图片无法转换

[hgmsq]

测试结果图片不能转换到md文档里面

[SigireddyBalasai]

make sure that you are using latest version

[hgmsq]

Today, I tested directly using the pip command to install dependency packages.

[SigireddyBalasai]

Today, I tested directly using the pip command to install dependency packages.

so any problem ?

[SigireddyBalasai]

if possible include full context your os the version of python you are using and the error message

[BlackPool888]

I also cannot output image content,I can only get the main idea of the images,oops~

[BlackPool888]

Python:3.12

e.g:

[SigireddyBalasai]

@BlackPool888 i think you are getting what is intended for giving image input you will get description

[BlackPool888]

@SigireddyBalasai Right,I get it now,I had expected to receive the main content,not just a description,thx

[KmBase]

https://github.com/microsoft/markitdown/issues/51 ,you can comment the code

[happy-xlf]

md = MarkItDown(llm_client=client, llm_model="gpt-4o") ,图片转md需要提供llm的接口才能识别

[neverlatetolearn0]

@SigireddyBalasai Right,I get it now,I had expected to receive the main content,not just a description,thx

This may require an OCR approach

[neverlatetolearn0]

md = MarkItDown(llm_client=client, llm_model="gpt-4o") ,图片转md需要提供llm的接口才能识别

This method can summarize the content of the picture, but can not identify the text in the picture, how to extract the text in the picture

[wking2014]

Insert the pictures in the PDF document into the corresponding positions in the Markdown document. This cannot be achieved.

[zenoda]

md = MarkItDown(llm_client=client, llm_model="gpt-4o") ,图片转md需要提供llm的接口才能识别

This method can summarize the content of the picture, but can not identify the text in the picture, how to extract the text in the picture

I also need this feature!