is it available to change output text format to Markdown?

#21
by MhmdSyd - opened

Is there any option to change the output text format to be Markdown format, because I need to parse text from image passing it in the prompt to another LLM

the output format is LaTeX format. how can I change it to be Markdown?

+1 I have the same problem. Would like to know if it suport markdown. The OCR for traditional chinese work like a charm. I would say it compares with OCR result from the flagship Claude sonnet 3.5.

+1 I have the same problem.

I solve by using a temporary solution.

By using pypandoc library to convert result from LaTeX to Markdown.

Really we need support to can select output format style

really, you just need to use a lib for latex -> markdown, LaTeX is the best for what this model does: tables, formulas, etc

@MhmdSyd , could you provide a small guide

You could simply use pandoc to convert latex to markdown.

Is there any library which does Latex to Markdown Conversion accurately. Pypandoc did not work well for me.

Is there any library which does Latex to Markdown Conversion accurately. Pypandoc did not work well for me.

I recommend to use llama3.2-vision for OCR it can generate the output Markdown or any format directly that you need based on you prompt

Sign up or log in to comment