document-ai-samples VS pdfGPT

Thanks for the example and that sounds really solid cost savings and definitely agree with the trend that it is here to stay.

For invoice parsing (various formats), are you just using GPT4V? When GPT4V initially came out, i benchmarked it against an out of the box invoice parser from Google Cloud (https://cloud.google.com/document-ai) on 16 documents and it was much better accuracy wise. For ex: i'd get results parsing 10,100 as 101100 (no comma).

Curious if you saw problems like this in your pipeline or if its gotten much better since?

Google Document AI: Google's generic document processor, found on the Google Cloud Platform, worked ok out of the box. However, it will require significant fine-tuning via manual data labeling for at least 15 to 20 documents before I have a decently accurate processor.

What's next? Well, it's already here, with Document AI, and keeps growing:

The source code for this demo is available in our Document AI sample repository.

From "Artificial intelligence is ineffective and potentially harmful for fact checking" (2023) https://news.ycombinator.com/item?id=37226233 : pdfgpt, knowledge_gpt, elasticsearch

pdfGPT: https://github.com/bhaskatripathi/pdfGPT :

> PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities.

GH "pdfgpt" topic: https://github.com/topics/pdfgpt

knowledge_gpt: https://github.com/mmz-001/knowledge_gpt

From https://news.ycombinator.com/item?id=39112014 : paperai

neuml/paperai:

What about systems like pdfgpt and knowledge_gpt; that, in returning citations from the trained texts, might be useful for legal discovery with admissibility?

pdfgpt: https://github.com/bhaskatripathi/pdfGPT

PDFChatter (Universal Sentence Encoder + GPT-3.5): out of the box, this solution works quite well. However, the need for Q&A prompting (and 'black-box' nature of the solution) seems to disqualify it as an optimal solution.

I was recommended pdfGPT and it looks good. Before I start setting it up, is there anything I should know? Are there better solutions? And how secure would it or they be?

https://github.com/bhaskatripathi/pdfGPT/blob/main/app.py it's a 200 line python script, all you need to do is rewrite pdf_to_text function for whatever format your file is. gpt4 can do it.