Hacker News Reader

9/10 requests for a simple sql query get a working query.

This isn't enough to enable a useful interface.

It takes a lot of scaffolding to get an llm powered interface to actually work.

I'm actively trying to scaffold an LLM for business usecases and my experience totally echoes this. I can tweak the prompt for a very representative set of training data, and then it vomits at a seemingly normal new case.

have you tried to train a model based on your expectation context data and the outputs you want?

You might be interested in another way to use LLMs inside a SQL query. For example, LLMs can be used to power a "soft join" between SQL tables for when a correspondence is only implied (e.g. different address formats, etc.).

More details here: https://medium.com/evadb-blog/augmenting-postgresql-with-ai-...

Reply on news.ycombinator.com