Layerup 安全

该Layerup Security 集成允许您保护对任何 LangChain LLM、LLM 链或 LLM 代理的调用。LLM 对象围绕任何现有的 LLM 对象进行包装，允许在用户和您的 LLM 之间建立安全层。

虽然 Layerup Security 对象被设计为 LLM，但它本身并不是 LLM，它只是围绕 LLM 进行包装，使其能够适应与底层 LLM 相同的功能。

设置

首先，您需要一个来自 Layerup 网站 的 Layerup Security 帐户。

接下来，通过仪表板创建一个项目，并复制您的 API 密钥。我们建议将您的 API 密钥放在项目的环境中。

安装 Layerup Security SDK

pip install LayerupSecurity

并安装 LangChain 社区版

pip install langchain-community

现在，您已准备好开始使用 Layerup Security 保护您的 LLM 调用了！

from langchain_community.llms.layerup_security import LayerupSecurity
from langchain_openai import OpenAI

# Create an instance of your favorite LLM
openai = OpenAI(
    model_name="gpt-3.5-turbo",
    openai_api_key="OPENAI_API_KEY",
)

# Configure Layerup Security
layerup_security = LayerupSecurity(
    # Specify a LLM that Layerup Security will wrap around
    llm=openai,

    # Layerup API key, from the Layerup dashboard
    layerup_api_key="LAYERUP_API_KEY",

    # Custom base URL, if self hosting
    layerup_api_base_url="https://api.uselayerup.com/v1",

    # List of guardrails to run on prompts before the LLM is invoked
    prompt_guardrails=[],

    # List of guardrails to run on responses from the LLM
    response_guardrails=["layerup.hallucination"],

    # Whether or not to mask the prompt for PII & sensitive data before it is sent to the LLM
    mask=False,

    # Metadata for abuse tracking, customer tracking, and scope tracking.
    metadata={"customer": "[email protected]"},

    # Handler for guardrail violations on the prompt guardrails
    handle_prompt_guardrail_violation=(
        lambda violation: {
            "role": "assistant",
            "content": (
                "There was sensitive data! I cannot respond. "
                "Here's a dynamic canned response. Current date: {}"
            ).format(datetime.now())
        }
        if violation["offending_guardrail"] == "layerup.sensitive_data"
        else None
    ),

    # Handler for guardrail violations on the response guardrails
    handle_response_guardrail_violation=(
        lambda violation: {
            "role": "assistant",
            "content": (
                "Custom canned response with dynamic data! "
                "The violation rule was {}."
            ).format(violation["offending_guardrail"])
        }
    ),
)

response = layerup_security.invoke(
    "Summarize this message: my name is Bob Dylan. My SSN is 123-45-6789."
)

API 参考：LayerupSecurity | OpenAI

相关

• LLM 概念指南
• LLM 操作指南