Uh oh!
There was an error while loading. Please reload this page.
Update the muxing rules to v3 - #1112
Conversation
aponcedeleonch
commented
Feb 19, 2025
Marking as draft because this would break the FE. We need to coordinate to merge |
lukehinds
commented
Feb 20, 2025
API Version 3? |
peppescg
commented
Feb 20, 2025
on it stacklok/codegate-ui#319 👨💻 |
Uh oh!
There was an error while loading. Please reload this page.
JAORMX
commented
Feb 20, 2025
uhm... I'd be careful with having a v3 that's not backwards compatible without more usecases. This already starts looking too optimized for fim/chat in a way that it might not cater for other rule types. |
As I see it, it will be optimized for the request type. Right now we can only distinguish between 2 request types, fim or chat. Hence the types we have. In the future we would be able to match more request types, e.g. request type: Persona based. But I was afraid of the same thing, of the types being very restrictive. In the end I convince myself that it wasn't as restrictive as I initially thought. But of course all discussions welcomed and any feedback is appreciated 😃 |
JAORMX
commented
Feb 20, 2025
Let's see this in action and I'll keep reviewing in the meantime. |
0edea97 to
0890c1aCompare9ea1504 to
d5957e0CompareCloses: #1060 Right now the muxing rules are designed to catch globally FIM or Chat requests. This PR extends its functionality to be able to match per file and request, i.e. this PR enables - Chat request of main.py -> model 1 - FIM request of main.py -> model 2 - Any type of v1.py -> model 3
d5957e0 to
34f4f02Compare
Closes: #1060
Right now the muxing rules are designed to catch globally FIM or Chat requests. This PR extends its functionality to be able to match per file and request, i.e. this PR enables