ZhipuAI Open Platform Node.js SDK

中文文档

The official Node.js SDK for ZhipuAI Open Platform Big Model API, enabling developers to easily integrate ZhipuAI's powerful AI capabilities into their Node.js applications.

✨ Features

• 🚀 Type-safe API: Complete TypeScript type definitions for excellent development experience
• 🔧 Easy Integration: Simple and intuitive API design for quick integration
• ⚡ High Performance: Built with modern Node.js libraries for optimal performance
• 🛡️ Secure: Built-in authentication and token management
• 📦 Lightweight: Minimal dependencies for easy project integration
• 🌊 Streaming Support: Full support for streaming response handling

📦 Installation

Requirements

• Node.js 14 or higher
• npm, yarn, or pnpm

npm

npm install zhipuai-sdk-nodejs-v4

yarn

yarn add zhipuai-sdk-nodejs-v4

pnpm

pnpm add zhipuai-sdk-nodejs-v4

📋 Dependencies

This SDK uses the following core dependencies:

Library	Version
axios	^1.6.7
jsonwebtoken	^9.0.2

🚀 Quick Start

Basic Usage

1. Create a Client with your API key
2. Call the desired API methods

Client Configuration

import { ZhipuAI } from 'zhipuai-sdk-nodejs-v4';

// Use API key from environment variable
const ai = new ZhipuAI();

// Or pass API key directly
const ai = new ZhipuAI({
    apiKey: 'your_api_key_here',
    baseUrl: 'https://open.bigmodel.cn/api/paas/v4', // Optional, default value
    timeout: 30000, // Optional, request timeout
    cacheToken: true // Optional, whether to cache token
});

💡 Examples

Chat Model Invocation

Synchronous Invocation

• Basic Chat

import { ZhipuAI } from 'zhipuai-sdk-nodejs-v4';

const dialogue = async () => {
    const ai = new ZhipuAI();
    const result = await ai.createCompletions({
        model: "glm-4",
        messages: [
            {"role": "user", "content": "What is the relationship between ZhipuAI and ChatGLM?"}
        ],
        stream: false
    });
    console.log(result);
};

dialogue();

Streaming Invocation (SSE)

• Basic Chat

import { ZhipuAI } from 'zhipuai-sdk-nodejs-v4';

const streamDialogue = async () => {
    const ai = new ZhipuAI();
    const stream = await ai.createCompletions({
        model: "glm-4",
        messages: [
            {"role": "user", "content": "What is the relationship between ZhipuAI and ChatGLM?"}
        ],
        stream: true
    });
    
    // Process streaming results
    for await (const chunk of stream) {
        console.log(chunk.toString());
    }
};

streamDialogue();

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

📞 Support

• 📖 Documentation: ZhipuAI Open Platform
• 🐛 Issues: GitHub Issues
• 💬 Community: ZhipuAI Developer Community

---

Note: This SDK is currently in active development. If you encounter any bugs or need additional features, please submit an issue.