fix Hyperbolic / Qwen message format #4008
Closed
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Short description of the problem this fixes or functionality that this introduces. This may be used for the CHANGELOG
Fix Qwen non-vision expected message format.
Give a summary of what the PR does, explaining any non-trivial design decisions
This addresses a regression from #3832: Hyperbolic supports both vision and non-vision formats, but separately, each for the respective LLM. If the LLM doesn't have vision enabled, the API returns 400 for
role=user
messages in vision-like format. So the compromise that PR 3832 tried to make doesn't work.This PR proposes to support the two formats for now with flags for the type of format:
vision_enabled
andcache_enabled
. It continues to use Pydantic serialization mechanism, restructured a bit. The flag is set per Message.Link of any specific issues this addresses
#4004