Configure Euclidean distance

Create a collection that measures straight-line distance between vectors.

Euclidean distance measures straight-line distance between points. It is well suited for image embeddings and spatial data where the absolute distance between vectors represents meaningful differences.

The SDK references this metric as Distance.Euclid.

This example creates a collection named image_embeddings configured to use Euclidean distance.

Python

from actian_vectorai import VectorAIClient, VectorParams, Distance

# Connect to VectorAI DB server
with VectorAIClient("localhost:6574") as client:
    # Create collection with Euclidean distance
    client.collections.create(
        "image_embeddings",  # Collection name
        vectors_config=VectorParams(size=128, distance=Distance.Euclid)  # Euclidean metric
    )

To confirm the collection was created successfully, call client.collections.get_info("image_embeddings") and check that the status field returns Ready.