parea sdk py下载parea sdk py源代码下载

测试，评估和监视您的AI应用程序

测试，评估和监视您的AI应用程序

？ Twitter/X • ？不和谐• parea ai • ？文档

Parea AI提供了一个SDK来评估和监视您的AI应用程序。您可以在下面看到快速入门：

评估和测试您的LLM应用程序
LLM应用程序的仪器记录和可观察性
部署提示以实现工程师与主题专家之间的合作

我们的完整文档在这里。

安装

pip install -U parea-ai

或与Poetry安装

poetry add parea-ai

评估您的LLM应用程序

测试您的AI应用意味着通过数据集执行并使用评估功能进行评分。这是通过定义和运行实验在Parea中完成的。在下面，您可以看到如何使用Levenshtein距离度量标准测试如何测试问候机器人的示例。

 from parea import Parea , trace
from parea . evals . general import levenshtein

p = Parea ( api_key = "<<PAREA_API_KEY>>" )  # replace with Parea AI API key

# use the trace decorator to score the output with the Levenshtein distance  
@ trace ( eval_funcs = [ levenshtein ])
def greeting ( name : str ) -> str :
    return f"Hello { name } "

data = [
    { "name" : "Foo" , "target" : "Hi Foo" },
    { "name" : "Bar" , "target" : "Hello Bar" },
]

p . experiment (
    name = "Greeting" ,
    data = data ,
    func = greeting ,
). run ()

在上面的片段中，我们使用trace装饰器捕获功能的所有输入和输出。该装饰器还可以通过在后台执行levenshtein评估来评分输出。然后，我们通过p.experiment定义了一个实验，以评估数据集（此处词典列表）上的功能（ greeting ）。最后，调用run将执行实验，并为数据集的任何示例创建输出，分数和痕迹的报告。您可以在此处找到指向执行实验的链接。（Todo：填充实验）

记录和可观察性

通过包装各自的客户，您可以自动将所有LLM调用访问到OpenAI＆Anthropic。此外，使用trace Decorator，您可以创建LLM应用程序的层次结构轨迹，以与RAG管道的检索步骤相关联的LLM调用。您可以在此处看到完整的可观察性文档，以及我们在这里的Langchain，DSPY，Litellm等人的集成。

自动记录所有OpenAi电话

要自动记录任何OpenAI调用，您可以使用wrap_openai_client方法与parea客户端包装OpenAI客户端。

 from openai import OpenAI
from parea import Parea

client = OpenAI ( api_key = "OPENAI_API_KEY" )

# All you need to do is add these two lines
p = Parea ( api_key = "PAREA_API_KEY" )  # replace with your API key
p . wrap_openai_client ( client )

response = client . chat . completions . create (
    model = "gpt-4o" ,
    messages = [
        {
            "role" : "user" ,
            "content" : "Write a Hello World program in Python using FastAPI." ,
        }
    ],
)
print ( response . choices [ 0 ]. message . content )

自动记录所有人类通话

要自动记录任何人类呼叫，您可以使用wrap_anthropic_client方法与Parea客户端一起包裹人类客户端。

 import anthropic
from parea import Parea

p = Parea ( api_key = "PAREA_API_KEY" )  # replace with your API key

client = anthropic . Anthropic ()
p . wrap_anthropic_client ( client )

message = client . messages . create (
    model = "claude-3-opus-20240229" ,
    max_tokens = 1024 ,
    messages = [
        {
            "role" : "user" ,
            "content" : "Write a Hello World program in Python using FastAPI." ,
        }
    ],
)
print ( message . content [ 0 ]. text )

嵌套迹线

通过使用trace Decorator，您可以创建LLM应用程序的层次结构痕迹。

 from openai import OpenAI
from parea import Parea , trace

client = OpenAI ( api_key = "OPENAI_API_KEY" )  # replace with your API key

p = Parea ( api_key = "PAREA_API_KEY" )  # replace with your API key
p . wrap_openai_client ( client )


# We generally recommend creating a helper function to make LLM API calls.
def llm ( messages : list [ dict [ str , str ]]) -> str :
    response = client . chat . completions . create ( model = "gpt-4o" , messages = messages )
    return response . choices [ 0 ]. message . content


# This will give the Span the name of the function.
# Without the decorator the default name for all LLM call logs is `llm-openai`
@ trace
def hello_world ( lang : str , framework : str ):
    return llm ([{ "role" : "user" , "content" : f"Write a Hello World program in { lang } using { framework } ." }])

@ trace
def critique_code ( code : str ):
    return llm ([{ "role" : "user" , "content" : f"How can we improve this code: n { code } " }])

# Our top level function is called chain. By adding the trace decorator here,
# all sub-functions will automatically be logged and associated with this trace.
# Notice, you can also add metadata to the trace, we'll revisit this functionality later.
@ trace ( metadata = { "purpose" : "example" }, end_user_identifier = "John Doe" )
def chain ( lang : str , framework : str ) -> str :
    return critique_code ( hello_world ( lang , framework ))


print ( chain ( "Python" , "FastAPI" ))

部署提示

部署的提示可以与产品经理和主题专家等非工程师合作。用户可以在Parea的操场上迭代，完善和测试提示。修补后，您可以部署该提示，这意味着它是通过API端点暴露的，以将其集成到您的应用程序中。在这里查看我们的完整文档。

 from parea import Parea
from parea . schemas . models import Completion , UseDeployedPrompt , CompletionResponse , UseDeployedPromptResponse


p = Parea ( api_key = "<PAREA_API_KEY>" )

# You will find this deployment_id in the Parea dashboard
deployment_id = '<DEPLOYMENT_ID>'

# Assuming your deployed prompt's message is:
# {"role": "user", "content": "Write a hello world program using {{x}} and the {{y}} framework."}
inputs = { "x" : "Golang" , "y" : "Fiber" }

# You can easily unpack a dictionary into an attrs class
test_completion = Completion (
  ** {
    "deployment_id" : deployment_id ,
    "llm_inputs" : inputs ,
    "metadata" : { "purpose" : "testing" }
  }
)

# By passing in my inputs, in addition to the raw message with unfilled variables {{x}} and {{y}}, 
# you we will also get the filled-in prompt:
# {"role": "user", "content": "Write a hello world program using Golang and the Fiber framework."}
test_get_prompt = UseDeployedPrompt ( deployment_id = deployment_id , llm_inputs = inputs )


def main ():
  completion_response : CompletionResponse = p . completion ( data = test_completion )
  print ( completion_response )
  deployed_prompt : UseDeployedPromptResponse = p . get_prompt ( data = test_get_prompt )
  print ( " n n " )
  print ( deployed_prompt )

？执照

该项目是根据Apache Software License 2.0许可证的条款许可的。有关更多详细信息，请参见许可证。

？引用

 @misc { parea-sdk ,
  author = { joel-parea-ai,joschkabraun } ,
  title = { Parea python sdk } ,
  year = { 2023 } ,
  publisher = { GitHub } ,
  journal = { GitHub repository } ,
  howpublished = { url{https://github.com/parea-ai/parea-sdk} }
}