Skip to main content

馃摌馃憪 Similarity Functions

Atlas Vector Search supports different similarity functions to search for top K-nearest neighbors. You can set the similarity function for vector type fields in your index definition.

  • euclidean - measures the distance between ends of vectors.
  • cosine - measures similarity based on the angle between vectors.
  • dotProduct - measures similarity like cosine, but takes into account the magnitude of the vector.

馃摎 About the similarity functions

CODE_BLOCK_15

Answer
{
    "name": ATLAS_VECTOR_SEARCH_INDEX_NAME,
    "type": "vectorSearch",
    "definition": {
        "fields": [
            {
                "type": "vector",
                "path": "embedding",
                "numDimensions": 512,
                "similarity": "dotProduct",
            },
        ]
    },
}