High Vector DB Question 167 of 223

How does product quantization change vector search?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

Without indexScan every row

With indexJump to keys

CostWrites slower

PQ compresses vectors into codebooks so RAM drops and distance is approximated.

LLMs use tokens (not full words) because it helps them:

This is a process

question about Vector DB.

Panels listen for order,

trade-offs, and what you would actually do on a GenAI / LLM project - not buzzwords.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

Before you speak the answer, walk the interviewer through these steps:

1
PQ compresses vectors into
codebooks so RAM drops and distance is approximated.
2
Recall usually falls unless
you rerank with full vectors.
3
It is a scale
lever when the raw float index no longer fits memory.
4
Give an example
One tiny concrete case you can say aloud.
5
Common mistake
What juniors usually get wrong.
6
Close
When you pick this over the alternative.

Here's a short line you can speak, broken into clear beats:

Say this line

“Recall usually falls unless you rerank with full vectors.”

Break into beats

Recallusuallyfallsunlessyourerank

Speaking order

2987408337471632900

Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.

PQ compresses vectors into codebooks so RAM drops and distance is approximated. Recall usually falls unless you rerank with full vectors.