Recognise Key Phrases - Text Analytics

[SaiPreetha]

I download the Text Analytics Skill from DX and integrated with BP.

While using the actions of the skill, I am able to successfully execute "Detect Language", where as, I get an error when going with "Recognise Key Phrases" as below,

Internal : Unexpected error Cannot execute action "Recognise Key Phrases" due to an error when running custom code: Column 'Language' does not belong to table Collection_of_Documents.

The input I am providing for this is an unstructured text of 4-5 lines in the form of collection. 

Please advice on the steps/procedure to be followed to perform this action

------------------------------
Sai Preetha
------------------------------

[ewilson · Accepted solution]

Hi Sai,

I believe the collection requires a column titled "Language" which includes information about the language of each document. In other words, the Azure service is expects you to tell it the language of each document you're wanting it to review instead of it trying to detect the language and then detect the key phases.

Does that make sense?

Here's a link to the Microsoft documentation that discusses what languages are supported and the specific language codes to use: Azure Text Analytics Languages

Cheers,

------------------------------
Eric Wilson
Director, Partner Integrations for Digital Exchange
Blue Prism
------------------------------