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

Vanna.ai: Chat with your SQL database

github.com

Post reply on HN
Print view View original

91–100 of 243 posts

Re: Vanna.ai: Chat with your SQL database

#91

Post by account-5 »

coder543 wrote: post #63
account-5 wrote: post #59

Earlier quoted context omitted.

Chatgpt 3.5. Maybe I should pay for a couple of months access to 4 to see the difference. Is it worth the money?

ChatGPT-3.5 isn’t even worth touching as an end-user application. Bard is better (due to having some integrations), but it’s still barely useful. ChatGPT-4 is on an another level entirely compared to either 3.5 or Bard. It is actually useful for a lot. ChatGPT-3.5 can still serve a purpose when you’re talking about API automations where you provide all the data in the prompt and have ChatGPT-3.5 help with parsing or…

You sample completely blows away what I got out of 3.5. I'm now wondering if Bing is 3.5 or 4. But will likely fork out for a couple of months.

Re: Vanna.ai: Chat with your SQL database

#92

Post by codyvoda »

kszucs wrote: post #90
codegeek wrote: post #64

I have been keeping track of a few products like these including some that are YC backed. Interesting space as I am looking for a solution myself: - Minds DB (YC W20) https://github.com/mindsdb/mindsdb - Buster (YC W24) https://buster.so - DB Pilot https://dbpilot.io and now this one

Please add Ibis Birdbrain https://ibis-project.github.io/ibis-birdbrain/ to the list. Birdbrain is an AI-powered data bot, built on Ibis and Marvin, supporting more than 18 database backends. See https://github.com/ibis-project/ibis and https://ibis-project.org for more details.

note that Ibis Birdbrain is very much work-in-progress, but should provide an open-source solution to do this w/ 20+ backends

old demo here: https://gist.github.com/lostmygithubaccount/08ddf29898732101...

planning to finish it...soon...

Re: Vanna.ai: Chat with your SQL database

#93

Post by realanswe91 »

pylua wrote: post #72
codegeek wrote: post #64

I have been keeping track of a few products like these including some that are YC backed. Interesting space as I am looking for a solution myself: - Minds DB (YC W20) https://github.com/mindsdb/mindsdb - Buster (YC W24) https://buster.so - DB Pilot https://dbpilot.io and now this one

I don’t fully understand the use of business case after reading the documentation. Is it really a time save?

[flagged]

Re: Vanna.ai: Chat with your SQL database

#94

Post by l5870uoo9y »

echelon wrote: post #27
bob1029 wrote: post #14

The most success I had with AI+SQL was when I started feeding errors from the sql provider back to the LLM after each iteration. I also had a formatted error message wrapper that would strongly suggest querying system tables to discover schema information. These little tweaks made it scary good at finding queries, even ones requiring 4+ table joins. Even without any examples or fine tuning data.

Please turn this into a product. There's enormous demand for that.

You can check this out https://www.sqlai.ai. It has AI-powered generators for:

- Generate SQL

- Generate optimized SQL

- Fix query

- Optimize query

- Explain query

Disclaimer: I am the solo developer behind it.

Re: Vanna.ai: Chat with your SQL database

#95

Post by samstave »

kulikalov wrote: post #89

While I recognize the efforts in developing natural language to SQL translation systems, I remain skeptical. The core of my concern lies in the inherent nature of natural language and these models, which are approximative and lack precision. SQL databases, on the other hand, are built to handle precise, accurate information in most cases. Introducing an approximative layer, such as a language model, into a system tha…

Reverse idea:

Use this to POPULATE sql based on captured NLP "surveillance" -- for example, build a DB of things I say as my thing listens to me, and categorize things, topics, place, people etc mentioned.

Keep count of experiencing the same things....

When I say I need to "buy thing" build table of frequency for "buy thing" etc...

Effectively - query anything you've said to Alexa and be able to map behaviors/habits/people/things...

If I say - Bob's phone number is BLAH. It add's bob+# to my "random people I met today table" with a note of "we met at the dog park"

Narrate yourself into something journaled.

Makes it easy to name a trip "Hike Mount Tam" then log all that - then have it create a link in the table to the pics folder on your SpaceDrive9000.ai and then you have a full narration with links to the pics that you take.

Re: Vanna.ai: Chat with your SQL database

#96

Post by realanswe91 »

aae42 wrote: post #86
marginalia_nu wrote: post #82

Earlier quoted context omitted.

In general, if something has been around for a very long time and nobody apparently seems to have thought to improve it, then odds are the reason is it's pretty good and genuinely hard to improve on.

in other words, SQL is a shark, not a dinosaur

The Shark Query Language

Re: Vanna.ai: Chat with your SQL database

#97

Post by pietz »

kulikalov wrote: post #89

While I recognize the efforts in developing natural language to SQL translation systems, I remain skeptical. The core of my concern lies in the inherent nature of natural language and these models, which are approximative and lack precision. SQL databases, on the other hand, are built to handle precise, accurate information in most cases. Introducing an approximative layer, such as a language model, into a system tha…

I think you have a point. I also think people who share this mindset and keep sticking with it will have a tough future.

The technical benefits and potentials clearly outshine the problems and challenges. That's also true in this example. You just have to let go of some principles that were helpful in the past but aren't anymore.

Re: Vanna.ai: Chat with your SQL database

#98

Post by qiller »

We did something similar for our reporting service which is based duckdb. Overall it works great, though we've ran into a few things:

* Even with low temperature, GPT-4 sometimes deviates from examples or schema. For example, sometimes it forgets to check one or another field...

* Our service hosts generic data, but customers ask to generate reports using their domain language (give me top 10 colors... what's a color?). So we need to teach customers to nudge the report generator a bit towards generic terms

* Debugging LLM prompts is just tricky... Customers can confuse the model pretty easily. We ended up exposing the "explained" generated query back to give some visibility of what's been used for the report

Re: Vanna.ai: Chat with your SQL database

#99

Post by kulikalov »

pietz wrote: post #97
kulikalov wrote: post #89

While I recognize the efforts in developing natural language to SQL translation systems, I remain skeptical. The core of my concern lies in the inherent nature of natural language and these models, which are approximative and lack precision. SQL databases, on the other hand, are built to handle precise, accurate information in most cases. Introducing an approximative layer, such as a language model, into a system tha…

I think you have a point. I also think people who share this mindset and keep sticking with it will have a tough future. The technical benefits and potentials clearly outshine the problems and challenges. That's also true in this example. You just have to let go of some principles that were helpful in the past but aren't anymore.

What technical benefits?

Re: Vanna.ai: Chat with your SQL database

#100

Post by kulikalov »

samstave wrote: post #95
kulikalov wrote: post #89

While I recognize the efforts in developing natural language to SQL translation systems, I remain skeptical. The core of my concern lies in the inherent nature of natural language and these models, which are approximative and lack precision. SQL databases, on the other hand, are built to handle precise, accurate information in most cases. Introducing an approximative layer, such as a language model, into a system tha…

Reverse idea: Use this to POPULATE sql based on captured NLP "surveillance" -- for example, build a DB of things I say as my thing listens to me, and categorize things, topics, place, people etc mentioned. Keep count of experiencing the same things.... When I say I need to "buy thing" build table of frequency for "buy thing" etc... Effectively - query anything you've said to Alexa and be able to map behaviors/habits/…

You are describing use case for a vector database
Post reply on HN