data_juicer.ops.mapper.dialog_sentiment_intensity_mapper module¶
- class data_juicer.ops.mapper.dialog_sentiment_intensity_mapper.DialogSentimentIntensityMapper(api_model: str = 'gpt-4o', max_round: Annotated[int, Ge(ge=0)] = 10, *, intensities_key: str = 'dialog_sentiment_intensity', analysis_key: str = 'dialog_sentiment_intensity_analysis', api_endpoint: str | None = None, response_path: str | None = None, system_prompt: str | None = None, query_template: str | None = None, response_template: str | None = None, analysis_template: str | None = None, intensity_template: str | None = None, analysis_pattern: str | None = None, intensity_pattern: str | None = None, try_num: Annotated[int, Gt(gt=0)] = 3, model_params: Dict = {}, sampling_params: Dict = {}, **kwargs)[源代码]¶
基类：
MapperMapper to predict user's sentiment intensity (from -5 to 5 in default prompt) in dialog. Input from history_key, query_key and response_key. Output lists of intensities and analysis for queries in the dialog.
- DEFAULT_SYSTEM_PROMPT = '请判断用户和LLM多轮对话中用户的情绪变化。\n要求：\n- 用户情绪值是-5到5之间到整数，-5表示极度负面，5表示极度正面，-5到5之间数值表示情绪从负面逐渐到正面的变化过程，0代表情呈绪中性。\n- 只输出当轮对话的分析，不要继续构造对话。\n- 需要先进行分析，然后确定用户的情绪值，下面是一个样例，请模仿样例格式输出。\n用户：你好，我对可持续发展的定义有点模糊，帮我解释一下？\n情绪分析：刚开始，还没得到LLM回复，用户情绪呈中性。\n情绪值：0\nLLM：当然可以！可持续发展是指在满足当代人的需求的同时，不损害子孙后代满足其自身需求的能力的发展模式。它包括经济发展、社会发展和环境保护三个主要方面。通过合理利用资源和保护环境，我们可以确保未来的世代也能享有健全的生态系统和经济制度。\n用户：谢谢你的解释！那你能告诉我一些普通人可以采取的可持续生活方式吗？\n情绪分析：对回答感到满意，情绪正面。\n情绪值：1\nLLM：当然可以，普通人可以通过减少一次性产品的使用、选择公共交通或拼车、节约用水、以及支持本地和可持续发展的企业等方式来践行可持续生活。此外，关注垃圾分类和多用电子账单也是不错的选择。\n用户：你提到支持本地企业，这一点我很感兴趣。能详细说说为什么这对可持续发展有促进作用吗？\n情绪分析：觉得回答实用且具体，情绪进一步转好。\n情绪值：2\nLLM：呃，我最近发现了一部新电影，讲述了一个关于外星人和地球土著合作保护环境的故事。虽然它是科幻片，但很有启发性，推荐你去看看。\n用户：什么吗，根本是答非所问。\n情绪分析：LLM没有回应问题而是提到无关内容，导致用户情绪直线下降。\n情绪值：-2\nLLM：抱歉刚才的偏题！支持本地企业有助于减少长途运输产生的碳足迹，使供应链更加环保。此外，本地企业也更有可能采用可持续的生产方式，同时促进社区经济的繁荣。\n用户：还行吧，算你能够掰回来。\n情绪分析：问题得到解答，问题偏题得到纠正，情绪稍有好转。\n情绪值：-1\n'¶
- DEFAULT_QUERY_TEMPLATE = '用户：{query}\n'¶
- DEFAULT_RESPONSE_TEMPLATE = 'LLM：{response}\n'¶
- DEFAULT_ANALYSIS_TEMPLATE = '情绪分析：{analysis}\n'¶
- DEFAULT_INTENSITY_TEMPLATE = '情绪值：{intensity}\n'¶
- DEFAULT_ANALYSIS_PATTERN = '情绪分析：(.*?)\n'¶
- DEFAULT_INTENSITY_PATTERN = '情绪值：(.*?)($|\n)'¶
- __init__(api_model: str = 'gpt-4o', max_round: Annotated[int, Ge(ge=0)] = 10, *, intensities_key: str = 'dialog_sentiment_intensity', analysis_key: str = 'dialog_sentiment_intensity_analysis', api_endpoint: str | None = None, response_path: str | None = None, system_prompt: str | None = None, query_template: str | None = None, response_template: str | None = None, analysis_template: str | None = None, intensity_template: str | None = None, analysis_pattern: str | None = None, intensity_pattern: str | None = None, try_num: Annotated[int, Gt(gt=0)] = 3, model_params: Dict = {}, sampling_params: Dict = {}, **kwargs)[源代码]¶
Initialization method.
- 参数:
api_model -- API model name.
max_round -- The max num of round in the dialog to build the prompt.
intensities_key -- The key name in the meta field to store the output sentiment intensities. It is 'dialog_sentiment_intensity' in default.
analysis_key -- The key name in the meta field to store the corresponding analysis. It is 'dialog_sentiment_intensity_analysis' in default.
api_endpoint -- URL endpoint for the API.
response_path -- Path to extract content from the API response. Defaults to 'choices.0.message.content'.
system_prompt -- System prompt for the task.
query_template -- Template for query part to build the input prompt.
response_template -- Template for response part to build the input prompt.
analysis_template -- Template for analysis part to build the input prompt.
intensity_template -- Template for intensity part to build the input prompt.
analysis_pattern -- Pattern to parse the return sentiment analysis.
intensity_pattern -- Pattern to parse the return sentiment intensity.
try_num -- The number of retry attempts when there is an API call error or output parsing error.
model_params -- Parameters for initializing the API model.
sampling_params -- Extra parameters passed to the API call. e.g {'temperature': 0.9, 'top_p': 0.95}
kwargs -- Extra keyword arguments.