US DoD heavily controls what can and can't be installed on their stuff. To make matters worse each branch and organization has their own approach to how they control what gets installed.
Sometimes it's just the path of least resistance to use what you already have.
I remember putting in a request to install Python. It took me 6 months to get a response of no. I had the opportunity to appeal with more information on the use case, but I just did it in VB for Excel at that point.
While that's true, FTEs (Flight Test Engineers) tend to have more leeway. As I said above, I've seen Army S6 give approvals for all sorts of programming environments. And the AFTCs seem to be a bit more lenient than that even when it comes to deploying in SCI environments.
Granted, I've also seen a piece of software denied because it has USB in the name (even though it had nothing to do with USB), so YMMV.
That was going to be the next stage, but this would have been a more complicated solution with additional challenges but definitely a lot of code could have been re-used as it would just have been a matter of substituting the database lookup portion.
There are unknowns with the vector store solution because it doesn't suffice to just fetch a few relevant sentences in arbitrary order; we had to fetch every relevant piece of information in appropriately-sized chunks (some of which had to be multiple lines, some of which required the section heading for context) to formulate a correct answer. Sometimes there was something mentioned in a different section of the text which changed the outcome. Going down the vector database route would have taken longer and involved additional learning and it's not clear that we could have reduced the input size by doing that. I still think it was a good decision to start with a regular database first given that all information mapped neatly under the headings in our table of contents and that each section was relatively short. All sections were less than 500 words but most were only about 100 to 200 words.
What platform do you use to teach the course? I've been teaching an ML from scratch course for junior devs at my company and think it'd be useful for others.
Dude run from your current employer. I actually transitioned into software dev after working as a Mech Eng after 2 years and I started at $120k. With you experience I feel like you could do way better.
