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.

Contextual Page Signals: Scoring Entities Instead of Listing Them
Nine entities come off one local-news page, three of them US politicians. Flat, it reads as a politics page. Scored, the top two are the actress and the sitcom and it is obviously a television story.

Filtered Vector Search: Why the Same Filter Is Free or Fatal
Adding a filter to a vector search looks like a WHERE clause. Selectivity decides whether it costs nothing or destroys your results, and the API call is identical either way.

Sparse and Dense Are One Spectrum, Not Two Camps
BM25, SPLADE and dense embeddings sit on one axis. What moves along it is how much vocabulary survives compression, which is why a rare identifier ranks below three passages that never mention it.

Agentic Retrieval: What Changes When the Caller Is Not a Person
A person types four words. An agent sends its accumulated state, prior tool output and the reason it is asking. The retrieval layer is answering a different kind of caller.

The S3 Vector Warehouse: Storage-First Vector Search
A billion 768-dimensional float32 vectors is about 3TB raw. Memory-resident, that is a cluster running whether anyone queries it or not. On object storage it is a rounding error of monthly storage.

Ingestion at Scale: Why the Obvious Loop Dies at a Million Files
The obvious loop is correct for a thousand files. At a million, one corrupt video kills it with 400,000 files unprocessed and no record of where it stopped.

The Object Storage Market Map: 27 Providers, Priced
27 object storage providers across seven categories, each carrying storage $/TB-month, egress $/TB, and ingress. The closing panel prices what it costs to walk out with 100 TB.

Contrastive Learning: How Two Encoders Learn One Space
Why a text query can retrieve an image: the pairing is the only supervision.

The Modality Gap: A Shared Space Is Really Two Cones
Why cross-modal retrieval underperforms same-modality retrieval in one shared space.

Three Ways to Score a Query Against a Document
Bi-encoder, cross-encoder, late interaction: when the query is allowed to see the document.

The Memory Math of Quantization
Every compression method is a discount on one term of vectors x dimensions x bytes.

A 0.83 Cosine Is Not 83% Relevant
Scores are ordinal, not cardinal, which is why a fixed threshold silently breaks.

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

Reverse Video Search: A Clip Is a Trajectory, Not a Point
Why image reverse-search matches a point and video reverse-search matches a path.

Scene Segmentation: How a Video Becomes Searchable Scenes
A raw video has no scenes. Two levels of boundary detection turn 108,000 frames an hour into a handful of searchable segments.

Frame Sampling: Which Frames Get Embedded, and What It Costs
Embedding is the expensive step, so the frames you choose to embed are the biggest lever on the cost and recall of a video search system.

Temporal Grounding: Query In, Timestamp Out
Frame search returns stills. Temporal grounding takes a text query and a video and returns the start and end timestamps of the moment you asked for.

Video RAG: Why Retrieval Over Video Is Not Retrieval Over Text
Text RAG gets chunk boundaries, one modality, and small units for free. Video gives you none of them, so every stage of the pipeline is redesigned.

Speaker Diarization: Who Said What, and When
Transcription tells you what was said. Diarization tells you who said it and when, by clustering voices before it ever aligns them to the transcript.