Skip to content

Deploy a Chat Interface in 5 Minutes

Deploy a fully functional chat interface with built-in safety guardrails. This guide uses Open WebUI with Lucid's chat auditor profile for toxicity filtering, injection protection, and data sovereignty.

Alpha Access Required

Lucid is in private alpha. Request access before proceeding.

Time to complete: ~3 minutes

What You'll Get

At the end of this quickstart, you'll have:

  • A live Open WebUI chat interface at a unique URL
  • Llama 3.1 8B model running in a TEE (Trusted Execution Environment)
  • Safety auditors protecting every interaction:
  • Prompt injection detection
  • Toxicity filtering
  • Data sovereignty enforcement
  • AI Passports providing cryptographic proof of compliance

Step 1: Install and Authenticate

If you haven't already, install the CLI and log in:

# Install the CLI
pip install lucid-cli

# Log in to your account
lucid login -e your@email.com -p yourpassword

Expected output:

Logged in as your@email.com

Step 2: Deploy Your Chat Interface

Run a single command to deploy:

lucid apply --app open-webui --model llama-3.1-8b --profile chat

Expected output:

[*] Creating serverless environment...
[+] Environment created: env-abc123def456

    Connection URL: https://env-abc123def456.serverless.lucid.ai
    App:            open-webui
    Model:          meta-llama/Llama-3.1-8B-Instruct
    Auditors:       injection, toxicity, sovereignty
    Region:         us-east-1

[+] Environment ready!

Step 3: Access Your Chat

Open the Connection URL in your browser:

https://env-abc123def456.serverless.lucid.ai

You now have a fully functional chat interface. Try it out:

  1. Ask a question: "What is machine learning?"
  2. Notice the response is fast and natural
  3. Every interaction is protected by the auditor chain

Step 4: Verify Security (Optional)

Confirm your environment has valid TEE attestation:

lucid verify environment env-abc123def456

Expected output:

[*] Fetching routing info for environment env-abc123def456...
  [+] Model: https://model-xyz.serverless.lucid.ai (us-east-1) - amd_sev_snp
  [+] Auditor: https://auditor-abc.serverless.lucid.ai (us-east-1) - amd_sev_snp
  [+] App: https://app-123.serverless.lucid.ai (us-east-1) - amd_sev_snp

[*] 3/3 endpoints have attestation reports

What the Chat Profile Includes

The chat profile activates these auditors:

Auditor What It Does
Injection Blocks prompt injection and jailbreak attempts
Toxicity Filters harmful, offensive, or inappropriate content
Sovereignty Ensures data stays in your selected region

Try Different Models

Want more capability? Switch to a larger model:

# 70B model for complex reasoning
lucid apply --app open-webui --model llama-3.1-70b --profile chat

# Qwen for multilingual support
lucid apply --app open-webui --model qwen-72b --profile chat

Try Different Regions

Need EU data residency? Add the --region flag:

lucid apply --app open-webui --model llama-3.1-8b --profile chat --region eu

View AI Passports

Every chat interaction generates a cryptographically signed AI Passport:

lucid passport list

ID              AGENT           TIMESTAMP
pass-001        env-abc123      2024-01-15T10:30:00Z
pass-002        env-abc123      2024-01-15T10:31:00Z

View details:

lucid passport show pass-001

Passport ID: pass-001
Hardware Attested: true
TEE Type: AMD SEV-SNP
Auditors: injection, toxicity, sovereignty

Clean Up

When you're done, you can manage your environment through the Observer dashboard at observer.lucid.sh or use the status command to check active environments:

lucid status

Serverless environments can be stopped via the Observer UI. For local development environments, use:

lucid teardown

Next Steps

Summary

You deployed a secure chat interface with:

Component Value
App Open WebUI
Model Llama 3.1 8B
Auditors injection, toxicity, sovereignty
TEE AMD SEV-SNP
Time ~3 minutes

Your chat interface is now protected by hardware-backed security with cryptographic proof of every interaction.