Updating embeddings: 0%| | 0/1398 [00:02Traceback (most recent call last):
File "C:\Users\Administrator\PaddleNLP\pipelines\utils\offline_ann.py", line 149, in
offline_ann(args.index_name, args.doc_dir)
File "C:\Users\Administrator\PaddleNLP\pipelines\utils\offline_ann.py", line 118, in offline_ann
document_store.update_embeddings(retriever)
File "D:\Anaconda\envs\nlp\lib\site-packages\paddle_pipelines-0.5.3-py3.9.egg\pipelines\document_stores\elasticsearch.py", line 1529, in update_embeddings
embeddings = retriever.embed_documents(document_batch) # type: ignore
File "D:\Anaconda\envs\nlp\lib\site-packages\paddle_pipelines-0.5.3-py3.9.egg\pipelines\nodes\retriever\dense.py", line 365, in embed_documents
embeddings = self._get_predictions(passages, **kwargs)["passages"]
File "D:\Anaconda\envs\nlp\lib\site-packages\paddle_pipelines-0.5.3-py3.9.egg\pipelines\nodes\retriever\dense.py", line 324, in _get_predictions
cls_embeddings = self.passage_encoder(datasets[i : i + self.batch_size], **kwargs)
File "D:\Anaconda\envs\nlp\lib\site-packages\paddlenlp\taskflow\taskflow.py", line 850, in __call__
results = self.task_instance(inputs)
File "D:\Anaconda\envs\nlp\lib\site-packages\paddlenlp\taskflow\task.py", line 516, in __call__
outputs = self._run_model(inputs)
File "D:\Anaconda\envs\nlp\lib\site-packages\paddlenlp\taskflow\text_feature_extraction.py", line 274, in _run_model
self.predictor.run()
RuntimeError: (PreconditionNotMet) The meta data must be valid when call the mutable data function.
[Hint: Expected valid() == true, but received valid():0 != true:1.] (at ..\paddle\phi\core\dense_tensor.cc:122)
[operator < fill_constant > error]

求大神指点