AI Content Moderation Pipeline
Automatically detect unsafe content across images, videos, and text. Flag NSFW material, violence, hate speech, and custom policy violations.
from mixpeek import Mixpeekclient = Mixpeek(api_key="YOUR_API_KEY")namespace = client.namespaces.create(name="moderation")collection = client.collections.create(namespace_id=namespace.id,name="user-uploads",extractors=["nsfw-detection", "violence-detection", "text-toxicity"])# Process user-uploaded contentclient.buckets.upload(collection_id=collection.id,url="s3://your-bucket/user-uploads/")# Query for flagged contentflagged = client.documents.search(namespace_id=namespace.id,filters={"safety_score": {"$lt": 0.85}})
Feature Extractors
Retriever Stages
attribute filter
Filter documents by metadata attribute values using boolean logic
Use Cases Using This Recipe
AI Content Moderation for User-Generated Content
Automatically detect and flag policy-violating content across text, images, and video
95%+ of violations flagged before going live
Pre-publication violation catch rate
UGC platforms, social media companies, marketplace operators, and community platforms processing 100K+ daily uploads requiring trust and safety review
Video Compliance Monitoring
Automatically verify regulatory and policy compliance across video content at scale
10x faster than manual review
Compliance review speed
Compliance teams, broadcast standards departments, advertising regulators, and enterprise communications teams reviewing video content for regulatory adherence
Related Recipes & Resources
Explore these related resources to deepen your understanding and discover more powerful features
Brand Safety & Ad Verification Pipeline
GARM-compliant brand safety pipeline for ad networks. Analyze video and image creatives for brand safety violations before serving.
E-commerce Catalog Enrichment
Automatically enrich product listings with visual attributes, descriptions, and tags extracted from product images. Fill in missing catalog data at scale.
Face Search Pipeline
Detect, align, and embed faces across your image and video library, then search by face identity. Uses SCRFD for detection and ArcFace for 512-dimensional identity embeddings, enabling large-scale face recognition and matching.
Visual Product Search
Enable camera-based product discovery for e-commerce. Customers snap a photo of a product they like, and the pipeline returns visually similar items from your catalog along with pricing, availability, and product metadata.
Visual Similarity Search
Unified visual similarity search across both images and video frames. Query with a photo, screenshot, or frame to discover visually related content regardless of format, with MMR diversification to ensure variety in results.
AI-Powered Catalog Search
Replace keyword-based catalog search with AI-powered semantic and visual search. Understands natural language queries like "lightweight summer dress under $50" and combines text understanding with visual similarity for comprehensive product discovery.