# Error on pipeline with docquery (Transformers) **URL:** \ **Category:** 🤗Transformers\ **Created:** [May 12, 2023, 3:51pm UTC](https://discuss.huggingface.co/t/error-on-pipeline-with-docquery-transformers/39672 "2023-05-12T15:51:11Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![Jack-cpu](https://avatars.discourse-cdn.com/v4/letter/j/49beb7/32.png) [@Jack-cpu](https://discuss.huggingface.co/u/Jack-cpu)\ **Post date:** [May 12, 2023, 3:51pm UTC](https://discuss.huggingface.co/t/error-on-pipeline-with-docquery-transformers/39672/1 "2023-05-12T15:51:11Z")
Hello, I’ve tried to implement docquery with different models like impira/layoutlm-invoices but I always have the same error (on collab notebook or pycharm, windows or ubuntu always the same): Code : from docquery import document, pipeline p = pipeline(task=‘document-question-answering’, model = “impira/layoutlm-invoices”) doc = document.load\_document(file) s = p(question=“What is the invoice number?”, \*\*doc.context) Error : Exception Traceback (most recent call last) Cell In[76], line 5 3 p = pipeline(task=‘document-question-answering’, model = “impira/layoutlm-invoices”) 4 doc = document.load\_document(file) ----\> 5 s = p(question=“What is the invoice number?”, \*\*doc.context) File ~\Documents\GitHub\Llama\venv\lib\site-packages\docquery\ext\pipeline\_document\_question\_answering.py:232, in DocumentQuestionAnsweringPipeline. **call** (self, image, question, \*\*kwargs) 229 else: 230 normalized\_images = [(image, None)] → 232 return super(). **call** ({“question”: question, “pages”: normalized\_images}, \*\*kwargs) File ~\Documents\GitHub\Llama\venv\lib\site-packages\transformers\pipelines\base.py:1111, in Pipeline. **call** (self, inputs, num\_workers, batch\_size, \*args, \*\*kwargs) 1109 return self.iterate(inputs, preprocess\_params, forward\_params, postprocess\_params) 1110 elif self.framework == “pt” and isinstance(self, ChunkPipeline): → 1111 return next( 1112 iter( 1113 self.get\_iterator( 1114 [inputs], num\_workers, batch\_size, preprocess\_params, forward\_params, postprocess\_params 1115 ) 1116 ) 1117 ) 1118 else: 1119 return self.run\_single(inputs, preprocess\_params, forward\_params, postprocess\_params) File ~\Documents\GitHub\Llama\venv\lib\site-packages\transformers\pipelines\pt\_utils.py:124, in PipelineIterator. **next** (self) 121 return self.loader\_batch\_item() 123 # We’re out of items within a batch → 124 item = next(self.iterator) 125 processed = self.infer(item, \*\*self.params) 126 # We now have a batch of “inferred things”. File ~\Documents\GitHub\Llama\venv\lib\site-packages\transformers\pipelines\pt\_utils.py:291, in PipelinePackIterator. **next** (self) 289 else: 290 item = processed → 291 is\_last = item.pop(“is\_last”) 292 accumulator.append(item) 293 return accumulator File ~\Documents\GitHub\Llama\venv\lib\site-packages\transformers\utils\generic.py:310, in ModelOutput.pop(self, \*args, \*\*kwargs) 309 def pop(self, \*args, \*\*kwargs): → 310 raise Exception(f"You cannot use `pop` on a {self. **class**. **name** } instance.") Exception: You cannot use `pop` on a ModelOutput instance. Thank you for your help. ---
**Author:** ![noexiste](https://avatars.discourse-cdn.com/v4/letter/n/f1d935/32.png) [@noexiste](https://discuss.huggingface.co/u/noexiste)\ **Post date:** [June 2, 2023, 9:32am UTC](https://discuss.huggingface.co/t/error-on-pipeline-with-docquery-transformers/39672/2 "2023-06-02T09:32:21Z")
I had the same error and was able to get rid of it by downgrading the transformers library like this: ```auto pip uninstall transformers pip install transformers==4.23 ``` ---
**Author:** ![Jack-cpu](https://avatars.discourse-cdn.com/v4/letter/j/49beb7/32.png) [@Jack-cpu](https://discuss.huggingface.co/u/Jack-cpu)\ **Post date:** [June 5, 2023, 11:49am UTC](https://discuss.huggingface.co/t/error-on-pipeline-with-docquery-transformers/39672/3 "2023-06-05T11:49:33Z")
Thank you, it works