-
Small refactor to ChatGPT requests, separating all the key variables to make it… · 9b5f8870
Small refactor to ChatGPT requests, separating all the key variables to make it easier to modify. Also, adding in token estimation and limits: 200 output tokens, 75% of the 16k context window, so super long conversations exceeding 12k tokens will be trimmed to the most recent messages.
Jonathan Thomas authored9b5f8870
×