Filimoa open-parse issues

Filimoa / open-parse

Improved file parsing for LLM’s

https://filimoa.github.io/open-parse/

MIT License

2.54k stars 99 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

can add got ocr2 support?

#87 mmxuan18 opened 9 hours ago
0
No nodes are extracted from some PDFs

#85 faileon opened 1 week ago
0
JPGs and PNGs images in the PDF

#84 tulas75 opened 1 week ago
0
PNG Bug

#83 Filimoa closed 2 weeks ago
1
Image example

#80 NuiMrme closed 2 weeks ago
1
two column PDF

#79 wawaa opened 4 weeks ago
0
nvfghekvskvsdhkvsdu,l

#78 bcdbs closed 1 month ago
0
get_mime_type bugfix

#76 dongcartney92 closed 2 weeks ago
1
solved error with code 400 from openai api for invalid input

#75 mihaidobrescu1111 opened 1 month ago
0
'dict' object has no attribute 'name'

#74 qkxie closed 2 weeks ago
2
Adding support for Azure OpenAI

#73 leonardobaggio opened 1 month ago
1
BadRequestError: Error code: 400

#72 NuiMrme closed 2 weeks ago
11
Add Arabic support

#71 mohamed99akram opened 1 month ago
0
Parser throws internal error

#70 LtSalt opened 1 month ago
0
scientific formula capturing

#67 Zabih-khan opened 2 months ago
0
Parse images pdf miner

#66 Filimoa closed 2 months ago
0
Add support for ImageElements -> Parse images

#64 ic-xu closed 2 months ago
7
Method to convert `ParsedDocument` object to LlamaIndex `Document` object

#63 mjspeck opened 3 months ago
1
Update doc on export of bboxes visualization

#62 Kydlaw closed 3 months ago
0
Fix Documentation

#61 moraneden closed 3 months ago
2
Table Extraction Tool

#58 xyzdeclan opened 3 months ago
1
Some PDF documents cannot be parsed

#57 tiamjiakun opened 4 months ago
3
add langchain document support

#56 priamai opened 4 months ago
3
ValueError: Coordinate 'right' is less than 'left'"

#55 anthopit closed 4 months ago
0
add homebrew installation path + fix linux prefix setting

#52 Gregory-Pereira closed 5 months ago
1
Whitespace Issues

#51 Filimoa closed 5 months ago
0
No whitespace in text?

#50 Filimoa closed 5 months ago
2
Fixes LTAnno objects being skipped which contains the needed whitespace for some PDFs

#48 cipherCOM closed 5 months ago
5
Fix CI & merge conflicts

#47 amonras closed 6 months ago
1
Is the purpose of this project to interpret and comprehensively analyze the content of PDF documents?

#42 Bruce337f closed 6 months ago
1
Llama Index Integration

#41 Filimoa closed 6 months ago
0
open parse seems missing some blocks within pdf file

#40 DinoLiww opened 7 months ago
3
[Memory Leak Fix] Create Fitz Pdf From Bytestream

#39 Filimoa closed 7 months ago
0
Named temp directory never clears temp files

#38 bradfox2 closed 7 months ago
3
Does the original image information in the PDF need to be parsed?

#37 ic-xu opened 7 months ago
1
ImportError: cannot import name 'DocumentParser' from partially initialized module 'openparse'

#36 spar025 closed 5 months ago
2
PyMuPdf Hierarchal Headings

#35 mingzhang798 closed 5 months ago
2
Config Object failing with AttributeError: module 'torch' has no attribute 'cuda'

#34 aman-paco closed 5 months ago
2
Fix layout inversion bug

#33 ic-xu closed 2 months ago
2
#29 [minor tweak to mashihua's branch]

#32 Filimoa closed 7 months ago
0
TypeError: sequence item 13: expected str instance, NoneType found

#31 mingzhang798 closed 7 months ago
1
Ollama integration

#30 Kydlaw closed 7 months ago
2
Fix bug with parse.py

#29 mashihua closed 7 months ago
1
NoneType error occured in pymupdf.output_to_markdown function

#28 mashihua closed 7 months ago
1
fix: Fix sequence item 2: expected str instance, NoneType found exception when table output is set to markdown.

#27 ic-xu closed 7 months ago
0
Improving Table Performance

#26 brianjking opened 7 months ago
10
update the cookbooks link

#24 brianjking closed 7 months ago
0
More Embedding Models [Draft]

#23 Filimoa opened 7 months ago
0
Request to Add License Information to PyPI

#22 fixxtion1 closed 6 months ago
1
support embeddings via ollama

#21 miku closed 7 months ago
3