Find answers from the community

Updated 8 months ago

Llamaparse doesnt recognize all heading/footer

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

anyone can help with it?
Attachment
image.png
Y
L
p
7 comments
need some help thank you
Hi! Taking a look.
In this case we are activelly removing the footer as sometime it will impact table reconstruction.
But i understand it is not ideal for your use case.
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
Add a reply
Sign up and join the conversation on Discord