API Description

KScaNN APIs are added and modified based on the open source ScaNN APIs, To achieve the optimal performance, KScaNN interfaces do not verify all input parameters. The validity of input parameters is ensured by the service that calls the interfaces. which are described in Table 1.

**Table 1** Python APIs provided by KScaNN
API	Function
set_num_threads	Configures the number of threads enabled during search. It is a new API added to the open source algorithm.
search_additional_params	Extends the ScaNN search function by configuring additional search parameters. It is a new API added to the open source algorithm.
search	Performs single-query search, which is executed by a single thread. It is consistent with the open source algorithm API.
search_batched	Performs batch-query search, which is executed by a single thread. It is consistent with the open source algorithm API.
search_batched_parallel	Performs parallel batch-query search, which is concurrently executed by multiple threads. It adds a new parameter batch_size to the open source algorithm API.
builder	Starts the build. It is consistent with the open source algorithm API.
tree	Adds parameters related to the inverted file (IVF) index partition. It is consistent with the open source algorithm API.
score_ah	Adds parameters related to partitioned product quantization (PQ). It is consistent with the open source algorithm API.
reorder	Adds parameters related to reordering. It is consistent with the open source algorithm API.
build	Builds indexes. It is consistent with the open source algorithm API.

Parent topic: KScaNN APIs