[ML] Removing error object check in inference API #132502
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Outdated suggestions cannot be applied.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.
This PR refactors the error handling logic within the inference API to remove some error handling code that is no longer needed after a previous refactoring PR.
Prior to this PR: #123076 we needed to check for the presence of an error object in the response from a 3rd party service. We needed to do this because some services would return a 200 and not label the message as an error within the SSE. So we would check if the body of the response looked like an error and if so we'd parse it as an error and return a failure.
After the retrying work for streaming we moved the structure check within the streaming parsing logic and no longer need to do it within the
BaseResponseHandler.