The qna maker service is being retired on the october 31, 2025 (extended from march 31, 2025) A newer version of the question and answering capability is now available as part of azure ai language. Use of the qna program is straightforward Followed by a relevance clause, and click the q/a button for evaluation The qna program can evaluate many queries at the same time It ignores any text not preceded by q:.
To create a query, call the query (array) or query (url, query options) method, depending on the type of the storage you access The query supports method chaining. How to configure cors to enable the azure api management developer portal's interactive test console I am trying to run a query using the “evaluate using query channel using qna”, and it hangs with a message “waiting for evaluation to finish”. It can be used to find the most appropriate answer for any given natural language input, from your custom knowledge base (kb) of information.
There are discrepancies between the test (qna portal) & the published version (api) A correct answer would drop 10%, while a bad answer rises 10%, which ultimately converts good matches in test into bad ones in the bot application. We are using qna maker generate answer api call for qna questions (to fulfill one of the requirement) We have created qnamaker knowledgebase separately on qnamaker.ai portal and not using the composer.
WATCH
