Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Hacker News Activity Analysis with GPT-4 Agent

eu.getdot.ai

Post reply on HN
Print view View original

31–40 of 54 posts

Re: Hacker News Activity Analysis with GPT-4 Agent

#31

Post by chittenden »

zurfer wrote: post #26
chittenden wrote: post #24

Very cool! Given that this is running arbitrary code, how are you thinking about solving prompt injection attacks? Imagine a case where malicious data gets into the underlying data warehouse (e.g. a malicious user submits a support ticket that whose contents end up in a warehouse) which then ends up in the automatic prompt context that you are creating (summarizing the column names, etc to help the prompt). The malic…

Security is an interesting challenge. The way we approach it is that we assume the LLM will spit out actions that are wrong or harmful. So everything needs to be handled with old school permissions. Dot has a technical user that right now can only read data, so nothing can get corrupted. And second we have an extra layer where we make sure that the user who asks the question has access to the tables that are accessed…

That sounds like the right way to handle it. What about the Python code that is run? That seems harder to lock down than the read-only data permissions.

Re: Hacker News Activity Analysis with GPT-4 Agent

#32

Post by pknerd »

Interesting Stuff. OpenBB has also implemented an LLM/AI-based solution using GPT to query stock/trading data in QnA format. I want to do something similar with an e-commerce website using RDBMS(MySQL/pgSQL). Does anyone know any such solution?

Like, if I am running a t-shirt store, my users can query like: "Do you have a round neck t-shirt in red color in XL size" and it returns all relevant results

Re: Hacker News Activity Analysis with GPT-4 Agent

#35

Post by zurfer »

fxd123 wrote: post #27

What information would this send to the third-party (you and/or OpenAI)? I assume from this demo at the very minimum the database structure? Does the post processing after the LLM response run on the customers' servers?

Great question. We allow Dot to work with just meta data, but you can enable it to also react to the content and we recommend to our customers to also pass content to the LLM (Azure GPT4) because it's a lot more capable, e.g. for filtering or even for visualizing data.

Re: Hacker News Activity Analysis with GPT-4 Agent

#36

Post by zurfer »

dennisy wrote: post #34

Has anyone seen a project such as this which is open source? I am not saying this project should be, it’s just that my pet project is something very similar and I am sure some people must be building this in the open?

The biggest project I am aware of is the SQL agent from langchain. It definitely gets you started and is great imo for single developers or small technical teams.

Re: Hacker News Activity Analysis with GPT-4 Agent

#37

Post by zurfer »

codingdave wrote: post #30

If this is self-serve, how would we go about asking questions to the system directly? FWIW, I'd ask: - 1) Who are the top posters and commenters by average score on posts and comments? - 2) Which users instigate the most positive discussions in reply to their comments. (Not longest or more... but highest quality, without arguments, flamewars, etc.) It is that 2nd question I'm really interested in because it really mi…

We will probably enable the Hackernews data as demo data in the future. Today we only have some e commerce demo data when you sign up. Although you could connect the public Big query dataset and do it yourself.

Your 2nd question would require some preprocessing per message that should probably be done as part of data preparation and not at query time.

Re: Hacker News Activity Analysis with GPT-4 Agent

#38

Post by codingdave »

zurfer wrote: post #37
codingdave wrote: post #30

If this is self-serve, how would we go about asking questions to the system directly? FWIW, I'd ask: - 1) Who are the top posters and commenters by average score on posts and comments? - 2) Which users instigate the most positive discussions in reply to their comments. (Not longest or more... but highest quality, without arguments, flamewars, etc.) It is that 2nd question I'm really interested in because it really mi…

We will probably enable the Hackernews data as demo data in the future. Today we only have some e commerce demo data when you sign up. Although you could connect the public Big query dataset and do it yourself. Your 2nd question would require some preprocessing per message that should probably be done as part of data preparation and not at query time.

OK, I'm a bit confused then - if this needs prep work to ask questions, what is AI bringing to the table?

Re: Hacker News Activity Analysis with GPT-4 Agent

#40

Post by usgroup »

I’m guessing the bot has access to the schema of the data and then builds sql queries to fetch subsets into python for plotting. Is that right?

You could potentially stage the query in two parts — one in which it builds the query that you execute , and the 2nd in which you provide data for it to analyse/visualise.

Post reply on HN