Skip to content
Provider Protocol Provider Protocol

Quick Start

Quick Start

Section titled “Quick Start”

Get up and running with the Unified Provider Protocol in minutes.

Installation

Section titled “Installation”
Terminal window
npm install @providerprotocol/ai

Your First LLM Call

Section titled “Your First LLM Call”

  1. Import the library and a provider

    import { llm } from '@providerprotocol/ai';
    import { anthropic } from '@providerprotocol/ai/anthropic';

  2. Create an LLM instance

    const claude = llm({
      model: anthropic('claude-sonnet-4-20250514'),
      system: 'You are a helpful assistant.',
    });

  3. Generate a response

    const turn = await claude.generate('What is the capital of France?');
    console.log(turn.response.text);
    // "The capital of France is Paris."

Streaming Responses

Section titled “Streaming Responses”

Stream tokens as they arrive:

const stream = claude.stream('Write a haiku about coding.');


for await (const event of stream) {
  if (event.type === 'text_delta') {
    process.stdout.write(event.delta.text ?? '');
  }
}


// Get the complete turn after streaming
const turn = await stream.turn;

Multi-Turn Conversations

Section titled “Multi-Turn Conversations”

Maintain conversation history:

import { Message } from '@providerprotocol/ai';


const history: Message[] = [];


// First turn
const turn1 = await claude.generate(history, 'My name is Alice.');
history.push(...turn1.messages);


// Second turn - model remembers context
const turn2 = await claude.generate(history, 'What is my name?');
history.push(...turn2.messages);


console.log(turn2.response.text);
// "Your name is Alice."

Using Different Providers

Section titled “Using Different Providers”

Switch providers by changing the import:

import { llm } from '@providerprotocol/ai';
import { openai } from '@providerprotocol/ai/openai';
import { google } from '@providerprotocol/ai/google';
import { anthropic } from '@providerprotocol/ai/anthropic';


// OpenAI
const gpt = llm({ model: openai('gpt-4o') });


// Google
const gemini = llm({ model: google('gemini-2.0-flash') });


// Anthropic
const claude = llm({ model: anthropic('claude-sonnet-4-20250514') });

Embeddings

Section titled “Embeddings”

Generate vector embeddings:

import { embedding } from '@providerprotocol/ai';
import { openai } from '@providerprotocol/ai/openai';


const embedder = embedding({
  model: openai('text-embedding-3-small'),
});


const result = await embedder.embed('Hello, world!');
console.log(result.vector.length); // 1536

Image Generation

Section titled “Image Generation”

Generate images from text:

import { image } from '@providerprotocol/ai';
import { openai } from '@providerprotocol/ai/openai';


const dalle = image({
  model: openai('dall-e-3'),
  params: { size: '1024x1024' },
});


const result = await dalle.generate('A sunset over mountains');
const imageData = result.images[0].image.toBytes();

Next Steps

Section titled “Next Steps”