Handle TGI error when streaming tokens #1711
Merged
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Outdated suggestions cannot be applied.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.
Fix #1651.
When streaming tokens from a TGI server, an error might happen and be returned in the stream of tokens. At the moment this raises a pydantic ValidationError as it's not recognized as a proper
TextGenerationStreamResponse
. This PR adds a check to parse correctly the error message + raise a custom exception whenever possible.cc @osanseviero @OlivierDehaene
Note: I couldn't really test this PR as the problem is hard to reproduce (it happened in the falcon-180b demo Space which has heavy usage -see thread (internal)). Shouldn't be too risky though (error/error_type being optional client-side).