23.1 aztext overview

20210610

A free Azure subscription allowing up to 5,000 text records per month (last checked at Azure Pricing 20210701) is available from Microsoft at https://azure.microsoft.com/free/. A text record is 1,000 characters. After subscribing visit the Azure Portal at https://portal.azure.com and Create a resource under AI and Machine Learning called Text Analytics. Once created you can access the web API subscription key and endpoint from the portal. These will be prompted for when you configure the package. The credentials will be saved to file to reduce the need for repeated authentication requests.

The first time you will be asked to enter the key and cloud endpoint:

$ ml configure aztext
Private information is required to access this service.
See the README for more details.

Please paste your Text Analytics key: *************************
Please paste your endpoint: https://myaztext.cognitiveservices.azure.com/

That information has been saved into the file:

    /home/kayon/.mlhub/aztext/private.json

If the file containing the private information already exists, you will be given a chance to display or edit the file, or else to load the private information from the file:

$ ml configure aztext
The following file has been found and is assumed to
contain the private information.

    /home/kayon/.mlhub/aztext/private.json

Use this private information ('d' to display, 'n' to update) [Y/d/n]?

The default response is Y (i.e., yes) but if you’d like to have a look at the key first then use d (i.e., display). To enter new information select n (i.e., respond no to loading the current private information).


Your donation will support ongoing availability and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2022 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0