TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Use natural language to query and visualize 400M tweets

11 点作者 tmostak大约 1 年前
We&#x27;ve been working hard for the last year on building HeavyIQ, an LLM-powered plugin to the GPU-accelerated HeavyDB database, that allows users to ask natural language questions and get SQL, visualizations, and natural language answers back. The LLM itself is fine-tuned on tens of thousands of question and answer pairs, with a major focus around building the model’s proficiency at performing spatial and temporal joins.<p>You can try it for yourself on this live demo of 400M tweets and a handful of other datasets of interest: <a href="https:&#x2F;&#x2F;demo-heavyiq.heavy.ai&#x2F;us_tweets&#x2F;sql-notebook" rel="nofollow">https:&#x2F;&#x2F;demo-heavyiq.heavy.ai&#x2F;us_tweets&#x2F;sql-notebook</a><p>For more info on the model and capabilities please read our blog: <a href="https:&#x2F;&#x2F;www.heavy.ai&#x2F;blog&#x2F;heavyiq-conversational-analytics" rel="nofollow">https:&#x2F;&#x2F;www.heavy.ai&#x2F;blog&#x2F;heavyiq-conversational-analytics</a>

2 条评论

patdwilson大约 1 年前
My favorite question is &quot;Show the percentage of tweets mentioning &quot;y&#x27;all&quot; or &quot;yall&quot; per state.&quot; Thank you, Louisiana :)
sdrg822大约 1 年前
Congrats on the launch!
评论 #39470036 未加载