FLATConfig(
name: str,
field_name: typing.Optional[str] = None,
vector_size: int = 128,
distance_strategy: langchain_community.vectorstores.utils.DistanceStrategy = DistanceStrategy.COSINE,
)
Configuration class for FLAT vector indexes, utilizing brute-force search.
Methods
FLATConfig
FLATConfig(
name: str,
field_name: typing.Optional[str] = None,
vector_size: int = 128,
distance_strategy: langchain_community.vectorstores.utils.DistanceStrategy = DistanceStrategy.COSINE,
)
Initializes the FLATConfig object.
Parameters | |
---|---|
Name | Description |
name |
str
The unique name for the vector index. This name is used to identify the index within the vector store or database. |
field_name |
str
The name of the field that contains the vector data to be indexed. This field should exist within the data structure that stores the documents or vectors. |
vector_size |
int
Specifies the dimensionality of the vectors to be indexed. All vectors added to this index must conform to this size. |
distance_strategy |
DistanceStrategy, optional
Determines the metric used to calculate the distance or similarity between vectors during search operations. |