doc: troubleshooting update

This commit is contained in:
Timothy J. Baek 2023-12-29 09:29:12 -08:00
parent 36d2a589d2
commit ec87a5e795

View file

@ -1,30 +1,32 @@
# Ollama Web UI Troubleshooting Guide
## Understanding the Ollama WebUI Architecture
The Ollama WebUI system is designed to streamline interactions between the client (your browser) and the Ollama API. At the heart of this design is a backend reverse proxy, enhancing security and resolving CORS issues.
- **How it Works**: When you make a request (like `/ollama/api/tags`) from the Ollama WebUI, it doesnt go directly to the Ollama API. Instead, it first reaches the Ollama WebUI backend. The backend then forwards this request to the Ollama API via the route you define in the `OLLAMA_API_BASE_URL` environment variable. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend.
- **Security Benefits**: This design prevents direct exposure of the Ollama API to the frontend, safeguarding against potential CORS (Cross-Origin Resource Sharing) issues and unauthorized access. Requiring authentication to access the Ollama API further enhances this security layer.
## Ollama WebUI: Server Connection Error
If you're running ollama-webui and have chosen to install webui and ollama separately, you might encounter connection issues. This is often due to the docker container being unable to reach the Ollama server at 127.0.0.1:11434(host.docker.internal:11434). To resolve this, you can use the `--network=host` flag in the docker command. When done so port would be changed from 3000 to 8080, and the link would be: http://localhost:8080.
If you're experiencing connection issues, its often due to the WebUI docker container not being able to reach the Ollama server at 127.0.0.1:11434 (host.docker.internal:11434) inside the container . Use the `--network=host` flag in your docker command to resolve this. Note that the port changes from 3000 to 8080, resulting in the link: `http://localhost:8080`.
Here's an example of the command you should run:
**Example Docker Command**:
```bash
docker run -d --network=host -v ollama-webui:/app/backend/data -e OLLAMA_API_BASE_URL=http://127.0.0.1:11434/api --name ollama-webui --restart always ghcr.io/ollama-webui/ollama-webui:main
```
## Connection Errors
### General Connection Errors
Make sure you have the **latest version of Ollama** installed before proceeding with the installation. You can find the latest version of Ollama at [https://ollama.ai/](https://ollama.ai/).
**Ensure Ollama Version is Up-to-Date**: Always start by checking that you have the latest version of Ollama. Visit [Ollama's official site](https://ollama.ai/) for the latest updates.
If you encounter difficulties connecting to the Ollama server, please follow these steps to diagnose and resolve the issue:
**Troubleshooting Steps**:
**1. Check Ollama URL Format**
1. **Verify Ollama URL Format**:
- When running the Web UI container, ensure the `OLLAMA_API_BASE_URL` is correctly set, including the `/api` suffix. (e.g., `http://192.168.1.1:11434/api` for different host setups).
- In the Ollama WebUI, navigate to "Settings" > "General".
- Confirm that the Ollama Server URL is correctly set to `/ollama/api`, including the `/api` suffix.
Ensure that the Ollama URL is correctly formatted in the application settings. Follow these steps:
- If your Ollama runs in a different host than Web UI make sure Ollama host address is provided when running Web UI container via `OLLAMA_API_BASE_URL` environment variable. [(e.g. OLLAMA_API_BASE_URL=http://192.168.1.1:11434/api)](https://github.com/ollama-webui/ollama-webui#accessing-external-ollama-on-a-different-server)
- Go to "Settings" within the Ollama WebUI.
- Navigate to the "General" section.
- Verify that the Ollama Server URL is set to: `/ollama/api`.
It is crucial to include the `/api` at the end of the URL to ensure that the Ollama Web UI can communicate with the server.
By following these troubleshooting steps, you should be able to identify and resolve connection issues with your Ollama server configuration. If you require further assistance or have additional questions, please don't hesitate to reach out or refer to our documentation for comprehensive guidance.
By following these enhanced troubleshooting steps, connection issues should be effectively resolved. For further assistance or queries, feel free to reach out to us on our community Discord.