The Start Operator enables users to define data formats customized for their AI-first applications.

#Release stage


#Operator Configuration

The operator configuration is used for setting up the input data and parameters of this component. The configuration is configured in pipeline recipe, please refer to pipeline for more details.

metadata*map<string, object>You can setup the pipeline trigger request fields here
metadata.<key>.title*stringThe title of the field
metadata.<key>.type*stringThe type of the field. Available types: text, image, audio, number, integer, boolean, text_array, image_array, audio_array, number_array, integer_array
metadata.<key>.descriptionstringThe description of the field.

#No-code setup

#Low-code setup

This is a sample configuration in the pipeline recipe.

"configuration": {
"metadata": {
"prompt": {
"title": "Prompt",
"type": "text"
"number": {
"title": "Number",
"type": "number"

When you send the request, you can use this request format

curl --location 'http://localhost:8080/vdp/v1alpha/users/<user-id>/pipelines/<pipeline-id>/trigger' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <api_token>' \
--data '{
"inputs": [
"prompt": "How are you",
"number": 10

For other operations, please refer to the VDP Protobufs.

Last updated: 11/2/2023, 4:56:49 PM