In Milvus, distance metrics are used to measure similarities among vectors. Choosing a good distance metric helps improve the classification and clustering performance significantly.
The following table shows how these widely used distance metrics fit with various input data forms and Milvus indexes.
|Distance Metrics||Index Types|
|Euclidean distance (L2)||
|Inner product (IP)|
Essentially, Euclidean distance measures the length of a segment that connects 2 points.
The formula for Euclidean distance is as follows:
where a = (a1, a2,..., an) and b = (b1, b2,..., bn) are two points in n-dimensional Euclidean space
It's the most commonly used distance metric, and is very useful when the data is continuous.
The IP distance between two embeddings are defined as follows:
where A and B are embeddings,
||B|| are the norms of A and B.
IP is more useful if you are more interested in measuring the orientation but not the magnitude of the vectors.
Suppose X' is normalized from embedding X:
The correlation between the two embeddings is as follows:
Why is the top1 result of a vector search not the search vector itself, if the metric type is inner product?This occurs if you have not normalized the vectors when using inner product as the distance metric.
What is normalization? Why is normalization needed?
Normalization refers to the process of converting an embedding (vector) so that its norm equals 1. If you use Inner Product to calculate embeddings similarities, you must normalize your embeddings. After normalization, inner product equals cosine similarity.
See Wikipedia for more information.