OpenAI 中间件集成

使用 LangChain Python 集成 OpenAI 中间件。

专为 OpenAI 模型设计的中间件。了解更多关于中间件的信息。

中间件	描述
Content moderation	使用 OpenAI 的审核端点审核智能体流量

内容审核

使用 OpenAI 的审核端点审核智能体流量（用户输入、模型输出和工具结果），以检测和处理不安全内容。 内容审核适用于以下场景：

• 需要内容安全和合规的应用
• 过滤有害、仇恨或不当内容
• 需要安全护栏的面向客户的智能体
• 满足平台审核要求

了解更多关于 OpenAI’s moderation models and categories.

API reference: OpenAIModerationMiddleware

from langchain_openai import ChatOpenAI
from langchain_openai.middleware import OpenAIModerationMiddleware
from langchain.agents import create_agent

agent = create_agent(
    model=ChatOpenAI(model="gpt-5.4"),
    tools=[search_tool, database_tool],
    middleware=[
        OpenAIModerationMiddleware(
            model="omni-moderation-latest",
            check_input=True,
            check_output=True,
            exit_behavior="end",
        ),
    ],
)

配置选项

model · ModerationModel · default: "omni-moderation-latest"

OpenAI moderation model to use. Options: 'omni-moderation-latest', 'omni-moderation-2024-09-26', 'text-moderation-latest', 'text-moderation-stable'

check_input · bool · default: "True"

Whether to check user input messages before the model is called

check_output · bool · default: "True"

Whether to check model output messages after the model is called

check_tool_results · bool · default: "False"

Whether to check tool result messages before the model is called

exit_behavior · string · default: "end"

How to handle violations when content is flagged. Options:

• 'end' - End agent execution immediately with a violation message
• 'error' - Raise OpenAIModerationError exception
• 'replace' - Replace the flagged content with the violation message and continue

violation_message · str | None

Custom template for violation messages. Supports template variables:

• {categories} - Comma-separated list of flagged categories
• {category_scores} - JSON string of category scores
• {original_content} - The original flagged content

Default: "I'm sorry, but I can't comply with that request. It was flagged for {categories}."

client · OpenAI | None

Optional pre-configured OpenAI client to reuse. If not provided, a new client will be created.

async_client · AsyncOpenAI | None

Optional pre-configured AsyncOpenAI client to reuse. If not provided, a new async client will be created.

完整示例

The middleware integrates OpenAI’s moderation endpoint to check content at different stages:

Moderation stages:

• check_input - User messages before model call
• check_output - AI messages after model call
• check_tool_results - Tool outputs before model call

Exit behaviors:

• 'end' (default) - Stop execution with violation message
• 'error' - Raise exception for application handling
• 'replace' - Replace flagged content and continue

from langchain_openai import ChatOpenAI
from langchain_openai.middleware import OpenAIModerationMiddleware
from langchain.agents import create_agent


# Basic moderation
agent = create_agent(
    model=ChatOpenAI(model="gpt-5.4"),
    tools=[search_tool, customer_data_tool],
    middleware=[
        OpenAIModerationMiddleware(
            model="omni-moderation-latest",
            check_input=True,
            check_output=True,
        ),
    ],
)

# Strict moderation with custom message
agent_strict = create_agent(
    model=ChatOpenAI(model="gpt-5.4"),
    tools=[search_tool, customer_data_tool],
    middleware=[
        OpenAIModerationMiddleware(
            model="omni-moderation-latest",
            check_input=True,
            check_output=True,
            check_tool_results=True,
            exit_behavior="error",
            violation_message=(
                "Content policy violation detected: {categories}. "
                "Please rephrase your request."
            ),
        ),
    ],
)

# Moderation with replacement behavior
agent_replace = create_agent(
    model=ChatOpenAI(model="gpt-5.4"),
    tools=[search_tool],
    middleware=[
        OpenAIModerationMiddleware(
            check_input=True,
            exit_behavior="replace",
            violation_message="[Content removed due to safety policies]",
        ),
    ],
)

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.