https://github.com/battlefieldduck/deepseek-webui-docker
Easily deploy DeepSeek-R1 and Open WebUI locally using docker-compose.yml. Quickly experience DeepSeek-R1 firsthand!
https://github.com/battlefieldduck/deepseek-webui-docker
deepseek deepseek-chat deepseek-r1 docker docker-compose open-webui
Last synced: about 1 month ago
JSON representation
Easily deploy DeepSeek-R1 and Open WebUI locally using docker-compose.yml. Quickly experience DeepSeek-R1 firsthand!
- Host: GitHub
- URL: https://github.com/battlefieldduck/deepseek-webui-docker
- Owner: BattlefieldDuck
- License: mit
- Created: 2025-01-29T18:31:20.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2025-01-29T23:21:59.000Z (4 months ago)
- Last Synced: 2025-04-11T20:47:51.477Z (about 1 month ago)
- Topics: deepseek, deepseek-chat, deepseek-r1, docker, docker-compose, open-webui
- Homepage: https://www.youtube.com/watch?v=qY-G8fysmxA
- Size: 7.81 KB
- Stars: 3
- Watchers: 1
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# deepseek-webui-docker
This repository contains the necessary configuration to deploy DeepSeek-R1 and Open WebUI locally using Docker Compose.
## Getting Started
Follow these instructions to get your deployment up and running.
### Prerequisites
Make sure you have Docker and Docker Compose installed on your machine.
- [Docker](https://docs.docker.com/get-docker/)
- [Docker Compose](https://docs.docker.com/compose/install/)### Installation
1. **Clone this repository:**
```bash
git clone https://github.com/BattlefieldDuck/deepseek-webui-docker.git
cd deepseek-webui-docker
```2. **Build and run the services:**
```bash
docker compose up -d
```
### Accessing the Web Interface
1. **Open your browser** and go to `http://localhost:3000` to access the Open WebUI interface.

### Registering an Account
1. **Register a local account** on the Open WebUI.
### Downloading the DeepSeek Model
1. Go to `http://localhost:3000/admin/settings`.
2. Navigate to the **Models** tab.
3. Click **Manage Models**.
4. Enter the model tab and type:```shell
deepseek-r1:1.5b
```You can find the list of available DeepSeek-R1 models [here](https://ollama.com/library/deepseek-r1).

Start chatting!

### Stopping the Services
To stop the services, run:
```bash
docker compose down
```## Configuration
The `docker-compose.yml` file in this repository includes the following configurations:
```yaml
services:
open-webui:
image: ghcr.io/open-webui/open-webui:ollama
container_name: open-webui
ports:
- "3000:8080"
volumes:
- ollama:/root/.ollama
- open-webui:/app/backend/data
restart: unless-stopped
# Uncomment the following block if your system has NVIDIA GPUs
# and you want to leverage GPU acceleration
#
# deploy:
# resources:
# reservations:
# devices:
# - driver: nvidia
# count: all
# capabilities: [ gpu ]volumes:
ollama:
open-webui:
```## Notes
- Ensure that your system's GPU is compatible with NVIDIA drivers, as specified in the `docker-compose.yml` file.
- Modify the `docker-compose.yml` file as needed to fit your specific configuration.
- Check the list of available DeepSeek-R1 models [here](https://ollama.com/library/deepseek-r1).## Contributing
Feel free to open issues or submit pull requests if you want to contribute.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.