AFM support for RAG Applications

Question

Created Oct ’24

Replies 4

Boosts 0

Participants 3

I‘m excited at the development possibilities presented by Apple Intelligence and have begun imagining retrieval augmented generation use cases. Writing tools suggest that this is possible, but I have not seen any direct statements by Apple regarding use of AFMs for RAG applications. Have any references to APIs or sample code for RAG applications been published?

Answered by Engineer in 809543022

Hello @XaepStudio, thank you for your post. There's no supported way for you to implement RAG with the APIs currently available.

If you'd like us to consider adding the necessary functionality, please file an enhancement request using Feedback Assistant. Once you file the request, please post the FB number here.

If you're not familiar with how to file enhancement requests, take a look at Bug Reporting: How and Why?

Boost

Answer 1

Engineer OP

Apple

Oct ’24

Accepted Answer

Hello @XaepStudio, thank you for your post. There's no supported way for you to implement RAG with the APIs currently available.

If you'd like us to consider adding the necessary functionality, please file an enhancement request using Feedback Assistant. Once you file the request, please post the FB number here.

If you're not familiar with how to file enhancement requests, take a look at Bug Reporting: How and Why?

1

Answer 2

XaepStudio OP

3w

Thank you @Engineer. Enhancement request filed - FB15586322 (Apple Intelligence RAG Support).

0

Answer 3

Donovan OP

3w

Enhancement request updated: FB15596260 Apple Intelligence RAG Support.

0

Answer 4

XaepStudio OP

1w

Follow-up question: Does the following Apple Intelligence API allow RAG use case support via Siri: https://developer.apple.com/documentation/appintents/making-onscreen-content-available-to-siri-and-apple-intelligence ?

For example can the file or document schema be used to submit the following to Siri/Apple Intelligence for conversational interrogation: a) a file or document with the content to be evaluated and (b) another file with context information ?

The expectation is that the user could ask Siri questions about file/document (a) and Siri will respond based on assessment that includes contextual information provided in file/document (b).

Any thoughts/ideas/suggestions are appreciated.

0