TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Acolyte – Query your data warehouse in plain English

6 pointsby mjirvover 3 years ago

6 comments

mjirvover 3 years ago
Hi all,<p>I&#x27;ve spent the past 4 years working as a data analyst and analytics engineer. One of the biggest pain points for analysts is that, even with tools like Looker and Tableau, they still spend a ton of time answering fairly simple questions from less-technical users instead of doing high-value analytics.<p>Often as a data analyst I&#x27;ve felt like a computer translating requests from English into SQL. That got me wondering - could an actual computer do it instead?<p>For a while, I thought the answer was &quot;no&quot; (or at least not in the near future). But then OpenAI&#x27;s Codex[0] was released. I started using GitHub Copilot[1] every day while writing SQL in Visual Studio, and it felt like magic. The autocomplete was getting my code right a lot of the time, even for complex SQL queries.<p>So I decided I&#x27;d give this a go. I&#x27;ve built a demo using the Codex API and dbt Labs&#x27;s &quot;Jaffle Shop&quot; example database, which will be familiar to many in the Analytics Engineering community. It&#x27;s a simple database, but the results are promising. The demo app gets a lot of queries right, and it does so <i>without any database-specific logic</i>.<p>The only input needed is a schema.yml file describing the tables and columns (which any dbt project would have) and 2 or 3 example queries, so I am hoping to open up testing to more data warehouses and users in the near future.<p>I hope you enjoy using the demo. If you have any feedback, ideas, or would like to test it out on your own data warehouse, my email is in my bio!<p>[0] <a href="https:&#x2F;&#x2F;openai.com&#x2F;blog&#x2F;openai-codex&#x2F;" rel="nofollow">https:&#x2F;&#x2F;openai.com&#x2F;blog&#x2F;openai-codex&#x2F;</a> [1] <a href="https:&#x2F;&#x2F;copilot.github.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;copilot.github.com&#x2F;</a>
seektableover 3 years ago
Tried the demo - it seems it doesn&#x27;t recognize names (values) yet, for example &quot;howard sum amount&quot; leads to simply &#x27;SELECT sum(amount) FROM orders&#x27;.<p>Our SeekTable has similar function where values could be matched too -- but instead of SQL result is a report configuration: <a href="https:&#x2F;&#x2F;www.seektable.com&#x2F;help&#x2F;search-driven-analytics" rel="nofollow">https:&#x2F;&#x2F;www.seektable.com&#x2F;help&#x2F;search-driven-analytics</a><p>Interesting that on practice this function is rarely used by end-users, and because of this we didn&#x27;t evolve this function.
评论 #28480373 未加载
ano88888over 3 years ago
great job. it works seamlessly. I like the fact that you show the underlying sql so that we know if it is wrong and edit it if needed. Some other tools just don&#x27;t show you how the magic is made and you cannot be 100% certain if data result is correct
评论 #28480395 未加载
mjirvover 3 years ago
For those having trouble with the URL, you can also use <a href="http:&#x2F;&#x2F;acolytehq.com" rel="nofollow">http:&#x2F;&#x2F;acolytehq.com</a>
qualudeheartover 3 years ago
How do you expect this to impact the job market for software engineers or database administrators?
评论 #28482067 未加载
Grimm1over 3 years ago
I see the jaffle shop example has made it&#x27;s way out of DBT ;)