GUARDRAILS MODERATOR

Guardrails Moderator is a SaaS solution designed to moderate user inputs, ensuring compliance and security by filtering PII (Personally Identifiable Information) and unwanted words using AI and Regex.

FEATURE

Censor inappropriate words with customizable filters
Detect and mask PII Choose between Regex-based filtering (fast) or AI-powered moderation (context-aware)
REST API for seamless integration into any application
Real-time text validation with flexible moderation settings

---

INSTALLATION GUIDE

# Install dependencies
pip install -r requirements.txt

Example API Request

Send a POST request to validate text:

curl -X POST "http://localhost:8000/validate/" -H "Content-Type: application/json" -d '{"text": "My email is test@example.com", "use_ai": false}'

Example Response

{
  "original": "My email is test@example.com",
  "censored": "My email is ****"
}

---

LICENSE

This project is licensed under the MIT License - see the LICENSE file for details.

---

CONTRIBUTING

Pull requests are welcome! Feel free to open an issue or suggest improvements.

---

DEVS LEARNING PLAN

• API concepts
• start API using (FastAPI framework)
• Use FastAPI interface to call app.py to test params calls
• Develop logic (Start simple like "if guardrails receive an prohibited pre-defined word, return to API user input censored")