Filter with must-not conditions

Exclude results where conditions are true.

Adding a must-not condition excludes any result where that condition is true. Use must-not conditions to remove unwanted results, such as filtering out discontinued products or blocked content.

Before you begin, make sure you have a running VectorAI DB instance and a products collection with 128-dimensional vectors and payload fields: category (string) and price (float).

Python

from actian_vectorai import VectorAIClient, FilterBuilder, Field
import random

# Connect to VectorAI DB server
with VectorAIClient("localhost:6574") as client:
    # Generate query vector
    query_vector = [random.gauss(0, 1) for _ in range(128)]
    
    # Filter: exclude electronics AND exclude expensive items (>= $100)
    filter = FilterBuilder()\
        .must_not(Field("category").eq("electronics"))\
        .must_not(Field("price").gte(100.0))\
        .build()
    
    # Search with filter
    results = client.points.search(
        "products",  # Collection name
        vector=query_vector,  # Query vector
        limit=10,  # Maximum results
        filter=filter  # Apply filter
    )
    
    # Display results
    for result in results:
        print(f"ID: {result.id}")
        print(f"Category: {result.payload['category']}")
        print(f"Price: ${result.payload['price']}")
        print("-" * 50)

Each result includes these fields:

• id: The unique identifier of the matching point.
• score: Similarity score based on vector distance.
• payload: Full metadata dictionary for the matching point.