Hugging Face's logo

Spaces:
Ansemin101
/
Markit_v2
Running

App Files Community
Markit_v2 / src /parsers

Commit History

Refactor OCR configuration in DoclingParser to use EasyOCR exclusively
18e6067

AnseMin commited on

Enhance DoclingParser for CPU-only processing and improved error handling
5e0609f

AnseMin commited on

Implement ZeroGPU support in DoclingParser for enhanced document processing
d66e90c

AnseMin commited on

Enhance README and parser functionality for improved document processing
4a97b0c

AnseMin commited on

Integrate Gemini API for enhanced image processing in MarkItDown
033e4ba

AnseMin commited on

Refactor document ingestion and chunking to support LaTeX content
63279a9

AnseMin commited on

Enhance Docling and Mistral OCR parsers with improved response handling and logging
c61b4e2

AnseMin commited on

Enhance multi-document processing capabilities in parsers
d437733

AnseMin commited on

Implement multi-document processing capabilities and enhance UI
111954a

AnseMin commited on

Refactor document ingestion and output file handling
3f1b4af

AnseMin commited on

Import configuration from core module in gemini_flash_parser.py to enhance parser functionality.
63f3b68

AnseMin commited on

Update .gitignore and enhance README with data management instructions
a4f1c9e

AnseMin commited on

Add Docling support for advanced document processing
c0c51c2

AnseMin commited on

Refactor and enhance application structure for Markit_v2
a773878

AnseMin commited on

Minor UI edit
55627c9

AnseMin commited on

New feature: Mistral OCR
98482ce

AnseMin commited on

Initial Implementation of Markitdown. Implemented:
dbdd7c8

AnseMin commited on

Approach #2 -- converting latex output from GOT OCR to markdown
5b7f920

AnseMin commited on

restore to version 1
23ad33e

AnseMin commited on

Latex2Markdown display changes --attemtp1
33f1b65

AnseMin commited on

Error: Error processing document with GOT-OCR: cannot pickle '_thread.lock' object
4cac30a

AnseMin commited on

ERROR - Failed to load GOT-OCR model: CUDA must not be initialized in the main process on Spaces with Stateless GPU environment.
3415bc4

AnseMin commited on

runtime error fix
36e49b4

Ansemin101 commited on

Please work
4fab3b3

AnseMin commited on

handling zerogpu usage
610b772

AnseMin commited on

enable zerogpu
62f9c09

AnseMin commited on

CUDA dfloat 16 issue again
dcdb7ac

AnseMin commited on

fixing the missing path of run_ocr_2.0.py by editing got_ocr_parser.py
7d77a56

AnseMin commited on

changes on logging for better debugging
5bb2b30

AnseMin commited on

missing run_ocr_2.0.py file
c9c21c7

AnseMin commited on

change in strategy --implementing github got ocr instead of hugging face model
0f5865d

AnseMin commited on

script to convert markdown to latex, changing UI output to fit right with got ocr
ad248f7

AnseMin commited on

restore to check point
2184c47

AnseMin commited on

failed to load got ocr model
f89451e

AnseMin commited on

Error: Too many output
fa54d05

AnseMin commited on

Error: Error processing document with GOT-OCR: GOTQwenForCausalLM.chat() got an unexpected keyword argument 'format'
c4c3253

AnseMin commited on

adding format=true
1312a63

AnseMin commited on

complete reimplementation of got ocr
3332d94

AnseMin commited on

complete reimplementation of got ocr
b61bec6

AnseMin commited on

Error: Error processing document with GOT-OCR: Current CUDA Device does not support bfloat16. Please switch dtype to float16.
6d39d2f

AnseMin commited on

Error: Error processing document with GOT-OCR: 'QWenTokenizer' object has no attribute 'startswith'
e5648b4

AnseMin commited on

Error: Error processing document with GOT-OCR: GotOcrParser._load_model..patched_chat() takes 3 positional arguments but 4 were given
e045d86

AnseMin commited on

Error: Error processing document with GOT-OCR: 'QWenTokenizer' object has no attribute 'startswith'
dbc3034

AnseMin commited on

Error: Error processing document with GOT-OCR: GOTQwenForCausalLM.chat() got multiple values for argument 'ocr_type'
932831a

AnseMin commited on

Error: Error processing document with GOT-OCR: GOTQwenForCausalLM.chat() got multiple values for argument 'ocr_type'
7f767e4

AnseMin commited on

Error: Error processing document with GOT-OCR: GOTQwenForCausalLM.chat() got multiple values for argument 'ocr_type'
ca43ad2

AnseMin commited on

Error: Error processing document with GOT-OCR: GOTQwenForCausalLM.chat() got multiple values for argument 'ocr_type'
0fb1586

AnseMin commited on

Error: Error processing document with GOT-OCR: Current CUDA Device does not support bfloat16. Please switch dtype to float16.
d95f73e

AnseMin commited on

Error: Error processing document with GOT-OCR: Current CUDA Device does not support bfloat16. Please switch dtype to float16.
84a7af0

AnseMin commited on

Error: Error processing document with GOT-OCR (ZeroGPU): Numpy is not available
6372663

AnseMin commited on