Sergey Filimonov open-parse Issues

Filimoa/open-parse Issues

No whitespace in text?
Closed a month ago2
ImportError: cannot import name 'DocumentParser' from partially initialized module 'openparse'
Closed 2 months ago2
Config Object failing with AttributeError: module 'torch' has no attribute 'cuda'
Closed 2 months ago2
PyMuPdf Hierarchal Headings
Closed 2 months ago2
open parse seems missing some blocks within pdf file
Updated 2 months ago3
Missing parts of documents
Updated 2 months ago3
nodes output
Closed 3 months ago6
Is the purpose of this project to interpret and comprehensively analyze the content of PDF documents?
Closed 3 months ago1
🚀 Roadmap
Updated 3 months ago8
ValueError: Coordinate 'right' is less than 'left'
Updated 3 months ago1
Request to Add License Information to PyPI
Closed 3 months ago1
integration to llamaindex and langchain
Closed 3 months ago3
Does the original image information in the PDF need to be parsed?
Updated 3 months ago1
Named temp directory never clears temp files
Closed 3 months ago3
NoneType error occured in pymupdf.output_to_markdown function
Closed 3 months ago1
TypeError: sequence item 13: expected str instance, NoneType found
Closed 3 months ago1
Ollama integration
Closed 3 months ago2
Different Embedding Models
Updated 3 months ago1
Improving Table Performance
Updated 3 months ago8
Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
Closed 3 months ago5
UniTable Cookbook notebook has errors
Closed 3 months ago3
Unable to run library following provided steps
Closed 3 months ago2
support for Litellm module and Azure , aws OCR modules
Closed 3 months ago1
ScannedPDF
Closed 3 months ago2
TypeError: Rect.__init__() got an unexpected keyword argument 'x0'
Closed 4 months ago1
NameError: name 'display' is not defined
Closed 4 months ago1

Filimoa / open-parse

Filimoa/open-parse Issues

No whitespace in text?

ImportError: cannot import name 'DocumentParser' from partially initialized module 'openparse'

Config Object failing with AttributeError: module 'torch' has no attribute 'cuda'

PyMuPdf Hierarchal Headings

open parse seems missing some blocks within pdf file

Missing parts of documents

nodes output

Is the purpose of this project to interpret and comprehensively analyze the content of PDF documents?

🚀 Roadmap

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

Request to Add License Information to PyPI

integration to llamaindex and langchain

Does the original image information in the PDF need to be parsed?

Named temp directory never clears temp files

NoneType error occured in pymupdf.output_to_markdown function

TypeError: sequence item 13: expected str instance, NoneType found

Ollama integration

Different Embedding Models

Improving Table Performance

Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

UniTable Cookbook notebook has errors

Unable to run library following provided steps

support for Litellm module and Azure , aws OCR modules

ScannedPDF

TypeError: Rect.init() got an unexpected keyword argument 'x0'

NameError: name 'display' is not defined