NEWMVS for embeddings. Managed for files. Both on object storage.Vectors or files. Pick a path.Start →

Choose how much Mixpeek handles

Deploy a working pipeline for one job in one click, then point it at your bucket.

Managed indexing

Connect a bucket. Mixpeek extracts scenes, faces, text and transcripts.

Bring your own models

Pick from 400+ models, or run your own on Enterprise.

Vector Store (MVS)

Bring your own vectors. Dense, sparse and BM25 search on object storage.

Building blocks

Feature Extractors

Typed pipelines for faces, scenes, transcripts, OCR, fingerprints.

Compose multi-stage search: filter, join, rerank.

S3, GCS, R2, Mux, LangChain, MCP, and more.

How it works →

Top solutions

Find what makes your best ads work

The hooks and patterns in your top-performing video ads, ready for the next brief.

Search basketball game film

Describe the play and get timestamped clips back from every game.

Organize a media library

Search and license every film, episode and clip by what is seen and said.

All solutions and industries →

By file type

Find any moment by what is seen, said or shown on screen.

Search images by content, faces, text and similarity.

Transcripts, speakers and sounds you can query.

Document Intelligence

Layout, tables and text pulled from PDFs and scans.

Browse the showcase →

Build & evaluate

API reference, SDKs, recipes, and architecture guides.

Mixpeek vs. Pinecone, Weaviate, Twelve Labs, more.

See what teams are building with Mixpeek.

Learn

Best-of comparisons: vector DBs, embedding models, moderation APIs.

Vendor-neutral deep dives on perception, retrieval, and embeddings.

Launches, deep dives, and field notes from our engineers.

Papers behind multimodal search (MUVERA, SAM 3, and more) explained.

Every term you need: embeddings to re-rankers.

Videos, diagrams & university →

Deploy a template in one click →

Mission, team, and the multimodal vision.

We're hiring across research, infra, and design.

Talk to sales, support, or press.

45-min working session on your data: leave with a running notebook.

One-click templates Pricing

Sign in Request Demo Get started →

Filter

Attribute Filter

Filter documents by metadata attribute values using boolean logic

attribute_filter

Note: This playground provides simulated output to showcase functionality. No data is processed on our servers. Use this demo to explore the stage's configuration options before integrating it into your retriever pipeline.

Configuration

fieldstring

Field path to filter on (for simple conditions).

operatorstring

Comparison operator.

valueany

Value to compare against.

ANDarray | null

Logical AND - all conditions must be true.

ORarray | null

Logical OR - at least one condition must be true.

NOTarray | null

Logical NOT - all conditions must be false.

Output

No output yet

Configure the stage parameters and click "Run Stage" to see the simulated output.

Related to attribute_filter

Pages on the same stages, extractors and patterns.

Feature Search

Search and filter documents by vector similarity using feature embeddings

Llm Filter

Filter documents using LLM-based semantic evaluation

Agent Search

LLM-driven multi-step retrieval with iterative reasoning and tool orchestration

Query Expand

Generate query variations with LLM and fuse search results via RRF

Score Threshold

Drop results below an absolute score and return no results when nothing qualifies