options.
## Environment Variables
- `NUXT_PUBLIC_LLAMA_MODEL`: Model name used by the frontend
- `LLAMA_MODEL`: Model name for Docker container to pull
Both variables should typically match and use the exact model name from oLlama's library.