embeddings

The concept underneath every RAG system you'll ever deploy. How to explain vectors, cosine similarity, and the one limitation of embeddings that costs real deployments accuracy.

The same operation scores attention and ranks your RAG results. Knowing exactly what the dot product measures, and when its magnitude term quietly breaks your retrieval, is what separates a working pipeline from a mysteriously bad one.

Cosine similarity finds topically close, not correct. The failure taxonomy behind most RAG accuracy complaints, and the hybrid-search + reranker fix stack interviewers expect you to know cold.

Everyone says '500 tokens with overlap.' The candidates who get hired explain why chunk boundaries are a recall problem, name three strategies, and describe the experiment that picks between them.

Pure vector search fails on the exact queries enterprise users ask most: IDs, error codes, product names. Here's the failure-mode framing that turns a definition question into a design answer.

Three plausible fixes, one decision framework. Interviewers grade the ordering (cheapest-reversible first) and whether you can say what each option costs in data, time, and operational burden.

A real interview question with a trap in its framing: it offers you two expensive options and hides the cheap one. The escalation ladder from feature-based reranking to two-tower fine-tuning, with the cold-start and position-bias answers ready.

Slides are the worst RAG corpus: text in shapes, meaning in charts, the message in the image. A query like 'the blue bar chart with Q3 revenue' fails if you embed only the extracted text, and citing the wrong slide number kills trust instantly.

Vectors from two versions of an embedding model are not comparable, and nothing in the stack will tell you so. The cosine between the same document's old and new vector is roughly zero, which is why a half-finished migration returns confident nonsense at full speed.

Brute force is O(N*d) per query and dies at ten million vectors. The answer is approximate nearest neighbor: trade a little recall for orders of magnitude less work, and know exactly which knob buys what.

The arithmetic is three sums; the signal is what you do when a vector is all zeros and the denominator vanishes. The warm-up that gates every RAG and retrieval coding round.

Every RAG deployment runs on this math, and most candidates can't say why cosine beats Euclidean, or when the two are secretly identical. The 90-second version with a worked example.

Triplet loss contrasts an anchor against one negative; modern contrastive losses like InfoNCE contrast against a whole batch at once, which is why CLIP-style training scales and old triplet pipelines stalled. The mining problem, the batch-size lever, and the call interviewers want.

Cache hits on similar prompts cut cost and latency, but one false hit serves a stranger's answer to your question. Picking the threshold and handling user-specific data is the whole game.

Everyone hardens the chat box; almost nobody hardens the index. This question checks whether you've realized the RAG corpus is a write path into your model's behavior, and what you'd do about it this sprint.

A track lasts three minutes, a session lasts an hour, and a new song has zero plays the day it drops. The interview is about blending collaborative filtering with audio content embeddings, surviving cold start on both sides, and reading a skip as the loud negative it is.

There are millions of landmarks, most with a handful of photos, and the next photo might be of something not in your catalog at all. A flat classifier dies on the long tail and never says 'I don't know.' The interview is embeddings plus retrieval plus a confident refusal.