Usage

Once you have a zylAI API key, you can start using SecretLLM with any OpenAI-compatible library.

Getting Started with SecretLLM​

Getting started with SecretLLM is straightforward:

1. Select a zylAI node url

2. Query the /v1/models endpoint or check available models

3. Select an available model and use it with the /v1/chat/completions zylAI node endpoint

Since SecretLLM is OpenAI-compatible, you can use any OpenAI library. Here's an example for querying the Llama-3.1-8B model:

• Node.js

• Python

• Next JS (API routes)

zylai/secretllm_nodejs/index.js

const OpenAI = require('openai');
require('dotenv').config();

// Initialize the OpenAI client
// baseURL is the zylAI node url: https://docs.zyllion.com/network#zylai-nodes
// apiKey is your zylAI node api key: https://docs.zyllion.com/build/secretLLM/access
const client = new OpenAI({
  baseURL: 'https://zylai-a779.zyllion.network/v1',
  apiKey: process.env.ZYLAI_API_KEY || 'YOUR_API_KEY_HERE'
});

async function generateText() {
  try {
    const response = await client.chat.completions.create({
      model: 'meta-llama/Llama-3.1-8B-Instruct',
      messages: [
        {
          role: 'system',
          content: 'You are a fitness coach.'
        },
        {
          role: 'user',
          content: 'What is better for you, salad or pizza?'
        }
      ],
      stream: false
    });

    // Every SecretLLM response includes a cryptographic signature for verification
    console.log(`Signature: ${response.signature}`);
    console.log(`Response: ${response.choices[0].message.content}`);
  } catch (error) {
    console.error('Error:', error);
  }
}

generateText();