Refactor LLM prompt to better use capabilities of the gpt4o-mini #227
Comments
github-actions bot
pushed a commit
that referenced
this issue
Jul 19, 2024
**Recommendation:** Because `GPT-4o-mini` is much smarter than `GPT-3.5-turbo`, I recommend you to disable GPT function processor `FFUN_LIBRARIAN_OPENAI_CHAT_35_FUNCTIONS_PROCESSOR__ENABLED="False"` and use only standard GPT processor `FFUN_LIBRARIAN_OPENAI_CHAT_35_PROCESSOR__ENABLED="False"`. In [gh-227](#227), one of the processors will be refactored, and one of them will be removed. - [gh-226](#226) Switch used OpenAI model to gpt4o-mini
github-actions bot
pushed a commit
that referenced
this issue
Jul 21, 2024
**Configs migration:** if you are have turned on OpenAI ChatGPT processors, like `FFUN_LIBRARIAN_OPENAI_CHAT_35_FUNCTIONS_PROCESSOR__ENABLED="True"` or `FFUN_LIBRARIAN_OPENAI_CHAT_35_PROCESSOR__ENABLED="True", remove their configs and add configs for OpenAI General Processor, like `FFUN_LIBRARIAN_OPENAI_GENERAL_PROCESSOR__ENABLED="True"`, instead. The semantic of the configs is the same. - [gh-227](#227) — Old OpenAI ChatGPT processors is replaced with OpenAI General Processor which utilizes power of GPT-4o-mini model.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
caused by gh-226
Also, tune API request parameters (temperature, etc.)
The text was updated successfully, but these errors were encountered: