eva2000
Well-known member
True depends on how you plan to analyse Xenforo messages. To get around API limits, you can batch thread/messages into one API call, so that can increase token context sizes. In a 1 - 2 million context LLM model, you could batch between 10,000 and 20,000 messages in one API call https://github.com/centminmod/or-cli/blob/master/examples/example-structured-xenforo-output.mdThat looks like a really cool tool you've been working on.
For the purpose of just analysing single message DMs though, surely you don't need such huge context limits?
