LLMConfigurationBase#

class council.llm.LLMConfigurationBase(env_var_prefix: str)[source]#

Bases: ABC

Configuration for OpenAI LLM Chat Completion GPT Model

Parameters:

  • temperature (float) – optional temperature settings for the LLM

  • max_tokens (int) – optional limit on number of tokens

  • top_p (int) – optional he model only takes into account the tokens with the highest probability mass

  • n (int) – optional How many completions to generate for each prompt

  • presence_penalty (float) – optional, impacts how the model penalizes new tokens based on whether they have appeared in the text so far

  • frequency_penalty (float) – optional, impacts how the model penalizes new tokens based on their existing frequency in the text.