Diagrams
How multimodal search actually works, one picture at a time. Each diagram explains a single idea — from what an embedding is, to why reranking exists, to how the whole extract → index → retrieve loop fits together.

99% of your data has no rows
Most enterprise data is unstructured — unsearchable by meaning until it is extracted, embedded, and indexed.

An embedding is meaning turned into coordinates
An embedding turns meaning into coordinates — similar things land near each other, across every modality.

Search by meaning = nearest neighbors
Search by meaning is a nearest-neighbor lookup — embed the query, return the closest points.

You search inside the file, not for it
You search inside the file, not for it

Pixels in, signals out
Extraction turns a raw frame into structured, searchable signals — the ceiling for every downstream search.

S3 stores bytes, not answers
Storage keeps the bytes; an index keeps the meaning — the archive is only useful once it is indexed.

How you split decides what you find
How you split decides what you find

Keywords catch what vectors miss
Hybrid search fuses keyword (BM25) and vector results so each covers the other's blind spots.

Wide net first, careful read second
Reranking re-scores first-stage candidates with a cross-encoder so the best results rise to the top.

The model answers with what you feed it
In RAG, retrieval sets the quality ceiling — the model answers from the passages you feed it.

Pick the metric that matches user behavior
Pick the metric that matches user behavior

Extract, index, retrieve: the whole loop
Extract, index, retrieve: the whole loop

MUVERA: How a Multi-Vector Set Becomes One Fixed Vector
How a Multi-Vector Set Becomes One Fixed Vector

MUVERA: Why Query and Document Are Encoded Asymmetrically
Why Query and Document Are Encoded Asymmetrically

MUVERA: Two-Tier Retrieval (Cheap FDE Recall, Exact Rerank)
Two-Tier Retrieval (Cheap FDE Recall, Exact Rerank)

MUVERA: Which Knob Actually Buys Recall (FDE Dimensionality Ablation)
Which Knob Actually Buys Recall (FDE Dimensionality Ablation)

MUVERA: Why Anisotropic Embeddings Break FDEs (and Mean-Centering Fixes It)
Why Anisotropic Embeddings Break FDEs (and Mean-Centering Fixes It)

Four Chunking Strategies, Same Document
Four Chunking Strategies, Same Document

The Embedding Model Landscape
The Embedding Model Landscape

One Ranking, Four Metrics
One Ranking, Four Metrics

Multimodal Search as an MCP Tool
Multimodal Search as an MCP Tool

Multimodal Decomposition: One File, Many Signals
Multimodal Decomposition: One File, Many Signals

Multi-Vector Search vs. a Single Embedding
Multi-Vector Search vs. a Single Embedding

Query Expansion: Rewriting the Question Before You Search
Query Expansion: Rewriting the Question Before You Search

How Reranking Works: Recall Wide, Then Score Precisely
How Reranking Works: Recall Wide, Then Score Precisely

The Retrieval Feedback Flywheel
The Retrieval Feedback Flywheel

Anatomy of a Retriever Pipeline
Anatomy of a Retriever Pipeline

Reciprocal Rank Fusion, Explained
Reciprocal Rank Fusion, Explained

Taxonomy-Aware Retrieval
Taxonomy-Aware Retrieval

Vector Index Structures: HNSW, IVF, and Friends
Vector Index Structures: HNSW, IVF, and Friends