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
