KnownVectorSearchAlgorithmMetric enum
The similarity metric to use for vector comparisons. It is recommended to choose the same similarity metric as the embedding model was trained on.
Fields
| Cosine | Measures the angle between vectors to quantify their similarity, disregarding magnitude. The smaller the angle, the closer the similarity. |
| DotProduct | Calculates the sum of element-wise products to gauge alignment and magnitude similarity. The larger and more positive, the closer the similarity. |
| Euclidean | Computes the straight-line distance between vectors in a multi-dimensional space. The smaller the distance, the closer the similarity. |
| Hamming | Only applicable to bit-packed binary data types. Determines dissimilarity by counting differing positions in binary vectors. The fewer differences, the closer the similarity. |