Urusan on Nostr: So for example you might have it classify posts in this format: "Positive sentiment, ...
So for example you might have it classify posts in this format:
"Positive sentiment, no objectionable content, topics: AI"
"Negative sentiment, abusive language, topics: other user"
Etc.
Unless you do additional training it'll probably output some other extraneous stuff, but as long as your output string is consistent you can extract it.
"Positive sentiment, no objectionable content, topics: AI"
"Negative sentiment, abusive language, topics: other user"
Etc.
Unless you do additional training it'll probably output some other extraneous stuff, but as long as your output string is consistent you can extract it.