Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add bf orchestrator support for Question Answering #1339

Open
jrpavoncello opened this issue Apr 8, 2022 · 3 comments
Open

Add bf orchestrator support for Question Answering #1339

jrpavoncello opened this issue Apr 8, 2022 · 3 comments
Labels
feature-request A request for new functionality or an enhancement to an existing one. needs-triage The issue has just been created and it has not been reviewed by the team.

Comments

@jrpavoncello
Copy link

Possibly related to #6413

Our Chatbot project is built in BotFramework-SDK using Dispatch CLI, some LUIS models, and some QnA Maker KBs. We're looking to migrate to Question Answering but we're stuck because we use Dispatch CLI, which is no longer supported, and Orchestrator doesn't seem to have support for it.

Feature Request: Add bf orchestrator support for adding models from Question Answering / Language Cognitive Service knowledge bases / projects.

@jrpavoncello jrpavoncello added feature-request A request for new functionality or an enhancement to an existing one. needs-triage The issue has just been created and it has not been reviewed by the team. labels Apr 8, 2022
@jrpavoncello
Copy link
Author

If this can't be achieved, is it possible to pause the scheduled deprecation of creating new QnA Maker resources in Azure? I don't know how many other customers are in our boat, but we relied on the Dispatch CLI to glue together our QnA/LUIS resources as is recommended in Microsoft's documentation, but Dispatch is deprecated by Orchestrator, QnA Maker is deprecated by Question Answering, so there's no path forward for us.

@rajeeshmenoth
Copy link

Are there any updates on this feature request? We are also facing the same problem and, @jrpavoncello the only way we can achieve this functionality using an inbuilt orchestrator in Langauge studio but if we are really planning to do it through code then the respective team should answer.

@jrpavoncello
Copy link
Author

@rajeeshmenoth This is a day late, a dollar short for those affected, but our team ended up writing a script to convert the Custom Question Answering exported model.json over to a TSV file for consumption by orchestrator as a qna file.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feature-request A request for new functionality or an enhancement to an existing one. needs-triage The issue has just been created and it has not been reviewed by the team.
Projects
None yet
Development

No branches or pull requests

2 participants