21–30 of 243 posts
I'm curious about how this performs with more complex queries, like joins across five tables. Also, does the training phase actually involve writing SELECT queries by hand? In the age of ORMs and so on, many people have probably forgotten how to write raw SQL queries.
Earlier quoted context omitted.
This works pretty well without a dedicated application today, e.g. "Knowing everything you do about music and music distribution, please define a database schema that supports albums, tracks, and artists" . If you have additional requirements or knowledge that the response doesn't address, just add it and re-prompt. When you're done, ask for the SQL to set up the schema in your database of choice.
Maybe my prompting needs to improve, I tried recently to get chatgpt to provide a schema for an sqlite database that implements vcard data in a normalised way. I gave up...
For fun, I just asked ChatGPT-4 to generate a normalized database representation of vcard information: https://chat.openai.com/share/1c88813c-0a50-4ec6-ba92-4d6ff8...
It seems like a reasonable start to me.
I wish we had landed on a better acronym than RAG.
The most success I had with AI+SQL was when I started feeding errors from the sql provider back to the LLM after each iteration. I also had a formatted error message wrapper that would strongly suggest querying system tables to discover schema information. These little tweaks made it scary good at finding queries, even ones requiring 4+ table joins. Even without any examples or fine tuning data.
https://raw.githubusercontent.com/vanna-ai/vanna/main/img/va...
That is, store your trained custom data in vector db and then use RAG to retrieve relevant content and inject that into the prompt of the LLM the user is querying with?
As opposed to fine tuning or other methods?
Does it work with Google/Facebook ads data? Can I ask it to show best performing ads from BigQuery Facebook/Google ads data by supermetrics or improvado.
