Skip to main content

Cloud Hosting Development and Deployment

CloudBase AI ToolKit has built-in support for cloud hosting development and deployment features. Cloud hosting enables you to easily deploy and run various backend services, supporting scenarios such as persistent connections, file uploads, and multi-language environments. This plugin is enabled by default—you simply need to tell the AI what you want to accomplish using natural language.

New Feature: AI Agent Development​

Now supports developing AI Agents based on Function-based Cloud Hosting, enabling you to quickly create and deploy personalized AI applications.

When to Use Cloud Hosting​

When you need to:

  • Real-time Communication: WebSocket, SSE, Streaming Responses
  • Long-running Tasks: Background Processing
  • Multi-language: Java, Go, PHP, Python, Node.js, etc.
  • AI Agent: Personalized AI Application Development

How to Choose Between Two Modes​

Function-based: Recommended for beginners, supports Node.js, includes built-in WebSocket support, can be debugged locally with a fixed port 3000.

Container-based: Suitable for existing projects, supports any language, requires providing a Dockerfile.

Quick Start​

1. Check Available Templates​

List available cloud hosting templates

2. Create a New Project​

Create a project named my-service using the helloworld template

3. Run Locally (Function-based)​

Run my-service locally on port 3000

4. Deploy to the Cloud​

Deploy my-service, enable public network access, with 0.5 CPU cores and 1GB memory

5. Create an AI Agent​

Create an agent named my-agent for customer service dialogues

Common Scenarios​

Mini Program Backend​

Create a function-based service supporting WebSocket for the chat feature of Mini Programs

Java Spring Boot Application​

Deploy a Spring Boot application to provide REST API services

Go Microservices​

Create a high-performance microservice in Go to handle user authentication

Python Data Processing​

Deploy a Python service to periodically process data and generate reports

PHP Laravel Application​

Deploy a Laravel application to provide comprehensive web-based backend management.

AI Agent Applications​

Create an agent to handle user inquiries and provide personalized services

Access to Your Service​

After the deployment is complete, you can access it through the following methods:

Direct Invocation from Mini Program (Recommended):

const res = await wx.cloud.callContainer({
  config: { env: "your-env-id" },
  path: "/api/data",
  method: "POST",
  header: { "X-WX-SERVICE": "my-service" }
});

Web Application:

import cloudbase from "@cloudbase/js-sdk";
const app = cloudbase.init({ env: "your-env-id" });
const res = await app.callContainer({
  name: "my-service",
  method: "GET",
  path: "/health"
});

Direct HTTP Access:

curl https://your-service-domain.com

AI Agent Development​

Create an Agent​

Create an agent named customer-service for customer service dialogues

Running Agents Locally​

Run the customer-service agent locally on port 3000

Invoke Agents​

// Invoking Web Applications
const app = cloudbase.init({ env: "your-env-id" });
const ai = app.ai();
const res = await ai.bot.sendMessage({
  botId: "ibot-customer-service-demo",
  msg: "msg: "Hello, I need help."
});
for await (let x of res.textStream) {
  console.log(x);
}
# Command Line Testing
curl 'http://127.0.0.1:3000/v1/aibot/bots/ibot-customer-service-demo/send-message' \
  -H 'Accept: text/event-stream' \
  -H 'Content-Type: application/json' \
  --data-raw '{"msg":"Hello"}'