Open
Description
Huggingface transformers.ConversationalPipeline is removed from the pinned version of transformers (now 4.43.1), breaking the conversational
transform task. Huggingface transformers spits out the following:
pyo3_runtime.PanicException: Error calling next on GeneralJsonIterator: error returned from database: Traceback (most recent call last):
File "transformers.py", line 489, in transform
File "transformers.py", line 463, in create_pipeline
File "transformers.py", line 343, in __init__
File "/opt/pgml-env/lib/python3.10/site-packages/transformers/pipelines/__init__.py", line 849, in pipeline
normalized_task, targeted_task, task_options = check_task(task)
File "/opt/pgml-env/lib/python3.10/site-packages/transformers/pipelines/__init__.py", line 533, in check_task
return PIPELINE_REGISTRY.check_task(task)
File "/opt/pgml-env/lib/python3.10/site-packages/transformers/pipelines/base.py", line 1350, in check_task
raise KeyError(
KeyError: "Unknown task conversational, available tasks are ['audio-classification', 'automatic-speech-recognition', 'depth-estimation', 'document-question-answering', 'feature-extraction', 'fill-mask', 'image-classification', 'image-feature-extraction', 'image-segmentation', 'image-to-image', 'image-to-text', 'mask-generation', 'ner', 'object-detection', 'question-answering', 'sentiment-analysis', 'summarization', 'table-question-answering', 'text-classification', 'text-generation', 'text-to-audio', 'text-to-speech', 'text2text-generation', 'token-classification', 'translation', 'video-classification', 'visual-question-answering', 'vqa', 'zero-shot-audio-classification', 'zero-shot-classification', 'zero-shot-image-classification', 'zero-shot-object-detection', 'translation_XX_to_YY']"