RDM Beta AI Assistant?
are any docs available yet for configuring the Ai Assistant RDM entry, I am currently attempting to use an Azure Open Ai provider but have been unable to get a response other than errors, my first question is the providers, I see in the drop down several GPT options but the field does take text, I've been attempting to use the model name as stated on azure 'DeepSeek-R1', I have also tried using various endpoint URLs and keys found on AI Foundry but none have worked yet, I will try a model listed in the RDM provider dropdown next but I assumed it would work with any Model / Provider is this not the case? Since AI Foundry also provides multiple endpoint URLs I am left to trial and error.
Any guidance would be appreciated for Azure Open AI.
Thanks
JK
Devolutions Force Member (and Long time Devolutions Fan)
All Comments (18)
Hello John,
I'm the one that did the integration. Our integration use the Semantic Kernel:
I'm not sure what could be missing. Are you sure that the model you entered is deployed on your Azure resource?
Regards
David Hervieux
Ive just managed to get the GPT-4O model to run using the endpoint containing openai, then once I set the token count to 4096 it worked.
But cant say the same with DeepSeek-R1 model yet using the same steps I got working for the above model??
Ill look at the link you provided, I really want to be able to use custom models created....
JK
Devolutions Force Member (and Long time Devolutions Fan)
Hello,
The list provided is only to simplify the configuration. It's not linked to anything. For example, I could add DeepSeek-R1 to the choices, so I suspect that something is missing in your Azure, or maybe it's not the model name in the Azure catalog. I will ask my team to deploy it for me and test it if you can't get it working.
Regards
David Hervieux