Inference Client

Performs the OAuth2 authentication using oauthClientId and oauthClientSecret on oauthTokenUrl and sends the request to the MLF model server. With the authentication token the request built from signatureName, inputTag, inputShape and input port data is sent to deploymentAPI. The response from the server has numberResults results.

Configuration Parameters

Parameter	Type	Description
oauthClientId	string	Mandatory. Client ID used for the OAuth2 authentication.
oauthClientSecret	string	Mandatory. Client Secret used for the OAuth2 authentication.
oauthTokenUrl	string	Mandatory. URL for the address where the OAuth2 authentication will be performed.
deploymentAPI	list	Mandatory. URL where the status of the server will be checked and the certificate and model host/port will be acquired.
numberResults	integer	Maximum number of results to be returned.
modelName	string	Mandatory. Model name which will process the input.
signatureName	string	Server signature name defined when building the model.
inputTag	string	Mandatory.
inputShape	list	List of integers with the input dimensions.

Input

Input	Type	Description
`config`	message	Input to dynamically change the configurations. Only the message headers are considered. If a field has the same field as the config, then it is considered.
`input`	message	Defines two modes of operation, according to the presence of the header in the message: If the header is empty, the body of the message is considered as the serialized input for the message. Otherwise, the message header, which is a dictionary is considered as the feature dictionary(that will be serialized). It is expected that the dictionaries have the following form: {"<Feature Name>": <[ float\|integer\|unicode ] or float\|integer\|unicode >} A dictionary whose keys are strings, and the values are values or a list of values of types: unicode, integers, float.

Output

Output	Type	Description
`response`	string	The response returned by the server as a string.