Filimoa / open-parse

Improved file parsing for LLM’s
https://filimoa.github.io/open-parse/
MIT License
2.34k stars 89 forks source link

ValueError: Coordinate 'right' is less than 'left'" #55

Closed anthopit closed 1 month ago

anthopit commented 1 month ago

Initial Checks

Description

When trying to extract tables from a pdf file with unitable I have the following error:

ValueError: Coordinate 'right' is less than 'left' "

Screenshot 2024-07-10 at 18 09 12

Example Code

doc_with_tables_path = "./pdf/table.pdf"

parser = openparse.DocumentParser(
    table_args={"parsing_algorithm": "unitable"}
)
parsed_doc2 = parser.parse(doc_with_tables_path)

Python, open-parse & OS Version

python_version: 3.10.11
             operating_system: Darwin
                   os_version: 23.1.0
           open-parse version: 0.5.7
                 install path: /Users/user/RAG-Test/.venv/lib/python3.10/site-packages/openparse
               python version: 3.10.11 (v3.10.11:7d4cc5aa85, Apr  4 2023, 19:05:19) [Clang 13.0.0 (clang-1300.0.29.30)]
                     platform: macOS-14.1-arm64-arm-64bit
             related packages: tokenizers-0.19.1 torchvision-0.18.1 pydantic-2.8.0 transformers-4.42.3 PyMuPDF-1.24.7 torch-2.3.1