Over the last couple of months I have seen so many trends about Large language models and frameworks around it that allow you to use building blocks to ramp up your applications really fast.
I've been keeping an eye, meanwhile life and work keep me busy, I haven't done much in few months regarding exploring those new trends until today. I picked up my laptop and took 1h or 2 to make a refresh on those topics.
Starting by taking deeplearning.ai course by Harrison Chase, the co-founder of LangChain , where you basically are able to take your data, loading and transform it in a way that can be used by LLMs and Magic happens where you can actually start asking questions about your data and receive an answer in natural language.
Well, for starters the building blocks are infinite and for each specific task like loading , splitting the text into chunks or using embedding models to load them into a Vector store so you can chat with them, are pretty quick to grasp.
My main goal: after taking this refresher, I want to build an app that you can take some documents, perhaps PDFs, Markdowns , ingest them and ask questions around it using this framework.
For starters , I'll leave my repository here and I plan to share progress as I go:
https://github.com/laurauzcategui/chat_with_your_data
Hope you like it :)
See you next time