NEW
Your agents can now see video. Connect Mixpeek via MCP in one command.
Agents can now see video via MCP.
Try it now →
Product
Ingest & Store
Feature Extractors
Typed pipelines for faces, scenes, transcripts, OCR, fingerprints.
Taxonomies
Encode your domain as versioned ontologies enforced at query time.
Storage
Hot, warm, cold and archive tiers that migrate on access patterns.
Retrieve & Analyze
Retrievers
Compose multi-stage search in <100ms:filter, join, rerank.
Templates
Pre-built retrieval pipelines for media, e-commerce, ad tech, and more.
Clusters
Group scenes, faces or objects by similarity with Thompson sampling.
Vector Store (MVS)
Mixpeek Vector Store:horizontally scaled, feature-aware indexes.
Build with the full platform
View all features →
Solutions
By Industry
Advertising
Talent search, brand safety, creative analytics.
Entertainment
Scene search, recommendation, archive access.
E-Commerce
Visual search, PDP enrichment, catalog QA.
Education
Lecture search, transcript Q&A, content safety.
View all solutions →
By Use Case
Face & Person Search
Find anyone across video libraries in milliseconds.
IP & Copyright Detection
Logos, songs, faces:one pipeline, one report.
Visual Taste & Recs
Scene-similarity ranked recommendations with RL.
Brand & Ad Safety
Pre-publish content screening at bid-time speeds.
View all use cases →
Not sure where you fit?
Browse the showcase →
Resources
Build
Documentation
API reference, SDKs, recipes, and architecture guides.
Blog
Launches, deep dives, and field notes from our engineers.
Education
Multimodal University
Fundamentals of multimodal retrieval, modules + certs.
Data Glossary
Every term you need:embeddings to re-rankers.
Video Library
Talks, demos, and customer sessions on demand.
Tutorials
End-to-end walk-throughs for real production pipelines.
Comparisons
Mixpeek vs. Pinecone, Weaviate, Twelve Labs, more.
Ship your first retriever this afternoon.
Open the quickstart →
About
Company
Mission, team, and the multimodal vision.
Careers
We're hiring across research, infra, and design.
Contact
Talk to sales, support, or press.
Partners
Technology and channel partner ecosystem.
Pilot Program
White-glove 30-day production pilot for new customers.
Pricing
Showcase
Sign in
Request demo
Get started →
Product
Pricing
Documentation
Showcase
Sign in
Request Demo
Glossary
Feature URI
Back to Glossary
What is Feature URI
Feature URI - A universal address for any feature emitted by a Mixpeek extractor, enabling query-time model compatibility across the warehouse.
URI Format
mixpeek://{extractor_name}@{version}/{output_name}
extractor_name: the feature extractor that produced the output (e.g., text_extractor, clip_vit_l_14, face_identity_extractor)
version: the extractor version (e.g., v1, v2), which guarantees embedding compatibility
output_name: the specific output of the extractor (e.g., text_embedding, image_embedding, face_embedding)
Examples
mixpeek://text_extractor@v1/text_embedding - 1024D E5 text embedding
mixpeek://clip_vit_l_14@v1/image_embedding - 768D CLIP image embedding
mixpeek://video_extractor@v1/scene_embeddings - scene-level multimodal embedding
mixpeek://face_identity_extractor@v1/face_embedding - 512D ArcFace identity vector
mixpeek://audio_fingerprint_extractor@v1/fingerprint - audio fingerprint feature
Where Feature URIs Are Used
Collection output schemas: define which features a collection produces
Retriever stages: the feature_address field in feature_search stages specifies which embedding to query
Taxonomies: reference which feature to classify against
Clustering jobs: specify the embedding space for vector grouping
Caching: inference cache uses URIs to shortcut repeated embedding requests
Why Feature URIs Matter
Model compatibility: prevents querying a CLIP embedding with an E5 query vector
Version safety: upgrading an extractor version creates new URIs, so old and new embeddings coexist
Lineage tracking: every feature in the warehouse can be traced back to its source extractor and version
Cross-collection queries: retrievers can reference features from multiple collections in the same pipeline
Related Pages
Core Concepts - Feature URIs: /docs/overview/concepts
Feature Extractors: /docs/processing/feature-extractors
Retriever Stages - Feature Search: /docs/retrieval/stages/feature-search
Warehouse Architecture: /docs/overview/warehouse-architecture
Related Terms
ACID
API
Blob Storage
CLIP
Embedding