WebInfer

Quick Start

Make your first AI request with WebInfer in 5 minutes

Your First AI Request

This guide will walk you through making your first AI request with WebInfer.

Prerequisites

  • Node.js 18+ installed
  • WebInfer extension installed (or daemon running)
  • At least one provider configured (API key or local model)

Step 1: Install WebInfer

terminal
npm install webinfer

Step 2: Import and Use

Create a new file called app.js:

app.js
import { generateText } from 'webinfer'// Simple text generationconst result = await generateText({  prompt: 'Write a haiku about programming'})console.log(result.text)

Run it:

terminal
node app.js

That's it! You've made your first AI request with WebInfer.

Understanding the Response

The generateText function returns a response object with:

response.ts
{  text: string              // The generated text  model: string            // Which model was used  provider: string         // Which provider executed it  usage: {    inputTokens: number    outputTokens: number    totalTokens: number  }  metadata: {    latency: number        // Response time in ms    cost?: number          // Estimated cost in USD  }}

Step 3: Different Use Cases

Use generateText for various AI tasks:

tasks.js
// Summarizationconst summary = await generateText({  prompt: 'Summarize the following article: [your long text here]'})console.log(summary.text)// Coding taskconst code = await generateText({  prompt: 'Write a React component for a todo list in TypeScript'})console.log(code.text)// Creative writingconst story = await generateText({  prompt: 'Write a short story about a robot'})console.log(story.text)

Step 4: Streaming Responses

For real-time text generation:

streaming.js
import { streamText } from 'webinfer'const stream = await streamText({  prompt: 'Write a long story about space exploration'})for await (const chunk of stream) {  process.stdout.write(chunk)}

Next Steps

Now that you've made your first request, explore more features: