deploymentClient
Performs the OAuth2 authentication using oauthClientId and oauthClientSecret on oauthTokenUrl and sends the request to the server. Deploys model from MLF Model Repository for subsequent inference. The server responds with the deployment status.
Configuration Parameters
|
Parameter |
Type |
Description |
|---|---|---|
|
oauthClientId |
string |
Client ID used for the OAuth2 authentication. |
|
oauthClientSecret |
string |
Client Secret used for the OAuth2 authentication. |
|
oauthTokenUrl |
string |
Url for the address where the OAuth2 authentication will be performed. |
|
deploymentAPI |
string |
Url where the model is deployed to. |
|
version |
string |
API Version |
| resourcePlan | string | Resource Plan used to deploy the model. For example: cpu-small-1-4 uses 1 CPU and 4GB of Memory. |
| useInput | bool | If set to true, the output from modelRepoClient is expected to be connected to modelRepoStatus.The statusCode header must be "201" and the values of namespace, modelName and modelVersion are defined from headers. If set to false, modelRepoStatus works as a signal to do the request, and new configuration parameters set to namespace, modelName and, modelVersion appear. |
| namespace | string | Namespace used. |
| modelVersion | string | Version of the model to be deployed. |
| modelName | string | Name of the model to be deployed. |
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, it is overridden |
|
modelRepoStatus |
message |
The model repo upload status. Connection with MLF Model Repository operator is expected. |
Output
|
Output |
Type |
Description |
|---|---|---|
|
response |
string |
Server response as free form string. |