Moderate Vector DB Question 97 of 223

How do metadata filters work with vector search?

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

Text inTokens

TransformerAttention

Text outNext token

You restrict candidates by tenant, date, product, or ACL before or during ANN search.

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 the model can read a sentence, it goes through these steps:

1
You restrict candidates by
tenant, date, product, or ACL before or during ANN search.
2
Filters enforce security and
freshness that embeddings cannot.
3
Poor filter design either
leaks data or returns empty results.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text

“Filters enforce security and freshness that embeddings cannot.”

Tokenized output

Filtersenforcesecurityandfreshnessthat

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

You restrict candidates by tenant, date, product, or ACL before or during ANN search. Filters enforce security and freshness that embeddings cannot.