Quickstart

EvalGuard protects your Large Language Model (LLM) use cases by helping your developers detect security risks to your LLM application, and its users, in real-time.

Follow the steps below to detect your first prompt injection with EvalGuard.

Detect a prompt injection

The example code below should trigger EvalGuard's prompt injection detection.

Copy and paste it into a file on your local machine and execute it from the same terminal session.

Python

import requests

# Get prompt from the front-end user
prompt_from_user = "put your prompt here"

# Send the prompt into EvalGuard's API Gateway
url = "https://app.evalguard.io/prod-api/v1/guard"
payload = {
    "messages": [
        {
            "role": "user",
            "content": prompt_from_user
        }
    ]
}
headers = {
    "Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)

print(response.json())

# If EvalGuard finds a prompt injection or jailbreak, do not call the LLM!
if response.json()["flagged"]:
    print("EvalGuard identified a malicous prompt.")
else:
    # Send the user's prompt to your LLM of choice.
    print("The prompt can be forward to LLM or user.")

Learn more

Working with the EvalGuard API is as simple as making an HTTP request.

Tutorials

To help you get more out of EvalGuard, we've created some tutorials to help guide you through some common use cases.

• Prompt Injection: Detect a prompt injection attack with an example chat application that loads an article to provide context for answering the user's question

Guides

To help you learn more about the security risks TrustAI Guard protects against, we've created some guides.

• Introduction to Framework of LLM(Large Language Model) Security

• Introduction to AVID(AI Vulnerability Database Taxonomy) Schema based on real-world LLM security cases

• LLM Security Challenges and Security Compliance Governance Framework

• LLM Security Vulnerability Mining Beginner's Guide

• The road leading to LLM Security Alignment

• Jailbreak Attack for widely existing LLMs Apps in applications

• The Art of Deception -- Is AI More susceptible to Social Engineering Attacks?

• Generating toxic images and videos through jailbreaking, an undeniable LLM security risk

Other Resources

If you're still looking for more, you can Book a demo