toucans

没有胡说八道的工程，使用Jinja2进行动态及时的模板和Litellm，以无缝使用各种LLM提供商。

入门

安装

 pip install toucans

用法

初始化及时功能：

 from toucans import PromptFunction

sentiment = PromptFunction (
    model = "gpt-4" ,
    temperature = 0.7 ,
    messages = [
        { "role" : "system" , "content" : "You are a helpful mood-sensitive agent." },
        { "role" : "user" , "content" : "Determine the sentiment of the sentence: {{ sentence }}" },
    ],
)

生成完成

通过用句子调用提示功能来生成一个完成：

 completion = sentiment ( sentence = "I'm so happy!" )

批处理并行生成完成

 batch_args = [
    { "sentence" : "Toucans is nice Python package!" }, 
    { "sentence" : "I hate bloated prompt engineering frameworks!" }
]

completion_batch = sentiment . batch_call ( batch_args = batch_args )

局部及时功能序列化

保存/加载提示功能到目录：

 # Push to dir (not implemented yet)
sentiment . push_to_dir ( "./sentiment/" )

# Load from dir (not implemented yet)
sentiment = PromptFunction . from_dir ( "./sentiment/" )

Toucans Hub

从Toucans Hub推动/提取及时功能：

 # Push to hub
sentiment . push_to_hub ( "juunge/sentiment" )

# Load from hub
sentiment = PromptFunction . from_hub ( "juunge/sentiment" )

目前，从Toucans集线器加载需要自己托管一个实例，并设置HUB_API_URL环境变量。