Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #13215

V

Vanna AI

Company blog · vanna.ai/blogaidata

Vanna AI is the company blog at vanna.ai, writing about ai and data. Since 2023, 6 different Hacker News readers have linked it 13 times, most often “AI SQL Accuracy: Testing different LLMs and context strategies to generate SQL”. No feed was found, so read it on the site itself.

No feed foundVisit the blog
13mentions?
6HN people?
2023–2024first – last linked?
Links on Hacker News per year · peak 8 in 2023

Too few sampled comments (3) to say how often HN recommends it.?

Why HN links it

HN readers link Vanna's blog and docs for its open-source tool that lets users chat with SQL databases using LLMs, and for a post on AI SQL accuracy. Comments are mostly links and integration notes.

Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Build AI agents that ship to production. User-scoped execution, rich UI components, and quota management built-in.

Most-linked posts?

  1. AI SQL Accuracy: Testing different LLMs and context strategies to generate SQL
    3 people · 4 mentions · first linked 2023-09-08
  2. /
    2 people · 2 mentions · first linked 2023-08-24

What Hacker News says?

  1. This should be nice to be easier to integrate with things like Vanna.ai, that was on HN recently. There a bunch of methods need to be implemented to work, but then usual OpenAI buts can be switched out to anything else, e.g. see the code stub in https://vanna.ai/docs/bigquery-other-llm-vannadb.html Looking forward to more remixes for other tools too.

    Comment linking /docs/bigquery-other-llm-vannadb.html

    on “Ollama releases Python and JavaScript Libraries”
  2. Submitted Show HN: Vanna AI – Open-Sourced Text-to-SQL in Python as a story · 3 points

    HN discussion
  3. The nitty gritty: https://vanna.ai/blog/ai-sql-accuracy.html

    Comment linking /blog/ai-sql-accuracy.html

    on “Vanna.ai: Chat with your SQL database”
  4. Submitted AI SQL Accuracy: Testing different LLMs and context strategies to generate SQL as a story · 2 points

    HN discussion
  5. 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 text2sql…

    Comment linking /

    on “An open source DuckDB text to SQL LLM”
  6. Submitted Vanna as a story · 1 points

    HN discussion
  7. We tested Bard (aka Bison in GCP) for generating SQL. It has worse generalization capabilities than even GPT-3.5 but actually does as well at GPT-4 when given contextually relevant examples selected from a large corpus of examples. https://vanna.ai/blog/ai-sql-accuracy.html This suggests to me that it needs longer prompts to avoid the hallucination problem that everyone else seems be experiencing.

    Comment linking /blog/ai-sql-accuracy.html

    on “Ask HN: 6 months later. How is Bard doing?”
  8. Nice! I’m going to try it out and possibly integrate it into my Python package: https://vanna.ai

    Comment linking /

    on “Show HN: Magentic – Use LLMs as simple Python functions”
  9. I’m building exactly this! https://vanna.ai

    Comment linking /

    on “ChatGPT plugins now support Postgres and Supabase”
  10. Nice job! We're building something relatively similar at Vanna AI: https://vanna.ai/

    Comment linking /

    on “Show HN: Dataherald AI – Natural Language to SQL Engine”
  11. Thanks for the link! I'll check it out. In the meantime, this post we wrote might be interesting for you: https://vanna.ai/blog/ai-sql-accuracy.html

    Comment linking /blog/ai-sql-accuracy.html

    on “Show HN: Vanna AI – Open-Sourced Text-to-SQL in Python”
  12. API key is optional -- that's only if you want to use the hosted vector database. When running locally, no Vanna API key is necessary. Instead, you can put in an OpenAI API key as shown here: https://vanna.ai/docs/local.html If you want to use a locally-hosted LLM, that's also possible by implementing the necessary abstract methods: https://vanna.ai/docs/vanna.html#open-source-and-extending

    Comment linking /docs/vanna.html

    on “Show HN: Vanna AI – Open-Sourced Text-to-SQL in Python”

Search all of HN for vanna.ai