Visualizers

Learn by moving things

Interactive explainers for the ideas behind retrieval, embeddings, and agents. A formula tells you what is true; dragging a vector shows you why. Each one also appears inside the article it belongs to, and runs entirely in your browser, so drag, poke, and break it.

Portrait of Sachin Gupta rendered in binary

Database search: scan vs graph

From: ANN at Scale: HNSW →

A tiny food database queried with real phrases. Answer the same query two ways over the same data, scan every row (kNN) or follow the graph (HNSW), and watch the difference in what gets touched.

Search the food database for…

checked 0/17

Scan (kNN): measure the query against every one of the 17 items, then keep the closest. Always exact, always 17 comparisons.

Reciprocal Rank Fusion

From: Hybrid Search →

How hybrid search merges a keyword list and a vector list into one. Watch two ranked results fuse by summing 1/(k + rank), with the math shown per document, and drag the rank constant to reshape the blend.

Query: “reset my password”rank constant k60

Keyword (BM25)

matches literal terms

1Reset your password
2Password reset email issues
3Change password in settings
4Forgot your username
5Cannot sign in

Semantic (vector)

matches meaning

1Recover a locked account
2Reset your password
3Cannot sign in
4Change password in settings
5Password reset email issues

Fused (RRF)

score = 1/(k+rank) summed

1Reset your password0.0325
K#1 V#2
2Password reset email issues0.0315
K#2 V#5
3Change password in settings0.0315
K#3 V#4
4Cannot sign in0.0313
K#5 V#3
5Recover a locked account0.0164
K— V#1
6Forgot your username0.0156
K#4 V—

A document ranked high in either list scores well; ranked high in both, it wins. No score normalization, just ranks. Larger k flattens the gap between ranks.

Chunking a document

From: How RAG Reads a Corpus →

Before retrieval can work, a document is cut into passages. Drag chunk size and overlap and watch the tradeoff: small chunks are sharp but lose context, big ones blur topics, and overlap keeps a thought from being cut at the seam.

chunk size18woverlap4w6 chunks

chunk 1

A vector database stores embeddings and finds the nearest ones to a query. Before anything can be stored,

chunk 2

anything can be stored, the source documents must be split into smaller passages called chunks. Each chunk becomes

chunk 3

chunks. Each chunk becomes a single vector. If a chunk is too large it mixes several topics and

chunk 4

mixes several topics and its vector turns blurry. If it is too small it loses the surrounding context

chunk 5

loses the surrounding context that made it meaningful. Overlap keeps a sentence from being cut in half at

chunk 6

cut in half at a boundary.

Smaller chunks are sharper but more numerous and lose context; larger chunks keep context but blur topics together. The greyed words are overlap, shared with the previous chunk so a thought is not cut at the seam.