skit_pipelines.components.final_conversation_generator package

Module contents

final_conversation_generator(output_path: <kfp.components._python_op.OutputPath object at 0x1097a5a00>, situation_info_list: typing.List[typing.Dict[str, str]], s3_links_to_prompts: str, n_iter: int, n_choice: int, temperature: float, model: str, llm_trainer_repo_name: str, llm_trainer_repo_branch: str)[source]
Parameters

  • situation_info_list (list) – list containing the id and situation mapping from the table

  • s3_links_to_prompts (str) – s3 links to the prompt to the model for data generation

  • n_iter (int) – No of times we make iterate on scenarios list to generate conversations

  • n_choice (int) – No of convs generated in a single time from a scenario.

  • temperature (float) – Temperature

  • model (str) – Model to be used for generating data

  • llm_trainer_repo_name (str) – The conversation generation repo name in Github.

  • llm_trainer_repo_branch (str, optional) – The branch name in the conversation generation repo to use , defaults to main.

output: path of the txt file where conversations is stored

final_conversation_generator_op(situation_info_list: List[Dict[str, str]], s3_links_to_prompts: str, n_iter: int, n_choice: int, temperature: float, model: str, llm_trainer_repo_name: str, llm_trainer_repo_branch: str)

Final conversation generator