Access table in PDF

[hdavis54]

I’m trying to get the table in the attached PDF file into KNIME, but I can’t seem to get it to work. I have looked at some other posts using the Tika Parser, but I’m not able to get it to acquire all of the data. Any help to point me in the right direction would be greatly appreciated.

2022_M_ArubaOceanClub.pdf (434.9 KB)

[mlauber71]

@hdavis54 you could take a look at the examples in this article.

KNIME — Extract Text and Tables from PDF Files with Python in a Low-Code...

Another approach is to use LLMs to extract information. Here are examples with local versions in order to protect the data privacy.

Extract Data from Invoices to XML or CSV?

@jannikw99 I set up a workflow to extract information from your PDFs with two different LLM models (Llama3, Mistral). From what I saw it will make sense to work on the prompt for example adding a passage about making sure the JSON structure is valid and avoid nested data. Your PDFs are from different banks and contain different sets of data like buying different products (stocks and bonds). I focussed on the first bank and stocks and I assume it will take some work on the prompt(s) to be ready …

GPT4All - Extract Information from PDF Bank Statements into JSON – mlauber71