[FEAT] Capturing the caption of the figure or tables

[Maikiii44]

💡 Cap

It would be helpful for the model to identify images in a document or scientific paper and determine the corresponding caption for each. The output could be in the JSON.

[kipavy]

💡 Cap

It would be helpful for the model to identify images in a document or scientific paper and determine the corresponding caption for each. The output could be in the JSON.

Are you talking about this ? https://github.com/datalab-to/marker/issues/838

[ankit8347]

please can you provide code with llm