[fix] error on invoke HuggingFaceEndpoint Bad request: following model_kwargs #27020
+54
−21
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Outdated suggestions cannot be applied.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 invoke error on HuggingFaceEndpoint: "fix invoke error HuggingFaceEndpoint Bad request"
Bad request: The following model_kwargs are not used by the model: ['return_full_text', 'stop', 'watermark', 'stop_sequences']
this is due to the fact that the call function send those parameters to the huggingface inferenceClient and huggingface raise an error if those parameters are not used, in this specific case, the user should set the unused parameters to None on the invoker.
however for the specific case of 'stop_sequences' and 'stop', if we set them up to None an error occured because the call was still trying to iterate through the stop_sequences parameter and concatenate it
Add tests and docs: modified integration_tests/llms/test_huggingface_endpoint.py file to reflect the change, tests did not work properly previously.
also added a note on HuggingFaceEndpoint docstring to inform users.