TorchServe

Provide access to PyTorch TorchServe servers to run inference with PyTorch models remotely

Metadata

Property	Value
Scheme	`torchserve`
Support Level	Preview
Labels	ai
Version	4.10.2

Maven Dependency

<dependency>
    <groupId>org.apache.camel</groupId>
    <artifactId>camel-torchserve</artifactId>
    <version>4.10.2</version>
</dependency>

Endpoint Properties

Name	Type	Required	Default	Description
`api`	string	✓		The TorchServe API
`operation`	string	✓		The API operation
`modelName`	string			The name of model.
`modelVersion`	string			The version of model.
`lazyStartProducer`	boolean		`false`	Whether the producer should be started lazy (on the first message). By starting lazy you can use this to allow CamelContext and routes to startup in situations where a producer may otherwise fail during starting and cause the route to fail being started. By deferring this startup to be lazy then the startup failure can be handled during routing messages via Camel's routing error handlers. Beware that when the first message is processed then creating and starting the producer may take a little time and prolong the total processing time of the processing.
`inferenceAddress`	string			The address of the inference API endpoint.
`inferencePort`	integer		`8080`	The port of the inference API endpoint.
`listLimit`	integer		`100`	The maximum number of items to return for the list operation. When this value is present, TorchServe does not return more than the specified number of items, but it might return fewer. This value is optional. If you include a value, it must be between 1 and 1000, inclusive. If you do not include a value, it defaults to 100.
`listNextPageToken`	string			The token to retrieve the next set of results for the list operation. TorchServe provides the token when the response from a previous call has more results than the maximum page size.
`managementAddress`	string			The address of the management API endpoint.
`managementPort`	integer		`8081`	The port of the management API endpoint.
`registerOptions`	object			Additional options for the register operation.
`scaleWorkerOptions`	object			Additional options for the scale-worker operation.
`unregisterOptions`	object			Additional options for the unregister operation.
`url`	string			Model archive download url, support local file or HTTP(s) protocol. For S3, consider using pre-signed url.
`metricsAddress`	string			The address of the metrics API endpoint.
`metricsName`	string			Names of metrics to filter.
`metricsPort`	integer		`8082`	The port of the metrics API endpoint.
`inferenceKey`	string			The token authorization key for accessing the inference API.
`managementKey`	string			The token authorization key for accessing the management API.