safevision 1.0.0

Official Python SDK for the SafeVision visual content moderation API

SafeVision Python SDK

Official Python client for the SafeVision visual content moderation API.

Detect NSFW content, gore, weapons, and blood in images — then automatically blur or pixelate offending regions with a single API call.

Installation

pip install safevision

Quick Start

from safevision import SafeVision

sv = SafeVision(api_key="sv_live_your_key_here")

# Scan an image
result = sv.scan("photo.jpg")
print(result["safe"])        # True or False
print(result["categories"])  # detected classes + bounding boxes
print(result["latency_ms"])  # inference time in milliseconds

# Censor violations (blur / pixelate / black_box)
if not result["safe"]:
    censored_bytes = sv.censor("photo.jpg", result, mode="blur")
    with open("censored.jpg", "wb") as f:
        f.write(censored_bytes)

Parameters

Parameter	Type	Default	Description
api_key	str	required	Your sv_live_… API key from the dashboard
base_url	str	https://safevision.guardextech.com	API server URL

Methods

scan(image_path) → dict

Scans an image and returns safety verdict + bounding box coordinates.

censor(image_path, moderation_results, mode) → bytes

Applies blur, pixelate, or black_box to detected regions. Returns censored image bytes.

Links

• 📖 Documentation
• 🔑 Get API Key
• 📧 Support