Creates an index using the index name specified at instance construction
create_index(
self,
dimensions: int = 1536,
similarity: DocumentDBSimilarityType = DocumentDBSimilarityType.COS,
m: int = 16,
ef_construction: int = 64
) -> dict[str, Any]| Name | Type | Description |
|---|---|---|
dimensions | int | Default: 1536Number of dimensions for vector similarity. The maximum number of supported dimensions is 2000 |
similarity | DocumentDBSimilarityType | Default: DocumentDBSimilarityType.COSSimilarity algorithm to use with the HNSW index. Possible options are:
|
m | int | Default: 16Specifies the max number of connections for an HNSW index. Large impact on memory consumption. |
ef_construction | int | Default: 64Specifies the size of the dynamic candidate list for constructing the graph for HNSW index. Higher values lead to more accurate results but slower indexing speed. |