TypeError: __init__() got an unexpected keyword argument 'detection_class_prob'

[Jimchoo91]

I tried uploading a 50 page PDF using the API, and received this error?

TypeError: init() got an unexpected keyword argument 'detection_class_prob'

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-199-16b05c99d0ba> in <module>
     10 )
     11 
---> 12 docs = loader.load()

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in load(self)
     84     def load(self) -> List[Document]:
     85         """Load file."""
---> 86         elements = self._get_elements()
     87         if self.mode == "elements":
     88             docs: List[Document] = list()

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in _get_elements(self)
    267 
    268     def _get_elements(self) -> List:
--> 269         return get_elements_from_api(
    270             file_path=self.file_path,
    271             api_key=self.api_key,

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in get_elements_from_api(file_path, file, api_url, api_key, **unstructured_kwargs)
    202         from unstructured.partition.api import partition_via_api
    203 
--> 204         return partition_via_api(
    205             filename=file_path,
    206             file=file,

/opt/anaconda3/lib/python3.8/site-packages/unstructured/partition/api.py in partition_via_api(filename, content_type, file, file_filename, api_url, api_key, **request_kwargs)
     86                 "metadata_filename must be specified as well.",
     87             )
---> 88         files = [
     89             ("files", (metadata_filename, file, content_type)),  # type: ignore
     90         ]

/opt/anaconda3/lib/python3.8/site-packages/unstructured/staging/base.py in elements_from_json(filename, text, encoding)
    117     """Loads a list of elements from a JSON file or a string."""
    118     exactly_one(filename=filename, text=text)
--> 119 
    120     if filename:
    121         with open(filename, encoding=encoding) as f:

/opt/anaconda3/lib/python3.8/site-packages/unstructured/staging/base.py in dict_to_elements(element_dict)
    100                     metadata=metadata,
    101                 ),
--> 102             )
    103 
    104     return elements

/opt/anaconda3/lib/python3.8/site-packages/unstructured/staging/base.py in isd_to_elements(isd)
     75 def isd_to_elements(isd: List[Dict[str, Any]]) -> List[Element]:
     76     """Converts an Initial Structured Data (ISD) dictionary to a list of elements."""
---> 77     elements: List[Element] = []
     78 
     79     for item in isd:

/opt/anaconda3/lib/python3.8/site-packages/unstructured/documents/elements.py in from_dict(cls, input_dict)
    171         if isinstance(self.filename, pathlib.Path):
    172             self.filename = str(self.filename)
--> 173 
    174         if self.filename is not None:
    175             file_directory, filename = os.path.split(self.filename)

Anyone seen this before?

[awalker4]

Hi there, we identified a breaking change in the latest version of the library. We've rolled back the hosted api while we work on a fix.

[Jimchoo91]

Just to let you know, there is now a new error when using the UnstructuredAPIFileLoader in LangChain which seems related:

TypeError                                 Traceback (most recent call last)
<ipython-input-361-d7f06958231b> in <module>
      9 )
     10 
---> 11 chev_docs_1 = loader.load()

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in load(self)
     84     def load(self) -> List[Document]:
     85         """Load file."""
---> 86         elements = self._get_elements()
     87         if self.mode == "elements":
     88             docs: List[Document] = list()

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in _get_elements(self)
    267 
    268     def _get_elements(self) -> List:
--> 269         return get_elements_from_api(
    270             file_path=self.file_path,
    271             api_key=self.api_key,

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in get_elements_from_api(file_path, file, api_url, api_key, **unstructured_kwargs)
    202         from unstructured.partition.api import partition_via_api
    203 
--> 204         return partition_via_api(
    205             filename=file_path,
    206             file=file,

/opt/anaconda3/lib/python3.8/site-packages/unstructured/partition/api.py in partition_via_api(filename, content_type, file, file_filename, api_url, api_key, **request_kwargs)
     86                 "metadata_filename must be specified as well.",
     87             )
---> 88         files = [
     89             ("files", (metadata_filename, file, content_type)),  # type: ignore
     90         ]

/opt/anaconda3/lib/python3.8/site-packages/unstructured/staging/base.py in elements_from_json(filename, text, encoding)
    117     """Loads a list of elements from a JSON file or a string."""
    118     exactly_one(filename=filename, text=text)
--> 119 
    120     if filename:
    121         with open(filename, encoding=encoding) as f:

/opt/anaconda3/lib/python3.8/site-packages/unstructured/staging/base.py in dict_to_elements(element_dict)
    100                     metadata=metadata,
    101                 ),
--> 102             )
    103 
    104     return elements

/opt/anaconda3/lib/python3.8/site-packages/unstructured/staging/base.py in isd_to_elements(isd)
     75 def isd_to_elements(isd: List[Dict[str, Any]]) -> List[Element]:
     76     """Converts an Initial Structured Data (ISD) dictionary to a list of elements."""
---> 77     elements: List[Element] = []
     78 
     79     for item in isd:

/opt/anaconda3/lib/python3.8/site-packages/unstructured/documents/elements.py in from_dict(cls, input_dict)
    171     # Metadata extracted via regex
    172     regex_metadata: Optional[Dict[str, List[RegexMetadata]]] = None
--> 173 
    174     # Detection Model Class Probabilities from Unstructured-Inference Hi-Res
    175     detection_class_prob: Optional[float] = None

TypeError: __init__() got an unexpected keyword argument 'parent_id'

Now it is an issue with 'parent_id'. I updated the Unstructured library as recommended too and this error also occurred there.

[awalker4]

Thanks for the heads up. Can you double check that the update command took you to unstructured>=0.10.15? This should fix the problem. I make a pr against langchain to enforce this as the new minimum version.

[Jimchoo91]

Thanks for replying, the version is 0.10.16.

[awalker4]

Strange, that version should know about parent_id. In any case, I removed the new field from the api, which should resolve this. Let me know if you're still having issues through Langchain.

[Jimchoo91]

Thanks @awalker4, I tried running my query again and now receive a new error - should I put this in a separate bug?

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-369-d7f06958231b> in <module>
      9 )
     10 
---> 11 chev_docs_1 = loader.load()

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in load(self)
     84     def load(self) -> List[Document]:
     85         """Load file."""
---> 86         elements = self._get_elements()
     87         if self.mode == "elements":
     88             docs: List[Document] = list()

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in _get_elements(self)
    267 
    268     def _get_elements(self) -> List:
--> 269         return get_elements_from_api(
    270             file_path=self.file_path,
    271             api_key=self.api_key,

/opt/anaconda3/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py in get_elements_from_api(file_path, file, api_url, api_key, **unstructured_kwargs)
    202         from unstructured.partition.api import partition_via_api
    203 
--> 204         return partition_via_api(
    205             filename=file_path,
    206             file=file,

/opt/anaconda3/lib/python3.8/site-packages/unstructured/partition/api.py in partition_via_api(filename, content_type, file, file_filename, api_url, api_key, **request_kwargs)
     88         files = [
     89             ("files", (metadata_filename, file, content_type)),  # type: ignore
---> 90         ]
     91         response = requests.post(
     92             api_url,

ValueError: Receive unexpected status code 504 from the API.

[awalker4]

Yes please! That looks like a transient network error so be sure to retry and create a new issue if it persists.

[Jimchoo91]

Hi @awalker4, I raised this a couple of weeks ago on the following link:

https://github.com/Unstructured-IO/unstructured-api/issues/255

I still see the problem, any idea what it may be? I have also received a new one 'ValueError: Receive unexpected status code 502 from the API.'