SWE Prep/ Learning OS
Menu

Learning track · 12 concepts

Vector DB & ANN

Vector search engines: similarity, top-k, brute force, HNSW, IVF, quantization, metadata filtering, and recall/latency tradeoffs.

What mastery looks like

This track contains 12 connected concepts rather than an unordered reading list. Mastery means you can move from vocabulary to mechanisms, predict how the system behaves under pressure, and support a design decision with code, measurements, or a failure-recovery exercise. For Vector DB & ANN, use the track description as the boundary: learn enough detail to reason clearly about vector search engines: similarity, top-k, brute force, hnsw, ivf, quantization, metadata filtering, and recall/latency tradeoffs.

A useful explanation names the state involved, the operation that changes it, the resource or safety constraint, and the observable signal that tells you whether the mechanism works. Avoid stopping at product names. Compare at least two approaches, state what each optimizes, and identify what breaks first as scale, concurrency, latency, or uncertainty increases.

Suggested study sequence

Start with the core concepts at the top of the list and write a one-paragraph mechanism note for each. Continue through the core concepts by alternating explanation with an executable drill. Treat HNSW, IVF (Inverted File), Product Quantization, Recall / Latency Tradeoffs as integration work: they should combine earlier mechanisms rather than introduce disconnected facts.

At the end of each session, record one decision you can now make, one failure mode you can now predict, and one unanswered question. Revisit that question through the linked primary sources, then prove the answer in the Playground or a real repository. The track is complete when you can transfer the reasoning to an unfamiliar system, not when every page has been opened.

Roadmaps

Concepts in this track

core

Embeddings

Mapping text/images into dense vectors where distance encodes meaning.

core

Vector Similarity

Cosine, dot product, and L2 distance — how to score vector closeness.

core

Brute-Force Vector DB

Exact nearest-neighbour search by scanning every vector — the correctness baseline.

advanced

HNSW

Hierarchical Navigable Small World graphs — the dominant ANN index.

advanced

IVF (Inverted File)

Cluster vectors with k-means, then search only the nearest cells (nprobe).

advanced

Product Quantization

Compress vectors into sub-space codebooks for tiny memory footprint.

core

Metadata Filtering

Combining vector search with structured predicates (tenant, date, tags).

advanced

Disk-Based ANN

DiskANN and SPANN — serving vector indexes that do not fit in memory.