ML model service API
The ML model service API allows you to make inferences based on a provided ML model.
The ML Model service supports the following methods:
| Method Name | Description |
|---|---|
Infer | Take an already ordered input tensor as an array, make an inference on the model, and return an output tensor map. |
Metadata | Get the metadata: name, data type, expected tensor/array shape, inputs, and outputs associated with the ML model. |
Reconfigure | Reconfigure this resource. |
DoCommand | Execute model-specific commands that are not otherwise defined by the service API. |
GetResourceName | Get the ResourceName for this instance of the ML model service with the given name. |
Close | Safely shut down the resource and prevent further use. |
Establish a connection
Viam Python SDK Support
To use the ML model service from the Viam Python SDK, install the Python SDK using the mlmodel extra:
pip install 'viam-sdk[mlmodel]'
To get started using Viam’s SDKs to connect to and control your machine, go to your machine’s page on the Viam app, navigate to the CONNECT tab’s Code sample page, select your preferred programming language, and copy the sample code.
To show your machine’s API key in the sample code, toggle Include API key.
Caution: Keep your API key and machine address safe
We strongly recommend that you add your API key and machine address as an environment variable. Anyone with these secrets can access your machine, and the computer running your machine.
When executed, this sample code creates a connection to your machine as a client.
The following examples assume that you have a machine configured with an MLModel service called "my_mlmodel_service", and that you have installed the mlmodel extra for the Python SDK.
If your ML model service has a different name, change the name in the code.
Import the mlmodel package for the SDK you are using:
from viam.services.mlmodel import MLModelClient
import (
"go.viam.com/rdk/services/mlmodel"
)
API
Infer
Take an already ordered input tensor as an array, make an inference on the model, and return an output tensor map.
Parameters:
input_tensors(Dict[str, typing.NDArray]) (required): A dictionary of input flat tensors as specified in the metadata.extra(Mapping[str, Any]) (optional): Extra options to pass to the underlying RPC call.timeout(float) (optional): An option to set how long to wait (in seconds) before calling a time-out and closing the underlying RPC call.
Returns:
- (Dict[str, typing.NDArray]): A dictionary of output flat tensors as specified in the metadata.
Example:
import numpy as np
my_mlmodel = MLModelClient.from_robot(robot=machine, name="my_mlmodel_service")
nd_array = np.array([1, 2, 3], dtype=np.float64)
input_tensors = {"0": nd_array}
output_tensors = await my_mlmodel.infer(input_tensors)
For more information, see the Python SDK Docs.
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.tensors(ml.Tensors): The input map of tensors, as specified in the metadata.
Returns:
- (ml.Tensors): The output map of tensors, as specified in the metadata, after being run through an inference engine.
- (error): An error, if one occurred.
Example:
input_tensors := ml.Tensors{"0": tensor.New(tensor.WithShape(1, 2, 3), tensor.WithBacking([]int{1, 2, 3, 4, 5, 6}))}
output_tensors, err := myMLModel.Infer(context.Background(), input_tensors)
For more information, see the Go SDK Docs.
Metadata
Get the metadata: name, data type, expected tensor/array shape, inputs, and outputs associated with the ML model.
Parameters:
extra(Mapping[str, Any]) (optional): Extra options to pass to the underlying RPC call.timeout(float) (optional): An option to set how long to wait (in seconds) before calling a time-out and closing the underlying RPC call.
Returns:
- (viam.services.mlmodel.mlmodel.Metadata): The metadata.
Example:
my_mlmodel = MLModelClient.from_robot(robot=machine, name="my_mlmodel_service")
metadata = await my_mlmodel.metadata()
For more information, see the Python SDK Docs.
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.
Returns:
- (MLMetadata): Name, type, expected tensor/array shape, inputs, and outputs associated with the ML model.
- (error): An error, if one occurred.
Example:
metadata, err := myMLModel.Metadata(context.Background())
For more information, see the Go SDK Docs.
Reconfigure
Reconfigure this resource. Reconfigure must reconfigure the resource atomically and in place.
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.deps(Dependencies): The resource dependencies.conf(Config): The resource configuration.
Returns:
- (error): An error, if one occurred.
For more information, see the Go SDK Docs.
DoCommand
Execute model-specific commands that are not otherwise defined by the service API.
For built-in service models, any model-specific commands available are covered with each model’s documentation.
If you are implementing your own ML model service and add features that have no built-in API method, you can access them with DoCommand.
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.cmd(map[string]interface{}): The command to execute.
Returns:
- (map[string]interface{}): The command response.
- (error): An error, if one occurred.
Example:
myMlmodelSvc, err := mlmodel.FromRobot(machine, "my_mlmodel_svc")
command := map[string]interface{}{"cmd": "test", "data1": 500}
result, err := myMlmodelSvc.DoCommand(context.Background(), command)
For more information, see the Go SDK Docs.
GetResourceName
Get the ResourceName for this instance of the ML model service with the given name.
Parameters:
name(str) (required): The name of the Resource.
Returns:
- (viam.proto.common.ResourceName): The ResourceName of this Resource.
Example:
my_mlmodel_svc_name = MLModelClient.get_resource_name("my_mlmodel_svc")
For more information, see the Python SDK Docs.
Close
Safely shut down the resource and prevent further use.
Parameters:
- None.
Returns:
- None.
Example:
my_mlmodel_svc = MLModelClient.from_robot(robot=machine, name="my_mlmodel_svc")
await my_mlmodel_svc.close()
For more information, see the Python SDK Docs.
Parameters:
ctx(Context): A Context carries a deadline, a cancellation signal, and other values across API boundaries.
Returns:
- (error): An error, if one occurred.
Example:
my_mlmodel, err := mlmodel.FromRobot(machine, "my_ml_model")
err := my_mlmodel.Close(context.Background())
For more information, see the Go SDK Docs.
Have questions, or want to meet other people working on robots? Join our Community Discord.
If you notice any issues with the documentation, feel free to file an issue or edit this file.
Was this page helpful?
Glad to hear it! If you have any other feedback please let us know:
We're sorry about that. To help us improve, please tell us what we can do better:
Thank you!