A lot of documents you might want to processes and gather intelligence on will have charts. For instance in our Naive RAG chat we want to find out from the Federal Women’s Budget Statement for 2024-2025. I also loaded all … Continued
It doesn’t take long after you run a Basic RAG pipeline with a PDF that contains charts and tables to find cases where it doesn’t work very well or not at all. I took the last 5 years of local … Continued
While experimenting with GraphRAG (see my notes on getting it working here), I wanted an example that I was very familiar with, didn’t have too much text so I went in search of an eBook. I settled on The Nursery … Continued
When I first came across GraphRAG – all the documentation pointed to this solution accelerator. While that’s great, to give it a go I wanted something simpler. After a bit of digging I finally came across this article. There’s lots … Continued
With so much news around AI RAG – what’s the easiest way to get started to “play around” with AI and PDFs? While there isn’t one definitive answer I’m going to walk through one using Azure AI Studio. This example … Continued
I still love a hard copy book to read, but when it comes to day to day documents I’m very much a read on screen person. I RARELY print these days, and those are the times that someone requires a … Continued
While Word documents tend to have well defined structures, not all PDFs are created equally. Some are literally images pasted into a document and some are not set up to be accessible. The easiest way I’ve found to tell if … Continued
I’m a bit old-school and like to grab code examples on my laptop and run them rather than spinning up codespaces etc. I’ve been using a lot more Python bits lately playing with various AI tools and eventually you hit … Continued
I see a lot of code examples with important keys in them or greyed out in screen shots. Newish to Python there had to be a better way and there is… the .env file. Place a .env file in your … Continued
