Hierarchical Classification
Assign content to multi-level category hierarchies using embedding-based classification. Define your taxonomy once, then classify new content automatically with confidence scores.
"Show all educational tutorial videos classified under safe content with high confidence"
Why This Matters
Taxonomies are organizational infrastructure. Once defined, they enable consistent classification, compliance tagging, and structured navigation across all content.
import requestsAPI_URL = "https://api.mixpeek.com"headers = {"Authorization": "Bearer YOUR_API_KEY", "X-Namespace": "your-namespace"}# Create hierarchical taxonomytaxonomy = requests.post(f"{API_URL}/v1/taxonomies", headers=headers, json={"taxonomy_name": "content_classification","taxonomy_type": "hierarchical","retriever_id": "ret_classifier","input_mappings": {"query_embedding": "mixpeek://multimodal_extractor@v1/embedding"},"hierarchy": [{"node_id": "safe","collection_id": "col_safe_examples","enrichment_fields": ["metadata.category"]},{"node_id": "educational","parent_node_id": "safe","collection_id": "col_educational_examples","enrichment_fields": ["metadata.topic"]}]}).json()# Apply taxonomy to collectionrequests.post(f"{API_URL}/v1/collections/col_my_content/apply-taxonomy",headers=headers,json={"taxonomy_id": taxonomy["taxonomy_id"]})# Search within taxonomy categoriesresults = requests.post(f"{API_URL}/v1/retrievers/taxonomy-search/execute",headers=headers,json={"query": {"text": "educational tutorial videos"}}).json()for doc in results["documents"]:print(f"Document: {doc['document_id']}")print(f" Category: {doc.get('taxonomy_path', 'N/A')}")
Feature Extractors
Video Embedding
Generate vector embeddings for video content
Retriever Stages
attribute filter
Filter documents by metadata attribute values using boolean logic
Documentation
Use Cases Using This Recipe
Product Affordance Intelligence
Understand what products can do, not just what they look like
+35% improvement
Search relevance (NDCG)
E-commerce platforms, product catalog managers, and merchandising teams managing 100K+ SKU catalogs
AdTech Creative Intelligence
Understand what makes ad creatives perform before they run
99% faster
Creative approval speed
Ad networks, DSPs, creative agencies, and brand marketing teams managing 10K+ creative assets monthly
Government Intelligence
Multimodal search and analysis for government document repositories
100% unified index
Cross-department search coverage
Government agencies, policy researchers, compliance teams, and public affairs professionals managing multi-department document repositories
Asset Intelligence (DAM Auto-Labeling)
Auto-tag and organize digital assets with multimodal AI
95% reduction
Manual tagging effort
Creative teams, brand managers, and media companies managing 100K+ digital assets across DAM platforms
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
AI-Powered Digital Asset Management
Search, organize, and enrich your media library with multimodal AI
80% faster search-to-find
Asset discovery time
Media companies, creative agencies, brand teams, and publishers managing libraries of 500K+ images, videos, and documents across production workflows
Automated Video Tagging for Streaming
Auto-generate rich metadata for every scene, shot, and moment in your catalog
10x more tags than manual editorial process
Metadata tags per title
Streaming platforms, content distributors, and VOD services managing catalogs of 10K+ titles that need rich metadata for discovery and recommendation
Visual Product Search for Ecommerce
Let shoppers search your catalog with images instead of keywords
2.3x increase for visual search users
Search-to-purchase conversion
Ecommerce platforms, online marketplaces, fashion retailers, home goods stores, and any product catalog with 10K+ SKUs where visual discovery drives conversion
Brand Safety Verification
AI-powered brand safety scoring for ad placements and content partnerships
95% reduction in unsafe ad adjacency
Brand safety violation rate
Brand safety teams at agencies, DSPs, SSPs, ad networks, and brand marketers who need to verify that ad placements and content partnerships meet safety standards before spend is allocated
AI Compliance Document Review
Automate regulatory document review with multimodal AI understanding
10x faster
Review cycle time
Compliance teams, regulatory affairs departments, and legal operations groups reviewing 1,000+ regulatory documents per quarter across banking, insurance, pharma, and financial services
Clinical NLP at Scale
Extract structured intelligence from clinical notes, pathology reports, and medical records
94% F1 on medical NER benchmarks
Entity extraction accuracy
Healthcare IT teams, clinical informatics departments, and health systems processing thousands of clinical documents daily
Brand Logo Detection in Video
Scan video assets for unauthorized brand logos and trademarks
Detect logos across 3K+ brands
Brand coverage
Brand safety teams, ad agencies, and content distributors managing video libraries with potential trademark exposure
Related Recipes & Resources
Explore these related resources to deepen your understanding and discover more powerful features
Video Embedding
Generate vector embeddings for video content
Video Embedding
Dense vector representations of video content
Image Embedding
Dense vector representations of image content
Brand Safety & Ad Verification Pipeline
GARM-compliant brand safety pipeline for ad networks. Analyze video and image creatives for brand safety violations before serving.
Video Content Analytics Pipeline
Analyze video content at scale to extract insights: scene composition, speaker time, topic distribution, and sentiment across your video library.
Automated Video Tagging
Automatically generate descriptive tags for video content using scene analysis, object detection, and taxonomy classification. Each video receives structured labels for scenes, objects, actions, and custom business categories without manual annotation.