LatticaAI Documentation
  • Welcome to LatticaAI
  • Conceptual Guide
  • Architecture Overview
    • Management Client
    • Query Client
  • Platform Workflows
    • Account Management
    • Model Management
    • User Access Management
    • Query Submission
    • Credit Management
    • Worker Management
  • How-To Guides
    • Client Installation
      • How-To: Install Management Client
      • How-To: Install Query Client
    • Model Lifecycle
      • How-To: Deploy AI model
      • How-To: Modify AI Model Settings
    • Access Control
      • How-To: Create User Access Token
      • How-To: Modify User Access Token Setting
      • How-To: Remove Token's Assignment
      • How-To: Assign Token to Model
      • How-To: See List of Tokens
    • Resource Management
      • How-To: Start Worker
      • How-To: Stop Worker
      • How-To: Monitor Worker Performance
    • Secure Query Processing
      • How To: Upload Evaluation Key
      • How-To: Encrypt Input Message
      • How To: Execute Query
      • How-To: Decrypt Output Data
      • How-To: Encrypt, Execute, and Decrypt in One Step
    • Account and Finance Operations
      • How-To: View Payment Transaction History
      • How-To: Update Account Information
      • How-To: View Credit Balance and Add Credit to Your Account
      • How-To: Monitor Balance and Usage
  • Demo Tutorials
    • Image Sharpening with LatticaAI Demo Tutorial
    • Sentiment Analysis with LatticaAI Demo Tutorial
    • Health Analysis with LatticaAI Demo Tutorial
    • Digit Recognition with LatticaAI Demo Tutorial
    • Zooming Into Each Step of Demo Run with LatticaAI flow
Powered by GitBook
On this page

Was this helpful?

  1. How-To Guides
  2. Secure Query Processing

How To: Execute Query

Executing a query allows an end-user to interact securely with an AI model on the LatticaAI platform. This guide explains how to submit an encrypted query using the Query Client.

PreviousHow-To: Encrypt Input MessageNextHow-To: Decrypt Output Data

Last updated 3 months ago

Was this helpful?

Prerequisites

  1. Encrypted Message: The input using the Secret Key in the Query Client.

  2. User Access Token: The user must have a valid Access Token, specific to the AI model being queried. Tokens are validated by LatticaAI during the query process.


Use the following code snippet to execute the query. Provide the User Access Token and the encrypted message as parameters:

import lattica_common.app_api as agent_app
​
# Notice your query token expires in 30 days
query_token = "the_query_token_you_got_using_the_generate_user_token"

# user_data is a tuple of: 
# (serialized_context, serialized_secret_key, serialized_homseq)
# which you need for encrypting the query and querying the model
user_data = agent_app.user.query_offline_phase(query_token)

dataset = pd.read_csv('data/mnist_data.csv').values / 255
data = torch.tensor(dataset[0])
serialized_ct = agent_app.user.encrypt(user_data, dataset)

serialized_ct_res = agent_app.user.apply_hom_pipeline(serialized_ct)

import { LatticaQueryClient } from 'lattica-query-client';

const client = new LatticaQueryClient('your-jwt-query-token');

// Uploaded the EK
const initialized = await client.init();
if (!initialized) {
  console.error('Initialization failed: The EK was not successfully uploaded.');
  throw new Error('EK upload failed.');
}
console.log('EK uploaded successfully.');

// The data you want to encrypt
const inputTensor = ....;

// Encrypt the provided input
const ct = await client.encrypt(pt);

// Send your encrypted query to and get a resopnse
const ct_res = await latticaClient.apply_query(ct);

Process the Response

  • If the query is successful, the result will be returned as an encrypted response.

the response using your Secret Key to obtain the result.

This step focuses on a specific part of the query process: Query Execution. If you prefer to perform encryption, query execution, and decryption in a single command, refer to [How-To: ].

message must be encrypted
Decrypt
Encrypt, Execute, and Decrypt in One Step