search

pteichman / cobe

A Markov chain based text generation library and MegaHAL style chatbot
http://teichman.org/blog/
MIT License
239 stars 51 forks source link

Add a dont_learn parameter to Brain.reply() #11

Closed wodim closed 10 years ago

wodim commented 10 years ago

I would like to have a dont_learn parameter for Brain.reply() if possible. It will make cobe generate a sentence, as always, but it won't learn anything about the sentence that was feed as the text parameter.

pteichman commented 10 years ago

This is already the behavior of Brain.reply(text). The only way to learn text is to call Brain.learn(text) explicitly.

In cobe 2.x, reply() is effectively a read only operation.