Hacker News Reader

What is the use case for this? Is the value here that you do not need to worry about accurately extracting text from a pdf? Or that you have full knowledge of where text is store as it relates to the original document? Or something different?

View on HN

There is a growing trend of applying Multimodal LLMs directly to PDF pages without doing extraction first (i.e. classic RAG). We've had this request from multiple customers whose products are supposed to handle visually rich documents like "GPT for pitch decks" or "GPT for investment bankers". The problem is that you must first find the relevant page to feed into the LLM. This helps to avoid the overhead of running an expensive model on each single page.

We first attempted to extract text from pages and do a semantic/hybrid search. Still, it felt massively suboptimal since much positional information was lost, so we decided to train our model that could help with this task!

Also, please feel free to take a look at the blog post if you are interested in more technical details!

https://blog.bynedocs.com/layoutlm-byne-v0.1-the-new-sota-in...

Thanks for the explanation- I have a need for this!

Reply on news.ycombinator.com