Extract pdf text

in form got file attachment, basically pdf attachment. then it will upload the pdf inside the google drive,
issue: i want to make the Ai Agent to extract input from the pdf to have output, such as name, age, address etc, mostly on personal details. so how can i make it happen?

Hi @Amnan_Sani, welcome to community!
You need to use RAG. See here for some example

i still have no idea :smiling_face_with_tear:

Hi Amman! If you want to return specific data in a required output, you can activate in the Agent the option “Require Specific Output Format” and then add the “Structured Output Parser” giving an example to the Agent. This will extract exactly the data you want from the PDF. You can edit and add as many values as you want, just be sure to tell the Agent in the prompt what values need to be extracted and how to handle edge cases (if the information is not provided.).


hey @Amnan_Sani here is a workflow which can extract information from pdf.
I have only added name, address and age:
you can finetune it to your needs:

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.