# OpenWebUI Configuration Guide

This guide explains how to configure OpenWebUI to use your AI service as its backend.

## Overview

Your AI service now implements the necessary API endpoints to be compatible with OpenWebUI. This allows OpenWebUI to use your AI service as its backend instead of connecting directly to Ollama.

## Configuration Steps

### 1. Update OpenWebUI Environment Variables

You need to modify the OpenWebUI environment variables to point to your AI service. This can be done by editing the `.env` file in the OpenWebUI installation directory or by setting environment variables when running the OpenWebUI container.

Add or modify the following environment variables:

```
OLLAMA_API_BASE_URL=http://your-server-ip:5251/ollama
OPENAI_API_BASE_URL=http://your-server-ip:5251/api
```

Replace `your-server-ip` with the IP address or hostname of the server where your AI service is running.

### 2. Restart OpenWebUI

After updating the environment variables, restart the OpenWebUI service to apply the changes.

If you're running OpenWebUI using Docker:

```bash
docker restart openwebui
```

If you're running OpenWebUI directly:

```bash
# Stop the current process
pkill -f "openwebui"

# Start OpenWebUI again
cd /path/to/openwebui
npm start
```

## Testing the Integration

To test if the integration is working correctly:

1. Open OpenWebUI in your browser (http://104.225.217.215:8080)
2. Try to create a new chat
3. Select one of the models (gemma3, llama3.3, llama3.1, mistral, or deepseek)
4. Send a message and check if you get a response

If everything is configured correctly, OpenWebUI will send requests to your AI service, which will then forward them to the Ollama API.

## Troubleshooting

If you encounter issues with the integration:

1. Check the logs of your AI service:
   ```bash
   tail -f logs/ai_service.log
   ```

2. Check the logs of OpenWebUI:
   ```bash
   docker logs openwebui
   ```

3. Verify that your AI service is running and accessible:
   ```bash
   curl http://your-server-ip:5251/health
   ```

4. Verify that the OpenWebUI environment variables are set correctly:
   ```bash
   docker exec openwebui env | grep URL
   ```

## Advanced Configuration

For advanced configuration options, refer to the OpenWebUI documentation:
https://docs.openwebui.com/getting-started/env-configuration