microsoft
Import error with 'from markitdown import MarkItDown'
When I do:
from markitdown import MarkItDown
I get the following error:
AttributeError Traceback (most recent call last) Cell In[14], line 1 ----> 1 from markitdown import MarkItDown 2 md = MarkItDown(enable_plugins=True) # Set to True to enable plugins 3 result = md.convert("spirometry-orig-gwy-pdf_1000423---Imported-Spirometry-Doc.pdf")
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\markitdown_init_.py:6 1 # SPDX-FileCopyrightText: 2024-present Adam Fourney [email protected] 2 # 3 # SPDX-License-Identifier: MIT 5 from .about import version ----> 6 from ._markitdown import ( 7 MarkItDown, 8 PRIORITY_SPECIFIC_FILE_FORMAT, 9 PRIORITY_GENERIC_FILE_FORMAT, 10 ) 11 from ._base_converter import DocumentConverterResult, DocumentConverter 12 from ._stream_info import StreamInfo
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\markitdown_markitdown.py:25 22 from ._stream_info import StreamInfo 23 from ._uri_utils import parse_data_uri, file_uri_to_path ---> 25 from .converters import ( 26 PlainTextConverter, 27 HtmlConverter, 28 RssConverter, 29 WikipediaConverter, 30 YouTubeConverter, 31 IpynbConverter, 32 BingSerpConverter, 33 PdfConverter, 34 DocxConverter, 35 XlsxConverter, 36 XlsConverter, 37 PptxConverter, 38 ImageConverter, 39 AudioConverter, 40 OutlookMsgConverter, 41 ZipConverter, 42 EpubConverter, 43 DocumentIntelligenceConverter, 44 ) 46 from ._base_converter import DocumentConverter, DocumentConverterResult 48 from ._exceptions import ( 49 FileConversionException, 50 UnsupportedFormatException, 51 FailedConversionAttempt, 52 )
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\markitdown\converters_init_.py:14 12 from ._pdf_converter import PdfConverter 13 from ._docx_converter import DocxConverter ---> 14 from ._xlsx_converter import XlsxConverter, XlsConverter 15 from ._pptx_converter import PptxConverter 16 from ._image_converter import ImageConverter
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\markitdown\converters_xlsx_converter.py:12 10 _xlsx_dependency_exc_info = None 11 try: ---> 12 import pandas as pd 13 import openpyxl 14 except ImportError:
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\pandas_init_.py:151 132 from pandas.core.computation.api import eval 134 from pandas.core.reshape.api import ( 135 concat, 136 lreshape, (...) 148 qcut, 149 ) --> 151 from pandas import api, arrays, errors, io, plotting, tseries 152 from pandas import testing 153 from pandas.util._print_versions import show_versions
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\pandas\api_init_.py:2 1 """ public toolkit API """ ----> 2 from pandas.api import ( 3 extensions, 4 indexers, 5 interchange, 6 types, 7 typing, 8 ) 10 all = [ 11 "interchange", 12 "extensions", (...) 15 "typing", 16 ]
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\pandas\api\typing_init_.py:31 19 from pandas.core.window import ( 20 Expanding, 21 ExpandingGroupby, (...) 26 Window, 27 ) 29 # TODO: Can't import Styler without importing jinja2 30 # from pandas.io.formats.style import Styler ---> 31 from pandas.io.json._json import JsonReader 32 from pandas.io.stata import StataReader 34 all = [ 35 "DataFrameGroupBy", 36 "DatetimeIndexResamplerGroupby", (...) 54 "Window", 55 ]
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\pandas\io\json_init_.py:1 ----> 1 from pandas.io.json._json import ( 2 read_json, 3 to_json, 4 ujson_dumps, 5 ujson_loads, 6 ) 7 from pandas.io.json._table_schema import build_table_schema 9 all = [ 10 "ujson_dumps", 11 "ujson_loads", (...) 14 "build_table_schema", 15 ]
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\pandas\io\json_json.py:71 66 from pandas.io.json._normalize import convert_to_line_delimits 67 from pandas.io.json._table_schema import ( 68 build_table_schema, 69 parse_table_schema, 70 ) ---> 71 from pandas.io.parsers.readers import validate_integer 73 if TYPE_CHECKING: 74 from collections.abc import ( 75 Hashable, 76 Mapping, 77 )
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\pandas\io\parsers_init_.py:1 ----> 1 from pandas.io.parsers.readers import ( 2 TextFileReader, 3 TextParser, 4 read_csv, 5 read_fwf, 6 read_table, 7 ) 9 all = ["TextFileReader", "TextParser", "read_csv", "read_fwf", "read_table"]
File c:\Users\C825005\Desktop\OCR.venv\Lib\site-packages\pandas\io\parsers\readers.py:32 29 from pandas._config import using_copy_on_write 31 from pandas._libs import lib ---> 32 from pandas._libs.parsers import STR_NA_VALUES 33 from pandas.errors import ( 34 AbstractMethodError, 35 ParserWarning, 36 ) 37 from pandas.util._decorators import Appender
File parsers.pyx:1418, in init pandas._libs.parsers()
AttributeError: partially initialized module 'pandas' has no attribute '_pandas_parser_CAPI' (most likely due to a circular import)
Hey there @neilbhutada,
I had the same issue :(, but I solved it by downgrading to markitdown[all] == 0.1.0
