LazAI API

One-step access to private data AI process, user can utilize privacy data on the LazAI for context engineering/inference/training/evaluation to build value-aligned agents. After contributing your private data and minting a DAT (Data Anchor Token), you can run AI inference on your data in a privacy-preserving way using LazAI. This workflow ensures your sensitive data remains secure and under your control, while still enabling powerful AI capabilities.

Why Private Data Inference?

In many industries—such as healthcare, finance, and research—data privacy is critical. Traditional AI services often require uploading your data to third-party servers, risking exposure. LazAI enables you to run AI models on your own data without ever giving up control, leveraging secure computation and cryptographic settlement.

Workflow Overview

Contribute Data: Complete the Data Contribution workflow and obtain your File ID after minting DAT.
Setup Inference Server: Deploy an inference server using the Running Inference Server guide.
Request Inference: Use the LazAI client to send an inference request, referencing your File ID and providing settlement headers for secure access.

Making Inference Queries

Python

Prerequisites

Before making inference queries, ensure you have:

Completed Data Contribution: You have contributed your private data and received a File ID
Inference Server Running: An inference server is deployed and registered with LazAI
Wallet Setup: A Web3 wallet with private key for authentication

Environment Setup

Create Python Virtual Environment

To avoid dependency conflicts and keep your environment clean, create and activate a Python virtual environment:


python3 -m venv venv
source venv/bin/activate

Install Alith


python3 -m pip install alith -U

Set Environment Variables


export PRIVATE_KEY=<your wallet private key>

Making Inference Queries


from alith import Agent, LazAIClient
 
# 1. Join the iDAO, register user wallet on LazAI and deposit fees (Only Once)
LAZAI_IDAO_ADDRESS = "0xc3e98E8A9aACFc9ff7578C2F3BA48CA4477Ecf49" 
client = LazAIClient()
 
DEPOSIT_AMOUNT = 10000000  
 
 
 
try:
    address = client.get_user(client.wallet.address)
    print("User already exists", address)
 
except Exception:
    print("User does not exist, adding user")
    try:
        client.add_user(DEPOSIT_AMOUNT)
        client.deposit_inference(LAZAI_IDAO_ADDRESS, DEPOSIT_AMOUNT)
        print(f"Successfully added user and deposited {DEPOSIT_AMOUNT}")
    except Exception as e:
        print("Error adding user or depositing:", e)
 
 
# 2. Request the inference server with the settlement headers and DAT file id
file_id = 10  # Use the File ID you received from the Data Contribution step
url = client.get_inference_node(LAZAI_IDAO_ADDRESS)[1]
print("url", url)
 
# Check if the user has an account with the inference node
try:
    account = client.get_inference_account(client.wallet.address, LAZAI_IDAO_ADDRESS)
    print("Inference account:", account)
    if not account or account[0] != client.wallet.address:
        print("Warning: User account not found with inference node. This may cause authentication errors.")
except Exception as e:
    print("Error checking inference account:", e)
 
agent = Agent(
    # Note: replace with your model here
    model="deepseek/deepseek-r1-0528",
    base_url=f"{url}/v1",
    # Extra headers for settlement and DAT file anchoring
    extra_headers=client.get_request_headers(LAZAI_IDAO_ADDRESS, file_id=file_id),
)
print(agent.prompt("summarize it"))

Node.js

Project Setup


mkdir lazai-inference
cd lazai-inference
npm init -y

Install Alith


npm i alith@latest

Create TypeScript Configuration

Create a file named tsconfig.json with the following content:


{
  "compilerOptions": {
    "target": "ES2022",
    "module": "ESNext",
    "moduleResolution": "bundler",
    "allowSyntheticDefaultImports": true,
    "esModuleInterop": true,
    "allowJs": true,
    "strict": true,
    "skipLibCheck": true,
    "forceConsistentCasingInFileNames": true,
    "resolveJsonModule": true,
    "isolatedModules": true,
    "noEmit": true
  },
  "ts-node": {
    "esm": true
  },
  "include": ["*.ts"],
  "exclude": ["node_modules"]
}

Set Environment Variables


export PRIVATE_KEY=<your wallet private key>

Step 1: Request Inference via LazAI Client

Create a file named app.ts with the following content:


import { ChainConfig, Client } from "alith/lazai";
import { Agent } from "alith";
 
// Set up the private key for authentication
process.env.PRIVATE_KEY = "<your wallet private key>";
 
const node = "0xc3e98E8A9aACFc9ff7578C2F3BA48CA4477Ecf49"; // Replace with your own inference node address
const client = new Client(ChainConfig.testnet());
 
await client.getUser(client.getWallet().address);
 
console.log(
  "The inference account of user is",
  await client.getInferenceAccount(client.getWallet().address, node)
);
 
const fileId = 10;
const nodeInfo = await client.getInferenceNode(node);
const url = nodeInfo.url;
const agent = new Agent({
  // OpenAI-compatible inference server URL
  baseUrl: `${url}/v1`,
  model: "deepseek/deepseek-r1-0528",
  // Extra headers for settlement and DAT file anchoring
  extraHeaders: await client.getRequestHeaders(node, BigInt(fileId)),
});
console.log(await agent.prompt("What is Alith?"));

Step 2: Run the Application


npx tsx app.ts

Security & Privacy

Your data never leaves your control. Inference is performed in a privacy-preserving environment, using cryptographic settlement and secure computation.
Settlement headers ensure only authorized users and nodes can access your data for inference.
File ID links your inference request to the specific data you contributed, maintaining a verifiable chain of custody.

LazAI API

Workflow Overview

Making Inference Queries

Python

Prerequisites

Environment Setup

Create Python Virtual Environment

Install Alith

Set Environment Variables

Making Inference Queries

Node.js

Project Setup

Install Alith

Create TypeScript Configuration

Set Environment Variables

Step 1: Request Inference via LazAI Client

Step 2: Run the Application

Rust

Coming Soon

Security & Privacy

See Also