My data consists of large pdf files containing state legislation. I can convert the pdf to xml, txt or html, and I can manually go through, identify the tables and write a script to extract only the laws and there relations etc.

But I'm not hugely experienced, and I was wondering if there were tools or tips that might put me on a better track.

I couldn't import the html files into ms sql, or mysql, even though I tried converting/saving it as straight text, as an aside. Anyway, anything to point me right would be appreciated.

Has anyone heard of someone making a project of loading relevant information from a states legislation into a db ... I was wanting to experiment with ML, chatGTP etc. on it.

  • $\begingroup$ If i understood correctly your question then i think you can use ChatGPT API with prompt engineering to to read texts and classify it or extract some info from it, $\endgroup$ Jul 5, 2023 at 12:43


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.