Filtered Vector Search

You can combine vector search with scalar filters to restrict results to a subset of documents — just like adding a WHERE clause to a similarity search.

Prerequisites

This guide assumes you:

• Have already opened a collection instance.
• Are familiar with vector querying and conditional filtering.

Performing Filtered Vector Search

To combine vector similarity search with filters, pass both a VectorQuery and a filter expression to the query() method.

import zvec

result = collection.query(
    zvec.VectorQuery(  
        field_name="dense_embedding",
        vector=[0.1] * 768,  # Replace with real embedding
    ),
    filter="publish_year > 1936",  # Only consider books published after 1936
    topk=10,
)
print(result)

This returns the top-10 most similar documents that satisfy publish_year > 1936, sorted by similarity score.