Sign up to take part
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
Extract tables from PDF
Added on February 17, 2025 11:01AM
Likes: 0
Replies: 1
art271
Registered Posts: 3 ✭
Hello community, to perform RAG, I want to extract tables from PDFs. I would like to do this using Dataiku plugins, but the quality is not what I expect. Do you know of other methods to do this? Thanks !
Answers
-
Marlan Neuron 2020, Neuron, Registered, Dataiku Frontrunner Awards 2021 Finalist, Neuron 2021, Neuron 2022, Dataiku Frontrunner Awards 2021 Participant, Neuron 2023 Posts: 330 NeuronWe are using the Azure Document Intelligence solution for converting PDFs. It is working quite well. It converts tables to HTML format. We haven't looked specifically at how well the table conversion is working but on an overall basis the conversion seems to be quite accurate.