Repository Not Found for url: https://huggingface.co/api/models/ds4sd/docling-models/revision/v2.1.0.

[thistleknot]

Bug

...

Steps to reproduce

from docling.document_converter import DocumentConverter

source = r"C:\Users\User\Documents\wiki\wiki\RPG\microlite\2020\Microlite2020-Core-Rules-1.02.pdf"  # document per local path or URL
converter = DocumentConverter()
result = converter.convert(source)
print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"

...

Docling version

2.20.0
python 3.10
windows 11
...

Python version

...

---------------------------------------------------------------------------
HTTPError                                 Traceback (most recent call last)
File [h:\python310\lib\site-packages\huggingface_hub\utils\_http.py:406](file:///H:/python310/lib/site-packages/huggingface_hub/utils/_http.py#line=405), in hf_raise_for_status(response, endpoint_name)
    405 try:
--> 406     response.raise_for_status()
    407 except HTTPError as e:

File [h:\python310\lib\site-packages\requests\models.py:1024](file:///H:/python310/lib/site-packages/requests/models.py#line=1023), in Response.raise_for_status(self)
   1023 if http_error_msg:
-> 1024     raise HTTPError(http_error_msg, response=self)

HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models/ds4sd/docling-models/revision/v2.1.0

The above exception was the direct cause of the following exception:

RepositoryNotFoundError                   Traceback (most recent call last)
Cell In[2], line 5
      3 source = r"C:\Users\User\Documents\wiki\wiki\RPG\microlite\2020\Microlite2020-Core-Rules-1.02.pdf"  # document per local path or URL
      4 converter = DocumentConverter()
----> 5 result = converter.convert(source)
      6 print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"

File [h:\python310\lib\site-packages\pydantic\_internal\_validate_call.py:38](file:///H:/python310/lib/site-packages/pydantic/_internal/_validate_call.py#line=37), in update_wrapper_attributes.<locals>.wrapper_function(*args, **kwargs)
     36 @functools.wraps(wrapped)
     37 def wrapper_function(*args, **kwargs):
---> 38     return wrapper(*args, **kwargs)

File [h:\python310\lib\site-packages\pydantic\_internal\_validate_call.py:111](file:///H:/python310/lib/site-packages/pydantic/_internal/_validate_call.py#line=110), in ValidateCallWrapper.__call__(self, *args, **kwargs)
    110 def __call__(self, *args: Any, **kwargs: Any) -> Any:
--> 111     res = self.__pydantic_validator__.validate_python(pydantic_core.ArgsKwargs(args, kwargs))
    112     if self.__return_pydantic_validator__:
    113         return self.__return_pydantic_validator__(res)

File [h:\python310\lib\site-packages\docling\document_converter.py:203](file:///H:/python310/lib/site-packages/docling/document_converter.py#line=202), in DocumentConverter.convert(self, source, headers, raises_on_error, max_num_pages, max_file_size, page_range)
    185 @validate_call(config=ConfigDict(strict=True))
    186 def convert(
    187     self,
   (...)
    193     page_range: PageRange = DEFAULT_PAGE_RANGE,
    194 ) -> ConversionResult:
    195     all_res = self.convert_all(
    196         source=[source],
    197         raises_on_error=raises_on_error,
   (...)
    201         page_range=page_range,
    202     )
--> 203     return next(all_res)

File [h:\python310\lib\site-packages\docling\document_converter.py:226](file:///H:/python310/lib/site-packages/docling/document_converter.py#line=225), in DocumentConverter.convert_all(self, source, headers, raises_on_error, max_num_pages, max_file_size, page_range)
    223 conv_res_iter = self._convert(conv_input, raises_on_error=raises_on_error)
    225 had_result = False
--> 226 for conv_res in conv_res_iter:
    227     had_result = True
    228     if raises_on_error and conv_res.status not in {
    229         ConversionStatus.SUCCESS,
    230         ConversionStatus.PARTIAL_SUCCESS,
    231     }:

File [h:\python310\lib\site-packages\docling\document_converter.py:261](file:///H:/python310/lib/site-packages/docling/document_converter.py#line=260), in DocumentConverter._convert(self, conv_input, raises_on_error)
    252 _log.info(f"Going to convert document batch...")
    254 # parallel processing only within input_batch
    255 # with ThreadPoolExecutor(
    256 #    max_workers=settings.perf.doc_batch_concurrency
    257 # ) as pool:
    258 #   yield from pool.map(self.process_document, input_batch)
    259 # Note: PDF backends are not thread-safe, thread pool usage was disabled.
--> 261 for item in map(
    262     partial(self._process_document, raises_on_error=raises_on_error),
    263     input_batch,
    264 ):
    265     elapsed = time.monotonic() - start_time
    266     start_time = time.monotonic()

File [h:\python310\lib\site-packages\docling\document_converter.py:302](file:///H:/python310/lib/site-packages/docling/document_converter.py#line=301), in DocumentConverter._process_document(self, in_doc, raises_on_error)
    298 valid = (
    299     self.allowed_formats is not None and in_doc.format in self.allowed_formats
    300 )
    301 if valid:
--> 302     conv_res = self._execute_pipeline(in_doc, raises_on_error=raises_on_error)
    303 else:
    304     error_message = f"File format not allowed: {in_doc.file}"

File [h:\python310\lib\site-packages\docling\document_converter.py:323](file:///H:/python310/lib/site-packages/docling/document_converter.py#line=322), in DocumentConverter._execute_pipeline(self, in_doc, raises_on_error)
    319 def _execute_pipeline(
    320     self, in_doc: InputDocument, raises_on_error: bool
    321 ) -> ConversionResult:
    322     if in_doc.valid:
--> 323         pipeline = self._get_pipeline(in_doc.format)
    324         if pipeline is not None:
    325             conv_res = pipeline.execute(in_doc, raises_on_error=raises_on_error)

File [h:\python310\lib\site-packages\docling\document_converter.py:289](file:///H:/python310/lib/site-packages/docling/document_converter.py#line=288), in DocumentConverter._get_pipeline(self, doc_format)
    283 # TODO this will ignore if different options have been defined for the same pipeline class.
    284 if (
    285     pipeline_class not in self.initialized_pipelines
    286     or self.initialized_pipelines[pipeline_class].pipeline_options
    287     != pipeline_options
    288 ):
--> 289     self.initialized_pipelines[pipeline_class] = pipeline_class(
    290         pipeline_options=pipeline_options
    291     )
    292 return self.initialized_pipelines[pipeline_class]

File [h:\python310\lib\site-packages\docling\pipeline\standard_pdf_pipeline.py:88](file:///H:/python310/lib/site-packages/docling/pipeline/standard_pdf_pipeline.py#line=87), in StandardPdfPipeline.__init__(self, pipeline_options)
     73 if (ocr_model := self.get_ocr_model(artifacts_path=artifacts_path)) is None:
     74     raise RuntimeError(
     75         f"The specified OCR kind is not supported: {pipeline_options.ocr_options.kind}."
     76     )
     78 self.build_pipe = [
     79     # Pre-processing
     80     PagePreprocessingModel(
     81         options=PagePreprocessingOptions(
     82             images_scale=pipeline_options.images_scale
     83         )
     84     ),
     85     # OCR
     86     ocr_model,
     87     # Layout model
---> 88     LayoutModel(
     89         artifacts_path=artifacts_path,
     90         accelerator_options=pipeline_options.accelerator_options,
     91     ),
     92     # Table structure model
     93     TableStructureModel(
     94         enabled=pipeline_options.do_table_structure,
     95         artifacts_path=artifacts_path,
     96         options=pipeline_options.table_structure_options,
     97         accelerator_options=pipeline_options.accelerator_options,
     98     ),
     99     # Page assemble
    100     PageAssembleModel(options=PageAssembleOptions()),
    101 ]
    103 # Picture description model
    104 if (
    105     picture_description_model := self.get_picture_description_model(
    106         artifacts_path=artifacts_path
    107     )
    108 ) is None:

File [h:\python310\lib\site-packages\docling\models\layout_model.py:54](file:///H:/python310/lib/site-packages/docling/models/layout_model.py#line=53), in LayoutModel.__init__(self, artifacts_path, accelerator_options)
     51 device = decide_device(accelerator_options.device)
     53 if artifacts_path is None:
---> 54     artifacts_path = self.download_models() / self._model_path
     55 else:
     56     # will become the default in the future
     57     if (artifacts_path / self._model_repo_folder).exists():

File [h:\python310\lib\site-packages\docling\models\layout_model.py:89](file:///H:/python310/lib/site-packages/docling/models/layout_model.py#line=88), in LayoutModel.download_models(local_dir, force, progress)
     87 if not progress:
     88     disable_progress_bars()
---> 89 download_path = snapshot_download(
     90     repo_id="ds4sd/docling-models",
     91     force_download=force,
     92     local_dir=local_dir,
     93     revision="v2.1.0",
     94 )
     96 return Path(download_path)

File [h:\python310\lib\site-packages\huggingface_hub\utils\_validators.py:114](file:///H:/python310/lib/site-packages/huggingface_hub/utils/_validators.py#line=113), in validate_hf_hub_args.<locals>._inner_fn(*args, **kwargs)
    111 if check_use_auth_token:
    112     kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
--> 114 return fn(*args, **kwargs)

File [h:\python310\lib\site-packages\huggingface_hub\_snapshot_download.py:232](file:///H:/python310/lib/site-packages/huggingface_hub/_snapshot_download.py#line=231), in snapshot_download(repo_id, repo_type, revision, cache_dir, local_dir, library_name, library_version, user_agent, proxies, etag_timeout, force_download, token, local_files_only, allow_patterns, ignore_patterns, max_workers, tqdm_class, headers, endpoint, local_dir_use_symlinks, resume_download)
    225     raise LocalEntryNotFoundError(
    226         "Cannot find an appropriate cached snapshot folder for the specified revision on the local disk and "
    227         "outgoing traffic has been disabled. To enable repo look-ups and downloads online, set "
    228         "'HF_HUB_OFFLINE=0' as environment variable."
    229     ) from api_call_error
    230 elif isinstance(api_call_error, RepositoryNotFoundError) or isinstance(api_call_error, GatedRepoError):
    231     # Repo not found => let's raise the actual error
--> 232     raise api_call_error
    233 else:
    234     # Otherwise: most likely a connection issue or Hub downtime => let's warn the user
    235     raise LocalEntryNotFoundError(
    236         "An error happened while trying to locate the files on the Hub and we cannot find the appropriate"
    237         " snapshot folder for the specified revision on the local disk. Please check your internet connection"
    238         " and try again."
    239     ) from api_call_error

File [h:\python310\lib\site-packages\huggingface_hub\_snapshot_download.py:155](file:///H:/python310/lib/site-packages/huggingface_hub/_snapshot_download.py#line=154), in snapshot_download(repo_id, repo_type, revision, cache_dir, local_dir, library_name, library_version, user_agent, proxies, etag_timeout, force_download, token, local_files_only, allow_patterns, ignore_patterns, max_workers, tqdm_class, headers, endpoint, local_dir_use_symlinks, resume_download)
    146 try:
    147     # if we have internet connection we want to list files to download
    148     api = HfApi(
    149         library_name=library_name,
    150         library_version=library_version,
   (...)
    153         headers=headers,
    154     )
--> 155     repo_info = api.repo_info(repo_id=repo_id, repo_type=repo_type, revision=revision, token=token)
    156 except (requests.exceptions.SSLError, requests.exceptions.ProxyError):
    157     # Actually raise for those subclasses of ConnectionError
    158     raise

File [h:\python310\lib\site-packages\huggingface_hub\utils\_validators.py:114](file:///H:/python310/lib/site-packages/huggingface_hub/utils/_validators.py#line=113), in validate_hf_hub_args.<locals>._inner_fn(*args, **kwargs)
    111 if check_use_auth_token:
    112     kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
--> 114 return fn(*args, **kwargs)

File [h:\python310\lib\site-packages\huggingface_hub\hf_api.py:2748](file:///H:/python310/lib/site-packages/huggingface_hub/hf_api.py#line=2747), in HfApi.repo_info(self, repo_id, revision, repo_type, timeout, files_metadata, expand, token)
   2746 else:
   2747     raise ValueError("Unsupported repo type.")
-> 2748 return method(
   2749     repo_id,
   2750     revision=revision,
   2751     token=token,
   2752     timeout=timeout,
   2753     expand=expand,  # type: ignore[arg-type]
   2754     files_metadata=files_metadata,
   2755 )

File [h:\python310\lib\site-packages\huggingface_hub\utils\_validators.py:114](file:///H:/python310/lib/site-packages/huggingface_hub/utils/_validators.py#line=113), in validate_hf_hub_args.<locals>._inner_fn(*args, **kwargs)
    111 if check_use_auth_token:
    112     kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__name__, has_token=has_token, kwargs=kwargs)
--> 114 return fn(*args, **kwargs)

File [h:\python310\lib\site-packages\huggingface_hub\hf_api.py:2533](file:///H:/python310/lib/site-packages/huggingface_hub/hf_api.py#line=2532), in HfApi.model_info(self, repo_id, revision, timeout, securityStatus, files_metadata, expand, token)
   2531     params["expand"] = expand
   2532 r = get_session().get(path, headers=headers, timeout=timeout, params=params)
-> 2533 hf_raise_for_status(r)
   2534 data = r.json()
   2535 return ModelInfo(**data)

File [h:\python310\lib\site-packages\huggingface_hub\utils\_http.py:454](file:///H:/python310/lib/site-packages/huggingface_hub/utils/_http.py#line=453), in hf_raise_for_status(response, endpoint_name)
    435 elif error_code == "RepoNotFound" or (
    436     response.status_code == 401
    437     and response.request is not None
   (...)
    444     # => for now, we process them as `RepoNotFound` anyway.
    445     # See https://gist.github.com/Wauplin/46c27ad266b15998ce56a6603796f0b9
    446     message = (
    447         f"{response.status_code} Client Error."
    448         + "\n\n"
   (...)
    452         " make sure you are authenticated."
    453     )
--> 454     raise _format(RepositoryNotFoundError, message, response) from e
    456 elif response.status_code == 400:
    457     message = (
    458         f"\n\nBad request for {endpoint_name} endpoint:" if endpoint_name is not None else "\n\nBad request:"
    459     )

RepositoryNotFoundError: 401 Client Error. (Request ID: Root=1-67a77bf7-6e28b5cf441444b8142bc699;bb1fd4a4-a602-460b-b033-5d2d8f4f066e)

Repository Not Found for url: https://huggingface.co/api/models/ds4sd/docling-models/revision/v2.1.0.
Please make sure you specified the correct `repo_id` and `repo_type`.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid credentials in Authorization header

[huijunwu]

saw the same error

(venv-torch-2.4.1) pig@z790:~/study-notes-2023-05$ docling --version
Docling version: 2.21.0
Docling Core version: 2.18.0
Docling IBM Models version: 3.3.1
Docling Parse version: 3.3.0
Python: cpython-312 (3.12.3)
Platform: Linux-6.11.0-17-generic-x86_64-with-glibc2.39
(venv-torch-2.4.1) pig@z790:~/study-notes-2023-05$ docling-tools models download
Downloading layout model...                                                                                                                                             model_downloader.py:36
Traceback (most recent call last):
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status
    response.raise_for_status()
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/requests/models.py", line 1024, in raise_for_status
    raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models/ds4sd/docling-models/revision/v2.1.0

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/bin/docling-tools", line 8, in <module>
    sys.exit(app())
             ^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/typer/main.py", line 338, in __call__
    raise e
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/typer/main.py", line 321, in __call__
    return get_command(self)(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/click/core.py", line 1161, in __call__
    return self.main(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/typer/core.py", line 728, in main
    return _main(
           ^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/typer/core.py", line 197, in _main
    rv = self.invoke(ctx)
         ^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/click/core.py", line 1697, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/click/core.py", line 1697, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/click/core.py", line 1443, in invoke
    return ctx.invoke(self.callback, **ctx.params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/click/core.py", line 788, in invoke
    return __callback(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/typer/main.py", line 703, in wrapper
    return callback(**use_params)
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/docling/cli/models.py", line 77, in download
    output_dir = download_models(
                 ^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/docling/utils/model_downloader.py", line 37, in download_models
    LayoutModel.download_models(
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/docling/models/layout_model.py", line 89, in download_models
    download_path = snapshot_download(
                    ^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/_snapshot_download.py", line 232, in snapshot_download
    raise api_call_error
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/_snapshot_download.py", line 155, in snapshot_download
    repo_info = api.repo_info(repo_id=repo_id, repo_type=repo_type, revision=revision, token=token)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 2704, in repo_info
    return method(
           ^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 2489, in model_info
    hf_raise_for_status(r)
  File "/home/pig/study-notes-2023-05/venv-torch-2.4.1/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status
    raise _format(RepositoryNotFoundError, message, response) from e
huggingface_hub.errors.RepositoryNotFoundError: 401 Client Error. (Request ID: Root=1-67abc5e4-30f0316e65d15f3b7d25f956;4bcbcf5c-1f80-4119-8376-0ba7256bac08)

Repository Not Found for url: https://huggingface.co/api/models/ds4sd/docling-models/revision/v2.1.0.
Please make sure you specified the correct `repo_id` and `repo_type`.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid credentials in Authorization header
(venv-torch-2.4.1) pig@z790:~/study-notes-2023-05$