Since then a lot has improved: More databases are supported, most of the product can now be used for free, and most importantly:
The app now comes with an analytics workspace powered by an embedded ClickHouse instance, running locally on your machine. This allows you to query local files, files on S3, PostgreSQL, SQLite & more - and all of those at once.
If you mean the common OpenAI API key, I'm not sure how that's different in regards to feeling secure compared to separate keys. Would you mind elaborating further, please?
To clarify, the common API key is known only by my server, not by the app!
Right now it's pretty simple: First I drop the table/column information if the token limit gets exceeded otherwise (this is shown as a warning in the UI). Then if the limit still gets exceeded, the I show an error to the user.
I plan to make this process more smart eventually.
In my experience though it is often a significant time saver if I only have to review the output of the AI vs. coming up with everything myself.
Re: ambiguities: You are right, the AI won't always be able to infer the correct fields to use. In such cases though it is often enough to help the AI out a little. E.g. by saying "information X is stored in field Y of table Z".
Even if you have to do that, you can still save time and more importantly mental effort by letting AI help you, compared to writing all the SQL yourself.
Re: iterative process: You can simply send a follow up message saying "You did X wrong". It is usually happy to correct itself.
This is a case where it could help to give the AI some example values of the actual data. The same applies for e.g. JSON fields.
I've been thinking about ways to make it possible for users to easily provide examples to the AI. Essentially that would mean selectively giving access for specific rows/columns to the AI.
I first announced DB Pilot on HN back in April: https://news.ycombinator.com/item?id=35761979.
Since then a lot has improved: More databases are supported, most of the product can now be used for free, and most importantly:
The app now comes with an analytics workspace powered by an embedded ClickHouse instance, running locally on your machine. This allows you to query local files, files on S3, PostgreSQL, SQLite & more - and all of those at once.
Embedding ClickHouse was possible thanks to chDB (https://github.com/chdb-io/chdb). A recent discussion on HN about it: https://news.ycombinator.com/item?id=37985005