The Chrome Extension is open source and is powered by DuckDB WASM which loads the parquet conversion of the datasets as views so you can query them with SQL.
Yes it is designed for users without SQL knowledge, however, it can still perform fairly well with questions on the difficult side (for non technical users) with queries having multiple joins, aggregations, ratios, and subqueries.
Next step is fine tuning and leveraging larger models that can handle very complex questions, reasoning, and data schemas since this is only a 7B.
No, those are benchmark, evaluation questions. The fine tune dataset was a custom, synthetically generated dataset of ~20k PostgreSQL Text to SQL pairs covering different SQL categories and question types.
Thanks! Yes, that was an earlier iteration. The v1 is here https://huggingface.co/chatdb/natural-sql-7b. Plan to push to Ollama soon and build an open source free tool around it.