guardrails下载 - guardrails源码下载

guardrails

Ai源码

v0.6.0

下载

什么是guardrails ？

guardrails是一个 Python 框架，通过执行两个关键功能来帮助构建可靠的 AI 应用程序：

guardrails在您的应用程序中运行输入/输出防护，以检测、量化和减轻特定类型风险的存在。要了解全套风险，请查看guardrails中心。
guardrails可帮助您从法学硕士生成结构化数据。

guardrails轮毂

guardrails Hub 是特定类型风险的预构建措施（称为“验证器”）的集合。多个验证器可以组合在一起形成输入和输出防护，拦截 LLM 的输入和输出。访问guardrails Hub 查看验证器的完整列表及其文档。

安装

 pip install guardrails - ai

入门

为 LLM 验证创建输入和输出防护

下载并配置guardrails Hub CLI。

pip install guardrails -ai
guardrails configure

从guardrails Hub 安装护栏。

 guardrails hub install hub:// guardrails /regex_match

从已安装的护栏创建一个守卫。

 from guardrails import Guard , OnFailAction
from guardrails . hub import RegexMatch

guard = Guard (). use (
    RegexMatch , regex = "(?d{3})?-? *d{3}-? *-?d{4}" , on_fail = OnFailAction . EXCEPTION
)

guard . validate ( "123-456-7890" )  # Guardrail passes

try :
    guard . validate ( "1234-789-0000" )  # Guardrail fails
except Exception as e :
    print ( e )

输出：

 Validation failed for field with errors: Result must match (?d{3})?-? *d{3}-? *-?d{4}

在一个 Guard 内运行多个guardrails 。首先，从guardrails中心安装必要的guardrails 。

 guardrails hub install hub:// guardrails /competitor_check
guardrails hub install hub:// guardrails /toxic_language

然后，从已安装的guardrails创建一个 Guard 。

 from guardrails import Guard , OnFailAction
from guardrails . hub import CompetitorCheck , ToxicLanguage

guard = Guard (). use_many (
    CompetitorCheck ([ "Apple" , "Microsoft" , "Google" ], on_fail = OnFailAction . EXCEPTION ),
    ToxicLanguage ( threshold = 0.5 , validation_method = "sentence" , on_fail = OnFailAction . EXCEPTION )
)

guard . validate (
    """An apple a day keeps a doctor away.
    This is good advice for keeping your health."""
)  # Both the guardrails pass

try :
    guard . validate (
        """Shut the hell up! Apple just released a new iPhone."""
    )  # Both the guardrails fail
except Exception as e :
    print ( e )

输出：

 Validation failed for field with errors: Found the following competitors: [['Apple']]. Please avoid naming those competitors next time, The following sentences in your response were found to be toxic:

- Shut the hell up!

使用guardrails从法学硕士生成结构化数据

让我们看一个例子，我们要求法学硕士生成假宠物名。为此，我们将创建一个 Pydantic BaseModel 来表示我们想要的输出的结构。

 from pydantic import BaseModel , Field

class Pet ( BaseModel ):
    pet_type : str = Field ( description = "Species of pet" )
    name : str = Field ( description = "a unique pet name" )

现在，从Pet类创建一个 Guard。 Guard 可用于以某种方式调用 LLM，以便将输出格式化为Pet类。在幕后，这是通过以下两种方法之一完成的：

函数调用：对于支持函数调用的LLM，我们使用函数调用语法生成结构化数据。
提示优化：对于不支持函数调用的LLM，我们将预期输出的schema添加到提示中，以便LLM可以生成结构化数据。

 from guardrails import Guard
import openai

prompt = """
    What kind of pet should I get and what should I name it?

    ${gr.complete_json_suffix_v2}
"""
guard = Guard . for_pydantic ( output_class = Pet , prompt = prompt )

raw_output , validated_output , * rest = guard (
    llm_api = openai . completions . create ,
    engine = "gpt-3.5-turbo-instruct"
)

print ( validated_output )

这打印：

 {
    "pet_type": "dog",
    "name": "Buddy
}

guardrails服务器

guardrails可以设置为由 Flask 通过guardrails start提供的独立服务，允许您通过 REST API 与其进行交互。这种方法简化了guardrails驱动的应用程序的开发和部署。

安装： pip install " guardrails -ai"
配置： guardrails configure
创建配置： guardrails create --validators=hub:// guardrails /two_words --name=two-word-guard
启动开发服务器： guardrails start --config=./config.py
通过下面的代码片段与开发服务器交互

 # with the guardrails client
import guardrails as gr

gr.settings.use_server = True
guard = gr.Guard(name='two-word-guard')
guard.validate('this is more than two words')

# or with the openai sdk
import openai
openai.base_url = "http://localhost:8000/guards/two-word-guard/openai/v1/"
os.environ["OPENAI_API_KEY"] = "youropenaikey"

messages = [
        {
            "role": "user",
            "content": "tell me about an apple with 3 words exactly",
        },
    ]

completion = openai.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
)

对于生产部署，我们建议使用 Docker 和 Gunicorn 作为 WSGI 服务器，以提高性能和可扩展性。