Welcome to RDK S100(P) Board repository
2. Install large model dialogue platform
Open WebUI
The large models available in Open WebUI are synchronized with Ollama. Users need to manually pull the large model from Ollama before switching to the corresponding model.
Open WebUI1. Environment Requirements2. Docker Setup2.1 Installing Docker from the Official Website2.2 Installing Docker on Alibaba Cloud2.3 Add Access Permissions2.4 Compatibility Modification3. Installing Open WebUI4. Running Open WebUI4.1 Administrator Account4.2 Registration and Login4.3 User Interface5 Model Dialogue5.1 Switching Models5.2 Demo Model: minicpm-v:8b6. Frequently Asked Questions6.1 Disabling Open WebUI6.2 Common ErrorsUnable to start Open WebUIService Connection Timeout6.3 Insufficient Memory ErrorWhen using a model with a large data volume to generate queries, the following error occurs:
Demo Environment
Development Board: RDK S100(P) Development Board
Open WebUI is an open-source project designed to provide a simple and easy-to-use user interface (UI) for managing and monitoring open-source software and services.
xxxxxxxxxxWhen using Open WebUI, there is a high probability of encountering unresponsive dialogues or timeouts. Try restarting Open WebUI or using the Ollama tool to run the model!
1. Environment Requirements
Installing Open WebUI on the host machine and Conda: Requires Node.js >= 20.10, Python = 3.11:
| Environment Setup Method | Difficulty (relatively speaking) |
|---|---|
| Host | High |
| Conda | Medium |
| Docker | Low |
This tutorial demonstrates installing Open WebUI using Docker.
2. Docker Setup
2.1 Installing Docker from the Official Website
If Docker is not installed, you can use a script to install it with one click.
xxxxxxxxxxDomestic users may not be able to install Docker through the official methods. We recommend using Alibaba Cloud to install Docker or directly using our image.
- Update local package list
xxxxxxxxxxsudo apt update
- Upgrade installed packages
xxxxxxxxxxsudo apt upgrade
- Download and run script Download the get-docker.sh file and save it in the current directory.
xxxxxxxxxxsudo apt install curlcurl -fsSL https://get.docker.com -o get-docker.sh
Run the get-docker.sh script file with sudo privileges.
xxxxxxxxxxsudo sh get-docker.sh
2.2 Installing Docker on Alibaba Cloud
If you cannot install it yourself, please use the image we provide.
-Update local package list
xxxxxxxxxxsudo apt update
- Install essential software
xxxxxxxxxxsudo apt install apt-transport-https ca-certificates curl gnupg2 lsb-release software-properties-common
- Add GPG key for software repository
xxxxxxxxxxcurl -fsSL https://mirrors.aliyun.com/docker-ce/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
- Add Alibaba Cloud mirror software repository
xxxxxxxxxxecho "deb [arch=arm64 signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://mirrors.aliyun.com/docker-ce/linux/ubuntu bionic stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
- Install Docker
xxxxxxxxxxsudo apt updatesudo apt install docker-ce docker-ce-cli containerd.io docker-compose-plugin
2.3 Add Access Permissions
Add access permissions for the current system user to the Docker daemon: Docker commands can be used without using the sudo command
xxxxxxxxxxsudo usermod -aG docker $USERnewgrp docker
2.4 Compatibility Modification
After successful installation, starting Docker may fail:

This issue stems from a compatibility conflict between Linux network stack architecture updates and Docker's network implementation. This error typically occurs on newer Linux distributions that default to the nf_tables backend, which Docker may have compatibility issues with. Therefore, switching to legacy mode (using iptables-legacy) can resolve most such issues.
- Switch to legacy iptables
xxxxxxxxxxsudo update-alternatives --set iptables /usr/sbin/iptables-legacysudo update-alternatives --set ip6tables /usr/sbin/ip6tables-legacy
- Check the current iptables mode
xxxxxxxxxxsudo iptables --version# It should display "legacy" instead of "nf_tables"
- Clean up iptables rules
xxxxxxxxxxsudo iptables -t nat -Fsudo iptables -t nat -Xsudo iptables -Fsudo iptables -X
- Restart Docker
xxxxxxxxxxsudo systemctl restart docker
- Check if the Docker service is running successfully
xxxxxxxxxxsudo systemctl status Docker

3. Installing Open WebUI
For systems with Docker already installed, you can directly enter the following command in the terminal: The image shows the result after pulling.
xxxxxxxxxxdocker pull ghcr.io/open-webui/open-webui:main

4. Running Open WebUI
Enter the following command in the terminal to start the specified Docker container:
xxxxxxxxxxdocker run --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main

After successful startup, access it in your browser using the following URL:
xxxxxxxxxxhttp://localhost:8080/

Access can be made via the motherboard IP:8080 on the same local area network:
xxxxxxxxxxAssuming the motherboard IP:192.168.2.105, we can access it via 192.168.2.105:8080
This method is recommended because when accessing the site locally on the motherboard, the browser requires some memory. If you then try to run a 7B or 8B model, it will prompt an insufficient memory error and fail to run.
4.1 Administrator Account
First-time users need to register an account. This account is the administrator account. You can fill in the required information yourself!
xxxxxxxxxxSince all content in our mirror has been set up and tested, users can log in directly using their registered account:Username: yahboomEmail: yahboom@163.comPassword: yahboom
4.2 Registration and Login

4.3 User Interface

5 Model Dialogue
Using the Open WebUI for dialogue will be slower than using the Ollam tool directly, and may even result in timeouts and connection failures. This is related to the Jetson motherboard's memory and is unavoidable!
xxxxxxxxxxUsers interested can switch to other Linux environments to set up the Ollam and Open WebUI tools for interaction.
5.1 Switching Models
Clicking Select a model in the upper left corner allows you to select a specific model for interaction.
xxxxxxxxxxModels retrieved using Ollam are automatically added to the Open WebUI model options. Refreshing the webpage will display the new model!

5.2 Demo Model: minicpm-v:8b
xxxxxxxxxxWhat do you see in this picture?

6. Frequently Asked Questions
6.1 Disabling Open WebUI
Disable the automatically starting Open WebUI.
- View running Docker containers
xxxxxxxxxxdocker ps
- Shut down running Docker containers
xxxxxxxxxxdocker stop [CONTAINER ID] # Example docker stop 5f42ee9cf784
- View stopped containers
xxxxxxxxxxdocker ps -a
- Clean up stopped containers
xxxxxxxxxxdocker rm [CONTAINER ID] # Example docker rm 5f42ee9cf784
Clean up all stopped containers:
xxxxxxxxxxdocker container prune
6.2 Common Errors
Unable to start Open WebUI
- docker: Error response from daemon: Conflict. The container name "/open-webui" is already in use by container "cfc05c84f8e38b290337e7178c76fd1c49076f94b11ed3d49d9448be72b7f20f". You have to remove (or rename) that container to reuse that name.
Solution: Close and restart Open WebUI!
Service Connection Timeout
- Open WebUI: Server Connection Error
Close and restart Open WebUI, then try asking the question again, or use the Ollam tool to run the model and ask the question!
6.3 Insufficient Memory Error
When using a model with a large data volume to generate queries, the following error occurs:
- 500: model requires more system memory (6.6 GiB) than is available (5.2 GiB)
- It is recommended to use a computer browser accessing the motherboard via IP:8080. Accessing the model locally on the motherboard requires some memory, and running a 7B or 8B model under these conditions will result in an insufficient memory error and the model will fail to run.
- Running Open WebUI also consumes some memory, which may prevent some larger models from running, such as Ollama_Instead of running it directly, consider pulling a larger model with a smaller dataset, or migrating it to Ollama to run the larger model.
- Increase swap space content.
xxxxxxxxxx# Create a 4GB swap filesudo fallocate -l 4G /swapfilesudo chmod 600 /swapfilesudo mkswap /swapfilesudo swapon /swapfile