Struct elasticsearch::ml::MlStartTrainedModelDeployment
source · pub struct MlStartTrainedModelDeployment<'a, 'b, B> { /* private fields */ }
Expand description
Builder for the Ml Start Trained Model Deployment API
Start a trained model deployment.
Optional, beta
This requires the beta-apis
feature. On track to become stable but breaking changes can
happen in minor versions.
Implementations
sourceimpl<'a, 'b, B> MlStartTrainedModelDeployment<'a, 'b, B>where
B: Body,
impl<'a, 'b, B> MlStartTrainedModelDeployment<'a, 'b, B>where
B: Body,
sourcepub fn new(
transport: &'a Transport,
parts: MlStartTrainedModelDeploymentParts<'b>
) -> Self
pub fn new(
transport: &'a Transport,
parts: MlStartTrainedModelDeploymentParts<'b>
) -> Self
Creates a new instance of MlStartTrainedModelDeployment with the specified API parts
sourcepub fn body<T>(
self,
body: T
) -> MlStartTrainedModelDeployment<'a, 'b, JsonBody<T>>where
T: Serialize,
pub fn body<T>(
self,
body: T
) -> MlStartTrainedModelDeployment<'a, 'b, JsonBody<T>>where
T: Serialize,
The body for the API call
sourcepub fn cache_size(self, cache_size: &'b str) -> Self
pub fn cache_size(self, cache_size: &'b str) -> Self
A byte-size value for configuring the inference cache size. For example, 20mb.
sourcepub fn error_trace(self, error_trace: bool) -> Self
pub fn error_trace(self, error_trace: bool) -> Self
Include the stack trace of returned errors.
sourcepub fn filter_path(self, filter_path: &'b [&'b str]) -> Self
pub fn filter_path(self, filter_path: &'b [&'b str]) -> Self
A comma-separated list of filters used to reduce the response.
sourcepub fn header(self, key: HeaderName, value: HeaderValue) -> Self
pub fn header(self, key: HeaderName, value: HeaderValue) -> Self
Adds a HTTP header
sourcepub fn number_of_allocations(self, number_of_allocations: i32) -> Self
pub fn number_of_allocations(self, number_of_allocations: i32) -> Self
The total number of allocations this model is assigned across machine learning nodes.
sourcepub fn queue_capacity(self, queue_capacity: i32) -> Self
pub fn queue_capacity(self, queue_capacity: i32) -> Self
Controls how many inference requests are allowed in the queue at a time.
sourcepub fn request_timeout(self, timeout: Duration) -> Self
pub fn request_timeout(self, timeout: Duration) -> Self
Sets a request timeout for this API call.
The timeout is applied from when the request starts connecting until the response body has finished.
sourcepub fn source(self, source: &'b str) -> Self
pub fn source(self, source: &'b str) -> Self
The URL-encoded request definition. Useful for libraries that do not accept a request body for non-POST requests.
sourcepub fn threads_per_allocation(self, threads_per_allocation: i32) -> Self
pub fn threads_per_allocation(self, threads_per_allocation: i32) -> Self
The number of threads used by each model allocation during inference.
Trait Implementations
sourceimpl<'a, 'b, B: Clone> Clone for MlStartTrainedModelDeployment<'a, 'b, B>
impl<'a, 'b, B: Clone> Clone for MlStartTrainedModelDeployment<'a, 'b, B>
sourcefn clone(&self) -> MlStartTrainedModelDeployment<'a, 'b, B>
fn clone(&self) -> MlStartTrainedModelDeployment<'a, 'b, B>
1.0.0 · sourcefn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source
. Read more