More Ways to Make Smart Bots

Today we’re excited to announce we are releasing two new offerings designed to make it easier for you to create smart bots. Here’s a bit more about each:

QnA Maker Service

Brought to you by the same engineers that develop Bing, our latest addition to Microsoft Cognitive Services, QnA Maker is a free, easy-to-use, REST API- and web-based service that trains AI to respond to users’ questions in a more natural, conversational way. With optimized machine learning logic and the ability to integrate industry-leading language processing, QnA Maker Service distills semi-structured data like those commonly found in website FAQs into distinct, helpful answers.

QnA Maker works in three steps: extraction, training and publishing. To start, feed it anything from existing FAQ URLs to documents and editorial content.

QnA Maker extracts all possible pairs of questions and answers, and through the easy-to-use web interface you can edit, remove or add any pairs, as well as test and train the knowledge base.

Once you’re satisfied with the scope of responses, you can publish your knowledge base as an API endpoint.

Even after publishing, you can review interactions in real time and refine responses as needed. QnA Maker integrates with other APIs and solutions seamlessly and at scale. By using other Cognitive Services with QnA Maker, you can create something as elegantly simple as a chat bot that answers FAQs, or as complex as an interactive virtual guide. Lastly, QnA Maker is also available as a template on Azure Bot Service. Azure Bot Service runs in a serverless environment, and enables rapid intelligent bot development powered by Microsoft Bot Framework. Bots scale based on demand and you pay only for the resources you consume.

Bing Location Control

The open source Bing Location Control for Bot Framework allows bot developers to easily and reliably get the user’s desired location within a conversation. The control is available in C# and Node.js and works consistently across all messaging channels supported by Bot Framework. All this with a few lines of code. Key features include:

  • Address look up and validation via Bing’s Maps REST services.
  • Address disambiguation when more than one address is found.
  • Support for declaring required location fields.
  • Support for FB Messenger’s location picker GUI dialog.
  • The control is open-source, with fully-customizable and localizable dialog strings, and is available here on github (awaiting your feedback and contributions)

Happy Making! The Bot Framework and Cognitive Services Teams