Which sources does it support? Discoverability is a huge problem for smaller events, as most get posted on IG, and it’s hard to even find them through IG.
I started relying on a mix of Muse/ChatGPT/Gemini depended on which data sources I want to combine, as they all seem to have special deals with different sources.
It seems to use a (probably AI generated) list of common event sites, Instagram, and a few hardcoded ones related to the region (like Makeout Room). There's no de-dupe so you'll see tons of the same event copied across Eventbrite/Tixr/etc.
This is pretty cool, does it scrape Instagram? A lot of events where I live (Toronto) are posted there and not many other places. It's a real problem if you don't want to spend time on that app.
Personally, I don't have a project that requires it right now, but aspirationally maybe! I agree with another commenter that mentioned this is basically a public service that should exist similar to Wikidata / Musicbrainz.
I know this is currently a paid service you're trying to make happen and the scraping part is a reasonable amount of effort, but if you wanted to make the data source public, you could publish community.lexicon.calendar.event ATProto records and it would be very cool. At the very least, you could ingest it as a data source!
Fine to be that guy! Let’s say you want to build a product that recommends concerts to people based on their music listening history. Do you want to pay for an expensive tool call and several second response time to surface answers back to the user? Yes of course you can build this yourself because SaaS is dead! Or someone else could maintain it for you :)
I started relying on a mix of Muse/ChatGPT/Gemini depended on which data sources I want to combine, as they all seem to have special deals with different sources.
any particular events that you'd flag that I could do some eval against?
I think it would be a nice addition once you get a larger spread of data! Great idea
I know this is currently a paid service you're trying to make happen and the scraping part is a reasonable amount of effort, but if you wanted to make the data source public, you could publish community.lexicon.calendar.event ATProto records and it would be very cool. At the very least, you could ingest it as a data source!
There's hundreds of events happening every week but finding them takes a lot of time.
I'm actually working to do this at ultra low cost as a public service like Wikipedia or musicbrainz.
I'll be publishing global costs to serve and letting people donate to support.
Forget the API. Even search engines have returned these results for years.
I can potentially see an angle with SLMs integrating with a self hosted version of this API, but it’s a bit niche.
Why use a token-burning middleman when someone has already done it for you?