thecalebf

the graphics in it make it so much better

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.

Here's the repo: https://github.com/cfahlgren1/hf-data-explorer

Yes please do! Looks awesome, would love to help any way I can as well.

Sorry, it seems complicated. Since it is a finetune of Deepseek-Coder, I had to include their license.

Deepseek is pretty open, just says not to use it for: - military purposes - exploiting vulnerabilities etc.

Just trying to include as much information as possible from the initial base model.

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.

Currently Postgres yes, already working on a dataset with more DDLs like MySQL, DuckDB, MSSQL, etc for a second iteration.

Neat, would you ever use a local model for that if it could work with ORMs?

That is really interesting. I took note of this. That would be really cool!

Great call out. Will definitely focus on that in the next iteration!

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.

I mention a little more about it here https://x.com/calebfahlgren/status/1754247740291207198?s=20

Updated the title since it may have been confusing, appreciate the feedback!

Not yet, planning to build an open source, local, CLI tool that utilizes natural-sql though!

Sure, there is a blog post with some other examples of the first model iteration with more complex, multipart questions. https://www.chatdb.ai/post/naturalsql-vs-sqlcoder-for-text-t...

I will update that to be a more truly difficult question. Appreciate the feedback!

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.

Would love to hear about what you are building!

Very neat! I am building something very similar, called ChatDB.ai

Hey, interesting. Make sure you have a home opened and it should populate with the charts. If that doesn't work feel free to send me an email at caleb at homescope.io and I can help you out :)

Thank you. Let me know if it meets your needs :)

The extension isn't storing any data from Zillow. Bigger Pocket's proprietary calculator pulls the data from Zillow as well. I think as long as you aren't storing or trying to make it proprietary it is better.

Also if Zillow is hiring new grad engineers reach out :)

Thanks for the tips!

Let me know if you have all the tools you need :). Always open to add things to help make finding deals easier!

Hey there, yes the only thing collected is authentication so email password signing in via Firebase. It isn’t used in any way other than auth. Hope that answers your question!

This tool is more for smaller investors not really massive funds or companies like Blackstone.

If you keep up with the project, checkout homescope.io :)