Introducing Bird SQL, a Twitter search interface that is powered by Perplexity’s structured search engine. It uses OpenAI Codex to translate natural language into SQL, giving everyone the ability to navigate large datasets like Twitter.

With Bird SQL, you can quickly find information on Twitter that would have been impossible to find with conventional search engines or web browsing: "most liked tweets about #worldcup"

Search through top content: "most liked tweets of all time"

Find new users to follow: "top astrophysicists"

Filter down to content you’re curious about: "tweets about chatGPT liked by Elon Musk"

Search your favorite topics: "top posts about ChatGPT"

Analyze social graphs: "People followed by Jeff Bezos who don’t follow him back"

Analyze how people engage: "people Sam Altman engages with the most"

If you are interested in using our search engine on your structured or unstructured data, contact us at [email protected], our Discord server, or via Twitter. Join our Discord to learn more about search and large language models:

This is a demo, not a commercial product. There are limitations to our Twitter data, database performance, and the expressiveness of SQL. Bird SQL does not interpret the content of tweets. For unstructured search, try Perplexity Ask.

I've been tinkering with something like this, but this implementation is so much further along -- and better. Wish I had known about it sooner, but nice to be able to cross something off my list of things to play with. :)

Thank you for trying it out! Would you be interested in seeing a similar search over HubSpot?