Guardian API Documentation

Welcome to Guardian API

Guardian API is a production-ready content moderation service that combines multiple AI models and rule-based heuristics to provide comprehensive text analysis. Built with FastAPI, it offers a robust, scalable solution for detecting harmful content across multiple categories.

Get Started

Start moderating content in minutes with our quickstart guide.

Key Features

Multi-Model Architecture

Four coordinated models working together: Sexism classifier, toxicity transformer, rule engine, and ensemble aggregator.

Multi-Label Detection

Detects sexism, toxicity, threats, self-harm, profanity, and other harmful content categories.

Production-Ready

FastAPI backend with proper error handling, logging, rate limiting, and comprehensive testing.

Developer-Friendly

OpenAPI documentation, structured JSON responses, and SDKs for Python and JavaScript/TypeScript.

How It Works

Guardian API uses a sophisticated ensemble approach:

Preprocessing: Text is cleaned and normalized
Model Inference: Three models analyze the content in parallel:
- Custom LASSO sexism classifier
- HuggingFace toxicity transformer
- Rule-based heuristics engine
Ensemble: Results are aggregated using weighted fusion and conflict resolution
Response: Structured JSON with scores, severity levels, and metadata

The ensemble model intelligently combines outputs from all models, with rule-based detections overriding low confidence scores for critical issues like threats and self-harm.

Quick Example

curl -X POST "http://localhost:8000/v1/moderate/text" \
  -H "Content-Type: application/json" \
  -d '{"text": "Your text to moderate here"}'

Response:

{
  "text": "Your text to moderate here",
  "label": {
    "sexism": {"score": 0.12, "severity": "low"},
    "toxicity": {"overall": 0.08},
    "rules": {"slur_detected": false, "threat_detected": false}
  },
  "ensemble": {
    "summary": "likely_safe",
    "score": 0.10,
    "severity": "low"
  },
  "meta": {
    "processing_time_ms": 24,
    "models_used": ["sexism_lasso_v1", "toxic_roberta_v1", "rules_v1"]
  }
}

Next Steps

Quickstart

Set up and run Guardian API locally

Architecture

Learn about the multi-model architecture

API Reference

Explore the REST API endpoints

SDKs

Use our Python or JavaScript SDKs

Use Cases

Social Media Platforms: Moderate user comments and posts
Chat Applications: Real-time message filtering
Content Platforms: Screen user-generated content
Community Forums: Maintain healthy discussions
Customer Support: Flag inappropriate messages

Author

Guardian API is developed and maintained by Kory Smith. Originally created as a CSC 380 (Machine Learning) sexism classification project at the University of Arizona.

Quickstart

​Welcome to Guardian API

Get Started

​Key Features

Multi-Model Architecture

Multi-Label Detection

Production-Ready

Developer-Friendly

​How It Works

​Quick Example

​Next Steps

Quickstart

Architecture

API Reference

SDKs

​Use Cases

​Author

Welcome to Guardian API

Key Features

How It Works

Quick Example

Next Steps

Use Cases

Author