For all the client devs but especially noStrudel @hzrd149 please help me categorize posts with highly visible tags. It's impressive how easy that is now with for example ppq: $ curl https://api.ppq.ai/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer sk-topSecretToken" -d '{"model": "gpt-4o-mini","messages": [{"role": "user", "content": "Classsify the following post on social media as one of trivia, technical, social interaction, cheap engagement or deep thought. Answer with just the classification: Splash of bourbon and wild honey in my iced coffee why not "}]}' | jq '.choices[0].message.content' "Social interaction"
The idea is that I provide noStrudel with my api key and it annotates all posts and I can filter by those annotations but relay operators could also provide these annotations to not run the same query for the same note multiple times. But then again, it's dirt cheap to run: https://i.nostr.build/CQ7F8flrozpw6FOT.png I'm not quite sure what's wrong with my query. The code example was using claude and I changed that to gpt-4o-mini which the api documentation claims to provide, too but even if the monster of a model claude is used, ... 0.1ct per post. I would probably pay that, too.
@PPQdotAI could we please have more detailed information in the "Account activity"? Price to all digits that actually got booked against the account or were these two api calls actually free? If so, how can I get a million of those? Or in other words, can I rely on the price to be the same the next time I run the same query or do prices surge at certain times? Also what did I do wrong that my Model ended up being "undefined"?
Sentiment analysis as bookmarklet. Yeah, that is fun! :D https://v.nostr.build/yRLOqslc6tW7kZQl.webm So what's going on here ... I load my timeline and click a bookmark which runs some far from perfect code but for me the key observations are: It's fast. It's somewhat useful in its results. It's probably quite cheap. ppq won't show me the price as it's less than 0.1ct or probably less than 0.05ct. noStrudel unloads and loads a lot of stuff, forgetting past tagging so there are many aspects that need work but I'll keep that Bookmarktlet around to maybe improve it in the future. nostr:nevent1qvzqqqqqqypzq3huhccxt6h34eupz3jeynjgjgek8lel2f4adaea0svyk94a3njdqy88wumn8ghj7mn0wvhxcmmv9uq3uamnwvaz7tmwdaehgu3dwp6kytnhv4kxcmmjv3jhytnwv46z7qpqjrkyqf58ufvze25vpfkrcpq6uewka9m6jpg3xf8wl8854eq70xpqrljyce