The Appian AI offering supports the integration of Google AI services in your Appian application. As part of the offering, the Google Cloud Translation connected system enables you to quickly and easily detect the language of a piece of text, and then translate it into the desired language. Once you're connected, you can call an integration in your process model or interface so you can dynamically detect and translate text, allowing you to communicate information quickly and effectively.
To use this connected system, you must have a Google Service Account. If you are an Appian AI customer, you are provided with fully setup and managed Google Cloud services by Appian on your behalf. Contact your Appian technical contact administrator for your service account credentials. Learn how to enroll in Appian AI, or to continue using the connected system with your own Google Cloud account, ensure you've set up the required Google Cloud service credentials.
In addition to the common properties, the Google Cloud Vision connected system has the following properties:
|Project ID||Found in your Google Service Account file.|
|Private Key ID||Found in your Google Service Account file.|
|Private Key||Found in your Google Service Account file.|
|Client Email||Found in your Google Service Account file.|
|Client ID||Found in your Google Service Account file.|
|Detect Language||Discovers languages from provided text||READ|
|Translate Text||Translates provided text||READ|
Detect and obtain the language of a piece of text. The detected language will return as a language code. See a list of supported languages to see which language matches the language code.
Detect the source language of a piece of plain or HTML text and translate it into the language of your choosing. To dynamically translate content, consider adding a rule input in your integration to pass different values to translate.
By default, text is translated using the Neural Machine Translation (NMT) model. If the NMT model is not supported for the requested language translation pair, then the Phrase-Based Machine Translation (PBMT) model is used. The runtime model will be returned in the result.
On This Page