embeddings

Retrieval quality decides most RAG products, and embeddings are where it starts. The interviewer wants the intuition, the failure modes, and the fixes a PM would push for.

Shorter and binary embeddings cut storage by orders of magnitude and lose a few points of retrieval. Decide with recall on your own queries and a rescoring step.

Two well-run teams published opposite defaults. Decide by repository size, how fast code changes, latency and whether customers will let you store embeddings of their code.

Cropping beats a bigger model, a smaller embedding buys back latency, and a stale index sends shoppers to items they cannot buy. Make each of those calls with numbers.

Embeddings are infrastructure that customers store and rebuild around. The interviewer wants retrieval quality on real tasks, multilingual coverage, cost, and above all a plan for version changes, because switching embeddings means re-indexing everything.