Open WebUI Integration with Token Circle Complete Tutorial: Build Your AI Chat Platform

```html

Open WebUI is one of the most popular open-source AI chat interfaces, supporting any OpenAI-compatible API service. This article will guide you step by step on how to connect Ciyuan Circle to Open WebUI and build your own AI chat platform in 5 minutes.

---

What is Open WebUI

Open WebUI (formerly Ollama WebUI) is an extensible, feature-rich self-hosted web interface designed for interacting with large language models. It is fully compatible with the OpenAI API format, meaning you can directly integrate Ciyuan Circle's API into it and enjoy a fully functional AI chat platform.

Why choose Open WebUI?

• Completely free and open-source: Code hosted on GitHub, active community, continuous updates
• Web access: No client installation required, open in a browser and use, supports mobile access
• Multi-user support: Invite team members to use together, each with independent chat history
• Rich features: File upload, image recognition, conversation templates, web search, and more
• Data self-control: Deployed on your own server, conversation data does not pass through third parties

---

Prerequisites

Before you start, you need to prepare the following:

1. A server or local computer: Recommended 2GB+ RAM, supports Docker or Python
2. Docker installed (recommended): If Docker is not yet installed, refer to the official installation guide
3. Ciyuan Circle account: Register at ciyuano.com/register
4. An API key: Created in the Ciyuan Circle backend

---

Detailed Integration Steps

Step 1: Get Ciyuan Circle API Key

First, you need to create an API key in the Ciyuan Circle backend:

1. Open your browser, visit www.ciyuano.com and log in
2. Go to the backend, click "API Keys" in the left menu
3. Click the "Create New Key" button
4. Add a note name for the key (e.g., "Open WebUI") for easy management later
5. Copy the generated key, format similar to sk-relay-xxxxxxxxxx

Step 2: Deploy Open WebUI

Docker deployment is recommended, can be done with a single command:

Explanation of this command:

• -d: Run container in the background
• -p 3000:8080: Map container's port 8080 to host's port 3000
• -v open-webui:/app/backend/data: Persist data to prevent loss after restart
• --restart always: Automatically start after server reboot

After deployment, open your browser and visit http://your_server_IP:3000. On first visit, you need to register an admin account.

Step 3: Configure API Connection

This is the most critical step: connect Open WebUI to Ciyuan Circle's API:

1. After logging into Open WebUI, click the avatar or settings icon in the bottom left corner
2. Go to the "Settings" page
3. Find the "Connections" tab
4. In the OpenAI API configuration area:
   • API Base URL fill in: https://www.ciyuano.com/v1
   • API Key fill in: your Ciyuan Circle key (sk-relay-xxx)
5. Click "Save"

Step 4: Select a Model and Start Chatting

After configuration, you can use all models from Ciyuan Circle in Open WebUI:

1. At the top of the chat page, click the model selection dropdown
2. You will see all available models provided by Ciyuan Circle, such as DeepSeek V4, Qwen 3, MiMo v2.5, etc.
3. Select a model, type your question, and start chatting

You can switch models at any time during a conversation to compare responses.

---

Advanced Configuration Suggestions

Set Default Model

If you frequently use a certain model, you can set it as default in Settings: go to Settings → General → Default Model, and choose your preferred model. This way, it will be automatically selected for each new conversation.

Custom System Prompt

Open WebUI supports setting a system prompt for each conversation, allowing the AI to work the way you want. You can:

• Add custom system prompts in the conversation settings
• Create "Prompt Presets" to switch between different AI roles with one click
• For example: translation assistant, code reviewer, copywriter, etc.

Multi-user Management

If you use Open WebUI in a team, the administrator can:

• Enable or disable new user registration
• Assign different model permissions to different users
• View usage statistics of all users

---

Common Troubleshooting

Issue	Solution
Model list is empty	Check that the API Base URL is correctly filled, must end with /v1
Prompt says API key is invalid	Confirm the key is correctly copied with no extra spaces; check if the key has expired or been disabled
Docker container unreachable	Check if firewall allows port 3000; cloud servers need to open it in security groups
Response speed is very slow	The model may be under high load; try switching to another model, or check your server's network quality
Error after uploading a file	Ensure the model you are using supports file input (e.g., DeepSeek V4, GPT-4o, etc.)

---

Comparison with Other Clients

If you are still deciding which AI client to choose, here is a simple comparison:

Feature	Open WebUI	Cherry Studio	LobeChat
Deployment method	Self-hosted Web	Desktop client	Self-hosted/Cloud
Multi-user	Native support	Not supported	Supported
Mobile access	Supported	Not supported	Supported
File upload	Supported	Supported	Supported
Best suited for	Team collaboration, self-hosted	Personal use, desktop	Personal/small team

---

Summary

Open WebUI is a powerful, easy-to-deploy AI chat interface. Paired with Ciyuan Circle's API relay service, you can:

• Use multiple models like DeepSeek, Qwen, MiMo, GPT, etc. from a single interface
• Invite team members to use together, each managing their own conversations independently
• Access from mobile, tablet, or computer anytime
• Have complete control over your data

```