Hi, Till here, worked on the DuckDB-NSQL model on MotherDuck side. 1. Definitely training data (for me), we explored about 10 different directions before settling on the current approach. It's easy to underestimate the effect of training data on the quality of the model. Starting point was the benchmark dataset though, which we assembled manually (to avoid data pollution and also because there was simply no... - Source: Hacker News / 4 months ago

The implementation of Text-to-SQL can be achieved through the use of Vanna.AI, an open-source 🐍Python library that allows the training of an RAG model with queries, DDL, and documentation from a database. - Source: dev.to / 5 months ago

Nice! I’m going to try it out and possibly integrate it into my Python package: https://vanna.ai. - Source: Hacker News / 8 months ago

Nice job! We're building something relatively similar at Vanna AI: https://vanna.ai/. - Source: Hacker News / 10 months ago

Https://insightbase.ai allows you to chat to your database and build analytics using the answers. You can ask for anything and it will answer with a number a text or a graph. You can build dashboards with widgets that auto-refresh at specified intervals. This saves a lot of time and has the advantage that anyone can use it without knowing the database structure & coding. What do you think about this? - Source: Hacker News / about 1 year ago