Как исправить проблему с Docling?

Question

xsezh #хочулето @XSezh

Python
PDF

Как исправить проблему с Docling?

Запускаю пример кода из оффициальной документации:

from docling.document_converter import DocumentConverter

# Change this to a local path or another URL if desired.
# Note: using the default URL requires network access; if offline, provide a
# local file path (e.g., Path("/path/to/file.pdf")).
source = "https://arxiv.org/pdf/2408.09869"

converter = DocumentConverter()
result = converter.convert(source)

# Print Markdown to stdout.
print(result.document.export_to_markdown())

На что сразу же получаю ошибку:

Traceback (most recent call last):
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling\datamodel\document.py", line 171, in __init__
self._init_doc(backend, path_or_stream)
~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling\datamodel\document.py", line 215, in _init_doc
self._backend = backend(self, path_or_stream=path_or_stream)
~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling\backend\docling_parse_v4_backend.py", line 206, in __init__
self.parser = DoclingPdfParser(loglevel="fatal")
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling_parse\pdf_parser.py", line 579, in __init__
self.parser = pdf_parser_v2(level=loglevel)
~~~~~~~~~~~~~^^^^^^^^^^^^^^^^
RuntimeError: filename does not exists: C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling_parse\pdf_resources_v2/glyphs//standard/additional.dat
2025-10-28 20:18:53,881 - INFO - Going to convert document batch...
Traceback (most recent call last):
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\docling_test\docling1.py", line 10, in
result = converter.convert(source)
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\pydantic\_internal\_validate_call.py", line 39, in wrapper_function
return wrapper(*args, **kwargs)
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\pydantic\_internal\_validate_call.py", line 136, in __call__
res = self.__pydantic_validator__.validate_python(pydantic_core.ArgsKwargs(args, kwargs))
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling\document_converter.py", line 237, in convert
return next(all_res)
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling\document_converter.py", line 260, in convert_all
for conv_res in conv_res_iter:
^^^^^^^^^^^^^
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling\document_converter.py", line 332, in _convert
for item in map(
~~~^
process_func,
^^^^^^^^^^^^^
input_batch,
^^^^^^^^^^^^
):
^
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling\document_converter.py", line 379, in _process_document
conv_res = self._execute_pipeline(in_doc, raises_on_error=raises_on_error)
File "C:\Users\Макс\Desktop\VS Code Projects\RAG\.venv\Lib\site-packages\docling\document_converter.py", line 415, in _execute_pipeline
raise ConversionError(f"Input document {in_doc.file} is not valid.")
docling.exceptions.ConversionError: Input document 2408.09869v5.pdf is not valid.
-> Cannot close object, library is destroyed. This may cause a memory leak!