1.  [](/)
2.  [Diagrams](/diagrams)
3.  Extract, index, retrieve: the whole loop

[Back to Diagrams](/diagrams)IR Foundations

# Extract, index, retrieve: the whole loop

Extract, index, retrieve: the whole loop

![The multimodal warehouse in one flow: extract signals from media (faces, scenes, speech, on-screen text, embeddings) so pixels become rows at ingest, index that meaning next to the bytes so it is queryable forever after one read, and retrieve by meaning with hybrid search and reranking, served to humans and agents the same way. Extract, index, retrieve; everything else is implementation detail.](/diagrams/foundations/multimodal-warehouse.webp)Full screen

Extract, index, retrieve: the whole loop

Twelve posts in this series, one picture.

Most of what a company knows is unstructured and unqueryable. Embeddings turn meaning into coordinates, so search becomes distance. Files decompose into moments, extraction turns pixels and audio into signals, because storage alone answers nothing. Chunking decides what's findable. Hybrid retrieval catches what vectors and keywords each miss. Reranking buys precision. RAG hands the result to a model. Eval tells you whether any of it actually works.

Run that as one system instead of ten separate vendor decisions and you get a multimodal warehouse: media in, structured searchable meaning out, humans and agents querying it the same way.

That's what we're building at Mixpeek. Not a vector database, not a RAG framework. The warehouse where the whole loop lives.

Three verbs the whole time: extract, index, retrieve. Everything else is implementation detail.

## Where this diagram appears

*   [Guide: What Is a Multimodal Data Warehouse? →](/guides/what-is-multimodal-data-warehouse)

Run this on your own data

Mixpeek turns video, images, audio, and documents in your object storage into searchable, timestamped results through one API.

[Search your own data](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=diagram_detail&utm_campaign=mvs_onramp)

## Related diagrams

[

![The unstructured-data problem: the large majority of enterprise data is unstructured (video, images, audio, and documents) that keyword systems and relational databases cannot search by meaning until it is turned into embeddings and indexed. The raw files are stored but not answerable.](/diagrams/foundations/unstructured-data.webp)

99% of your data has no rows



](/diagrams/unstructured-data)[

![An embedding turns meaning into coordinates: a model reads 'dog', 'puppy', and 'invoice' and outputs vectors, so 'dog' and 'puppy' land near each other while 'invoice' lands far away. Text, images, audio clips, video frames, and faces all map into one shared coordinate space where distance measures difference in meaning.](/diagrams/foundations/embeddings.webp)

An embedding is meaning turned into coordinates



](/diagrams/embeddings)[

![Semantic search as nearest-neighbor lookup: embed the query into the same vector space as your content, measure distance to every indexed point, and return the closest top-K results with no keyword matching. Exact brute-force compares against everything and is accurate but slow, while approximate nearest-neighbor (ANN) indexes like HNSW and IVF check a smart fraction of the space and return 95-99% of true answers in milliseconds.](/diagrams/foundations/similarity-search.webp)

Search by meaning = nearest neighbors



](/diagrams/similarity-search)