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 / 5 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 / 6 months ago

Nice! I’m going to try it out and possibly integrate it into my Python package: https://vanna.ai. - Source: Hacker News / 9 months ago

Nice job! We're building something relatively similar at Vanna AI: https://vanna.ai/. - Source: Hacker News / 11 months ago

I think my app still can't beat chatpdf.com. :(. Source: 12 months ago

Quoting directly from the FAQ popup on chatpdf.com:. Source: about 1 year ago

Try using chatpdf.com I don't really use documents that much. Source: about 1 year ago

I've asked ChatGPT to create excel formulas for me, that's the extent of my experience here. As far as analyzing an actual spreadsheet data, I believe the beta OpenAI tool, code interpreter, can do that. I don't have access to that, however. I have more experience with PDFs. There are several plug-ins for interacting with PDFs if you are a ChatGPT plus subscriber. For free, you can open a PDF in the Microsoft... Source: about 1 year ago

ChatPdf: Free version supports 120 pages/PDF, 10 MB/PDF, 3 PDFs/day, and 50 questions/day. Source: about 1 year ago