Use the DeepSeek model to quickly build a conversational AI site
This document describes how to leverage Edge AI DeepSeek model combined with our Pages' "AI Chat Template," enabling developers to build a dialogue-based AI website in just 1 minute. You can also explore more play modes—adding an AI assistant to a tech blog, creating a knowledge library search prototype for your team, and experiencing the millisecond-level response of Edge AI at zero cost.
The following video demonstrates the deployment steps and how to use the Template.
Overview
The platform offers free access to edge deployment of DeepSeek series models, combining with EdgeOne Pages to launch "AI chat Template," providing developers with a low-cost, efficient dialogue AI solution to promote the popularization of Edge AI technology.
Main features and advantages:
Preset DeepSeek series models, no need for complex configuration, just quickly launch
Deploy AI computing power to edge nodes for lower delay and a fast and smooth experience
Visit the demo site https://deepseek-r1-edge.edgeone.app to experience the ultimate speed of Edge AI, or log in to the EdgeOne Pages console for one-click deployment of your exclusive AI application.
Scenarios
Using this Template, developers can quickly verify various application scenarios: building an intelligent customer service system to automatically parse user inquiries and push operation guides, reducing manual processing; creating a SaaS product assistant to support ticket categorization, report interpretation, process configuration, and other scenarios, saving repetitive operation time and achieving deep integration of AI and business.
Operation Steps
1. Creating a Project
Enter the template page, https://pages.edgeone.ai/templates/deepseek-r1-edge, click the "Deploy" button, enter the Pages console, configure the project, and then click "Create now".

2. Deploy
Project creation successful will enter the deployment process. View the deployment procedure on the build deployment details page.

3. Generate a Preview URL
After successful deployment, click the preview button in the project overview to generate a preview URL for quick deployment verification.

4. Sending Questions
Open the preview URL, send any question in the dialog box, and you will see a very quick streaming output response.

This is merely a simple Demo. You can clone the code locally and update the project as you wish, such as adding some modules to enrich product capabilities.
In addition, our service connects edge nodes directly to large models with a fully Serverless architecture AI interface. No API key is required for free invocation.
// In the edge function (example path: /functions/v1/chat/completions/index.js)export async function onRequestPost({ request }) {// Parse user inputconst { content } = await request.json();try {// Call the Edge AI serviceconst response = await AI.chatCompletions({model: '@tx/deepseek-ai/deepseek-v3-0324',messages: [{ role: 'user', content }],stream: true, // Enable streaming output});// Return streaming response// ......} catch (error) {// ......}}
Since the project domain name has a validity period, we recommend that you add a custom domain (such as www.example.com) to use it as a persistent API address.

API calls are compliant with the Open AI API standard, which means you can easily switch between different AI providers and reuse existing code and tools.
The following code shows how to quickly integrate the service into your AI business, implement a multi-AI provider auto failover mechanism, and give your business the service elasticity of multi-protection.
export class AIService {//......constructor(deepseekApiKey: string,siliconFlowApiKey: string,groqApiKey: string,tencentApiKey: string) {// Initialize AI service settingsthis.serviceConfigs = [// Add configuration item{name: 'edgeonepages',baseURL: 'https://www.example.com/v1', // Replace www.example.com with your domain nameenabled: true,priority: 1 // highest priority},{name: 'tencent',baseURL: 'https://api.lkeap.cloud.tencent.com/v1',model: 'deepseek-v3',enabled: true,priority: 2 // second priority},{name: 'deepseek',baseURL: 'https://api.deepseek.com/v1',model: 'deepseek-chat',enabled: true,priority: 3 // third priority}];//......}}
Conclusion
The EdgeOne Pages DeepSeek AI chat Template provides developers with the possibility of deploying AI applications on edge nodes. Although currently in the early stage, it has shown huge potential. We sincerely invite developers to trial this template, experience DeepSeek on edge nodes while also enjoying the convenience and efficiency of Pages. We look forward to your valuable feedback to help us continuously improve the Pages experience.
