Llamaparse doesnt seem to extract the full file for example the heading and footer of the file. It doesnt recognize the footer in this case ( sometimes header as well ) which is a very important factor for me to determine the section when im building a rag
You could try to add a parsing instruction: "do not remove page footer" for the model. Alternatively, I will add an api parameter to allow deactivation of this feature
I see, that would be much appreciated as I'm building a data extraction RAG SAAS that can let anyone modify the instructions so that would be very useful. Thank you
