Extracting Data from PDFs for Use in Clay: Seeking Solutions

·

Hey 02 Support, I need to extract a specific value from annual account PDFs. I’ve tried using several AI models (OpenAI + Claygent) but they clearly aren’t meant to read raw PDFs directly. Has anyone here run into a similar problem and found a good (preferably free) way to transform PDFs into text or JSON so the data can then be extracted in Clay?

🎫1

4 comments

· Sorted by Oldest

Noah
·
·
Amit Kallakuri https://app.clay.com/workspaces/314705/workbooks/wb_0t1p0jyGPQ9ApXgVDZN/tables/t_0t1p0jyu8TqHAJA4XMF/views/gv_0t1p0jyvH62sW7qHZFj
Noah
·
·
Right now i'm trying to convert the pdf's to xlsx files and then extracting but this is not optimal either. So if you have a solution that works in Clay i'm still interested yes
Amit Kallakuri
·
·
Hey Noah, a workaround you can try is using document context. This allows you to use the chatGPT integration specifically reading those PDFs. Hope this helps!
Noah
·
·
Thanks for the tip, Amit! I'll definitely try this out. For now, everything is working smoothly with the n8n setup.

Noah
·
·
Amit Kallakuri https://app.clay.com/workspaces/314705/workbooks/wb_0t1p0jyGPQ9ApXgVDZN/tables/t_0t1p0jyu8TqHAJA4XMF/views/gv_0t1p0jyvH62sW7qHZFj
Noah
·
·
Right now i'm trying to convert the pdf's to xlsx files and then extracting but this is not optimal either. So if you have a solution that works in Clay i'm still interested yes
Amit Kallakuri
·
·
Hey Noah, a workaround you can try is using document context. This allows you to use the chatGPT integration specifically reading those PDFs. Hope this helps!
Noah
·
·
Thanks for the tip, Amit! I'll definitely try this out. For now, everything is working smoothly with the n8n setup.