> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mixpeek.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Mixpeek is the semantic retrieval layer for unstructured and multimodal data

Mixpeek makes the world's unstructured data programmable.

Your AI agent can read text. It cannot watch a video, scan a photo for faces, or search audio by what was said. Mixpeek turns video, images, audio and documents into named semantic features, then serves them through retrievers your agent calls by name.

> [card] [Start building on Mixpeek](https://studio.mixpeek.com/?utm_source=docs\&utm_medium=docs_intro\&utm_campaign=mvs_onramp)
>
> Create a workspace and run your first multimodal search — index your own video, images, audio, or documents in minutes.

## How It Works

**1. Index**

Upload video, images, audio, and documents to [Buckets](https://docs.mixpeek.com/docs/platform/data-model.md#create-a-bucket). Mixpeek runs feature extraction automatically — faces, objects, transcripts, embeddings, and structured metadata all get indexed into searchable [Collections](https://docs.mixpeek.com/docs/overview/concepts.md).

![Indexing multimodal content into semantic layers](https://mintcdn.com/mixpeek/TwtTrae3Fi3EFJ72/assets/mixpeek-decomposition.svg?fit=max\&auto=format\&n=TwtTrae3Fi3EFJ72\&q=85\&s=4bfa40801fe7d78a68db0bd3f48b49c4)

Breaking down a video into semantic layers

See this running on real content — 7 PDFs that fan out into 59 searchable knowledge-graph nodes — in the [sample data](https://docs.mixpeek.com/docs/overview/sample-data.md#diagram-1-how-content-decomposes).

**2. Search**

Build retrieval pipelines that your agent calls. Semantic search, face search, object search, transcript search — chain them together into multi-stage [Retrievers](https://docs.mixpeek.com/docs/retrieval/retrievers.md) and expose them as a single endpoint.

![Multi-stage retrieval pipeline](https://mintcdn.com/mixpeek/TwtTrae3Fi3EFJ72/assets/mixpeek-retrieval.svg?fit=max\&auto=format\&n=TwtTrae3Fi3EFJ72\&q=85\&s=4089a289e16b0cb17b6decd075b46f13)

Chaining search stages into a retrieval pipeline

Run this exact pipeline against the [sample data](https://docs.mixpeek.com/docs/overview/sample-data.md#diagram-2-how-retrieval-reassembles) right now — no account or API key needed.

**3. Integrate**

Wire Mixpeek into your agent as a [LangChain tool](https://docs.mixpeek.com/docs/integrations/agents.md#langchain), an [MCP server](https://docs.mixpeek.com/docs/integrations/agents.md#mcp-model-context-protocol), or a direct REST call. Your agent sends a query, gets structured results back, and acts on them.

> [!TIP]
>
> **Already have embeddings?** Skip extraction entirely — bring your own vectors and search instantly with the [Mixpeek Vector Store](https://docs.mixpeek.com/docs/vector-store/overview.md). Sixty seconds to first query.

## Quickstart

> [card] [Get Started](https://docs.mixpeek.com/docs/overview/quickstart.md)
>
> Index multimodal content and search it in under 10 minutes — LangChain, MCP, or REST

## What Can You Build?

Pick an outcome and follow the guide — each one is end-to-end and copy-pasteable.

> [card] [Search video](https://docs.mixpeek.com/docs/tutorials/video-understanding.md)
>
> Find moments by what's shown or said — visual + speech embeddings

> [card] [Reverse image & video search](https://docs.mixpeek.com/docs/tutorials/reverse-search.md)
>
> Use an image or clip as the query to find visually similar media

> [card] [Hybrid search](https://docs.mixpeek.com/docs/retrieval/stages/feature-search.md#lexical-bm25-search)
>
> Combine dense vectors with keyword/BM25 and attribute filters

> [card] [Rerank for precision](https://docs.mixpeek.com/docs/retrieval/stages/rerank.md)
>
> Push the most relevant results to the top with a cross-encoder

> [card] [Cluster content](https://docs.mixpeek.com/docs/enrichment/clusters.md)
>
> Group, label, and visualize a collection automatically

> [card] [Build a taxonomy](https://docs.mixpeek.com/docs/enrichment/taxonomies.md)
>
> Classify content against your own hierarchy with a multimodal join

> [card] [Secure per-user retrieval](https://docs.mixpeek.com/docs/platform/permissions.md)
>
> Enforce access control with built-in ACLs or external OpenFGA

> [card] [Bring your own vectors](https://docs.mixpeek.com/docs/vector-store/overview.md)
>
> Use Mixpeek as a standalone vector store — upsert and query instantly

> [card] [Auto-tune relevance](https://docs.mixpeek.com/docs/retrieval/auto-tune.md)
>
> Improve ranking automatically from click and reward signals

> [card] [Migrate embedding models](https://docs.mixpeek.com/docs/processing/model-migration.md)
>
> Re-extract, validate, and cut over to a new model with no downtime

## What Gets Extracted

| File Type | Extracted Features |
| - | - |
| **[Video](https://docs.mixpeek.com/docs/processing/extractors/multimodal.md)** | Face embeddings (ArcFace 512D), scene descriptions (Gemini), visual embeddings (Vertex AI 1408D), transcripts (Whisper), transcript embeddings (E5-Large 1024D), keyframes |
| **[Images](https://docs.mixpeek.com/docs/processing/extractors/image.md)** | Visual embeddings (SigLIP 768D or Vertex AI 1408D), face embeddings (ArcFace 512D), OCR text, descriptions, structured extraction |
| **[Audio](https://docs.mixpeek.com/docs/processing/extractors/multimodal.md)** | Transcripts (Whisper), transcript embeddings (E5-Large 1024D), multimodal audio embeddings (Vertex AI 1408D) |
| **[Documents](https://docs.mixpeek.com/docs/processing/extractors/document.md)** | Text chunks, text embeddings (E5-Large 1024D), OCR for scanned PDFs, structured extraction |

Each extracted feature becomes an independently searchable document. A single video can produce hundreds of documents — one per face, one per transcript segment, one per scene.

## Key Concepts

* **Namespaces** isolate data between tenants, environments, or projects. Every API request includes a namespace header.
* **Buckets** hold your raw files. Upload once, process many ways.
* **Collections** define what gets extracted. Each collection runs a feature extractor (CLIP, Whisper, LayoutLM, etc.) against objects in a bucket.
* **Retrievers** are search pipelines you configure in JSON. Chain stages together — vector search, face matching, filters, re-ranking — and expose the result as one endpoint your agent calls.

## Next Steps

> [card] [Core Concepts](https://docs.mixpeek.com/docs/overview/concepts.md)
>
> Understand namespaces, buckets, collections, and retrievers in depth

> [card] [Data Model](https://docs.mixpeek.com/docs/platform/data-model.md)
>
> See how namespaces, buckets, collections, objects, and features fit together

> [card] [Feature Extractors](https://docs.mixpeek.com/docs/processing/feature-extractors.md)
>
> Learn what each extractor does and how to configure it

> [card] [Tutorials](https://docs.mixpeek.com/docs/tutorials.md)
>
> Step-by-step guides for common use cases


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.