Filimoa/open-parse issues and pull requests

#64 - Add support for ImageElements -> Parse images

Pull Request - State: open - Opened by ic-xu 9 days ago - 7 comments

#63 - Method to convert `ParsedDocument` object to LlamaIndex `Document` object

Issue - State: open - Opened by mjspeck about 1 month ago - 1 comment

#62 - Update doc on export of bboxes visualization

Pull Request - State: closed - Opened by Kydlaw about 1 month ago

#61 - Fix Documentation

Issue - State: closed - Opened by moraneden about 1 month ago - 2 comments
Labels: bug

#58 - Table Extraction Tool

Issue - State: open - Opened by xyzdeclan about 2 months ago - 1 comment

#57 - Some PDF documents cannot be parsed

Issue - State: open - Opened by tiamjiakun about 2 months ago - 3 comments
Labels: bug

#56 - add langchain document support

Issue - State: open - Opened by priamai 2 months ago - 3 comments

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

Issue - State: closed - Opened by anthopit 2 months ago
Labels: bug

#52 - add homebrew installation path + fix linux prefix setting

Pull Request - State: closed - Opened by Gregory-Pereira 3 months ago - 1 comment

#51 - Whitespace Issues

Pull Request - State: closed - Opened by Filimoa 3 months ago

#50 - No whitespace in text?

Issue - State: closed - Opened by Filimoa 4 months ago - 2 comments

#48 - Fixes LTAnno objects being skipped which contains the needed whitespace for some PDFs

Pull Request - State: closed - Opened by cipherCOM 4 months ago - 5 comments

#47 - Fix CI & merge conflicts

Pull Request - State: closed - Opened by amonras 4 months ago - 1 comment

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

Issue - State: closed - Opened by Bruce337f 5 months ago - 1 comment

#41 - Llama Index Integration

Pull Request - State: closed - Opened by Filimoa 5 months ago

#40 - open parse seems missing some blocks within pdf file

Issue - State: open - Opened by DinoLiww 5 months ago - 3 comments
Labels: bug

#39 - [Memory Leak Fix] Create Fitz Pdf From Bytestream

Pull Request - State: closed - Opened by Filimoa 5 months ago

#38 - Named temp directory never clears temp files

Issue - State: closed - Opened by bradfox2 5 months ago - 3 comments
Labels: bug

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

Issue - State: open - Opened by ic-xu 5 months ago - 1 comment
Labels: enhancement

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

Issue - State: closed - Opened by spar025 5 months ago - 2 comments
Labels: bug

#35 - PyMuPdf Hierarchal Headings

Issue - State: closed - Opened by mingzhang798 5 months ago - 2 comments
Labels: enhancement

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

Issue - State: closed - Opened by aman-paco 5 months ago - 2 comments
Labels: bug

#33 - Fix layout inversion bug

Pull Request - State: open - Opened by ic-xu 5 months ago - 2 comments

#32 - #29 [minor tweak to mashihua's branch]

Pull Request - State: closed - Opened by Filimoa 5 months ago

#31 - TypeError: sequence item 13: expected str instance, NoneType found

Issue - State: closed - Opened by mingzhang798 5 months ago - 1 comment
Labels: bug

#30 - Ollama integration

Issue - State: closed - Opened by Kydlaw 5 months ago - 2 comments

#29 - Fix bug with parse.py

Pull Request - State: closed - Opened by mashihua 5 months ago - 1 comment

#28 - NoneType error occured in pymupdf.output_to_markdown function

Issue - State: closed - Opened by mashihua 5 months ago - 1 comment
Labels: bug

#27 - fix: Fix sequence item 2: expected str instance, NoneType found exception when table output is set to markdown.

Pull Request - State: closed - Opened by ic-xu 5 months ago

#26 - Improving Table Performance

Issue - State: open - Opened by brianjking 5 months ago - 10 comments
Labels: bug

#24 - update the cookbooks link

Pull Request - State: closed - Opened by brianjking 5 months ago

#23 - More Embedding Models [Draft]

Pull Request - State: open - Opened by Filimoa 5 months ago

#22 - Request to Add License Information to PyPI

Issue - State: closed - Opened by fixxtion1 5 months ago - 1 comment

#21 - support embeddings via ollama

Pull Request - State: closed - Opened by miku 5 months ago - 3 comments

#20 - Update pymupdf.md

Pull Request - State: closed - Opened by ada-lovecraft 5 months ago - 1 comment

#19 - Global PyTorch Config

Pull Request - State: closed - Opened by Filimoa 5 months ago

#18 - fix cuda device error for tableformer/unitable

Pull Request - State: closed - Opened by jinmang2 5 months ago - 1 comment

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

Issue - State: closed - Opened by fjw1049 5 months ago - 5 comments

#15 - integration to llamaindex and langchain

Issue - State: closed - Opened by saitej123 6 months ago - 3 comments
Labels: enhancement

#13 - UniTable Cookbook notebook has errors

Issue - State: closed - Opened by zacharysmithdatatonic 6 months ago - 3 comments

#12 - Unable to run library following provided steps

Issue - State: closed - Opened by dvalletj 6 months ago - 2 comments
Labels: bug

#11 - ValueError: Coordinate 'right' is less than 'left'

Issue - State: open - Opened by atgreen 6 months ago - 2 comments
Labels: bug, good first issue

#10 - support for Litellm module and Azure , aws OCR modules

Issue - State: closed - Opened by saitej123 6 months ago - 2 comments

#9 - Missing parts of documents

Issue - State: open - Opened by zby 6 months ago - 3 comments

#8 - Different Embedding Models

Issue - State: open - Opened by gvlx 6 months ago - 2 comments
Labels: enhancement

#7 - nodes output

Issue - State: closed - Opened by atgreen 6 months ago - 6 comments

#6 - Unitable

Pull Request - State: closed - Opened by Filimoa 6 months ago

#5 - ScannedPDF

Issue - State: closed - Opened by atulpant 6 months ago - 2 comments
Labels: enhancement

GitHub / Filimoa/open-parse issues and pull requests