Uwe Dreiss
PRO
@uwe
Thanks! I keep seeing the Google Gemini ads in my Gmail, but didn't know it also integrates with Gdrive.
Regarding (2) I'm not yet sure. I am playing around with text-to-sql at the moment. It might be sufficient. But I'll also research vector search!
Thanks so much! Very interesting. So that's sort of text-to-sql (or vice versa)?
Any resources where I can go down a bit of a rabbit hole for a few hours and learn more about it?
So my understanding would be that in case 2 I would send in the prompt itself something like
table: my_table
fields: id INT; name VARCHAR, email VARCHAR, country VARCHAR
And then if I e.g. ask how many people in my app are from the UK, I'd send the query + the table structure in the prompt and it would probably return something along the lines of SELECT count(id) FROM my_table WHERE country = UK, right?
So depending on the complexity of the database (and how often it changes), it still might be a bit tricky, especially if I have relational tables that connect multiple tables via IDs, etc. as this might need additional explanations in the prompt. If I'd use one of the big LLMs, such as OpenAI, what sort of model would work best with this?
Yes, it's text-to-sql. I would just dump your entity relationships into the prompt and ask for the SQL for some example questions. Then, I'd take those and correct the SQL so that it works -- either asking the LLM to correct bugs you see or just doing it by hand. Then I'd put those input-output examples into the prompt and try it on new things and rinse & repeat.
o1-preview
will do best, but once you have a good prompt that works well, I would try that out on 4-o and smaller models
There are a few Fintechs in Europe that give you Spanish IBAN's. A lot of my Dutch friends in Valencia talked about a Dutch Fintech that does that. That was a few years back though. Also, I used Sabadell when I lived in Valencia and it was ok. Nothing to complain about to be honest.
I think tech leads and project managers might be more willing and capable of writing good articles. They’re used to writing a lot anyway
Following as i am looking into the same right now