-
Notifications
You must be signed in to change notification settings - Fork 75
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
Fix FIM on Continue. Have specific formatters for chat and FIM #1015
Conversation
Still testing. Opened a PR to check if I hadn't broken something using CI |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I know this is a draft, but I think this patch makes sense and in general I think this is caused by openai python libraries being bumped in litellm. I noticed that the new versions don't support prompt anymore.
92a7698
to
c4c75b5
Compare
Until now we had a general formatter on the way out of muxing. This is wrong since sometimes the pipelines respond with different format for chat or FIM. Such is the case for Ollama. This PR separates the formatters and declares them explicitly so that they're easier to adjust in the future.
c4c75b5
to
095bcbb
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
minor comments, feel free to address them in subsequent PRs
Closes: #1005
Until now we had a general formatter on the way out of muxing. This is wrong since sometimes the pipelines respond with different format for chat or FIM. Such is the case for Ollama.
This PR separates the formatters and declares them explicitly so that they're easier to adjust in the future.