Refactor OCR configuration in DoclingParser to use EasyOCR exclusively

Enhance DoclingParser for CPU-only processing and improved error handling

Implement ZeroGPU support in DoclingParser for enhanced document processing

Enhance README and parser functionality for improved document processing

Integrate Gemini API for enhanced image processing in MarkItDown

Refactor document ingestion and chunking to support LaTeX content

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

Enhance multi-document processing capabilities in parsers

Implement multi-document processing capabilities and enhance UI

Refactor document ingestion and output file handling

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

Update .gitignore and enhance README with data management instructions

Add Docling support for advanced document processing

Refactor and enhance application structure for Markit_v2

Minor UI edit

New feature: Mistral OCR

Initial Implementation of Markitdown. Implemented:

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

restore to version 1

Latex2Markdown display changes --attemtp1

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

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

runtime error fix

Please work

handling zerogpu usage

enable zerogpu

CUDA dfloat 16 issue again

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

changes on logging for better debugging

missing run_ocr_2.0.py file

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

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

restore to check point

failed to load got ocr model

Error: Too many output

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

adding format=true

complete reimplementation of got ocr

complete reimplementation of got ocr

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

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

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

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

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

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

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

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

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

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

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