5 likes
·
447 reads
3 comments
Wow - what a powerful new AI feature and clever use case too. Thank you - a terrific blog I will reference through my studies.
Thank you Sandra! I'm glad you liked it. You can share with them the previous one too - how to run it with local open-source LLMs for free (instead of using OpenAI, Cohere or OCI, which are all paid options).
Hi there!
Good writeup.
I am wondering whether you can give me some clues for these questions:
- While using the APEX AI Assistant there are literally no other controls what so ever for the end user. For example, a) I only want a user to ask a maximum of 5 questions. b) I only want a user chat interaction should last for a maximum 5 minutes c) There is no "User Consent" acceptance mechanism to this interface so as to show some disclaimer or a compliance note, so as to cover any applicable Data Privacy laws GDPR/HIPAA/etc. Once the chat bot is invoked, except from tuning the "system prompt" there are no other hard controls.
These kind of controls seem to be necessary so as that some vicious user won't overwhelm the system, or I would like to control the budget for my backend OpenAI/Cohere/OCI paid services. Even Windows Copilot on my PC has 30 questions per session!
Do you think, these kind of controls be acheived using the da.ai.xxxx mechanism? Can you throw any light on that?
2) Apart from using the AI Assistant from DA, did you happen to use the APEX_AI.GENERATE method via Server-side Script? Because that API is offering some methods on user consent; however when tried to use them I got stumbled because literally there is "NO" documentation what so ever on this aspect. Can you elaborate on this ?
Regards
Ravi