PDF to Markdown

Hi all,

Was just wondering what the most native way to go from PDF or docx to markdown is? I know some of the model providers allow for uploading docx and PDF into their APIs. Is there anyway to do this programatically in Palantir? For example, I think you can do it in Agent Studio but can’t call to agent studio from an automate.

This would be super helpful!

Best,
Jack

Model providers where this seems to be available:

  • https://cloud.google.com/vertex-ai/generative-ai/docs/samples/generativeaionvertexai-gemini-pdf#generativeaionvertexai_gemini_pdf-nodejs
  • https://community.openai.com/t/converting-pdf-to-markdown-with-ocr/762476/2
  • https://support.anthropic.com/en/articles/8241126-what-kinds-of-documents-can-i-upload-to-claude-ai