包装器

langsmith.wrappers

该模块为常用库提供了便捷的跟踪包装器。

函数	描述
wrap_anthropic	修补 Anthropic 客户端，使其可被跟踪。
wrap_openai	修补 OpenAI 客户端，使其可被跟踪。

wrap_anthropic

wrap_anthropic(client: C, *, tracing_extra: TracingExtra | None = None) -> C

修补 Anthropic 客户端，使其可被跟踪。

参数	描述
client	要修补的客户端。 类型： Anthropic | AsyncAnthropic
tracing_extra	额外的跟踪信息。默认为 None。 类型： TracingExtra | None 默认值： None

返回	描述
C	Union[Anthropic, AsyncAnthropic]: 修补后的客户端。

示例

.. code-block:: python

    import anthropic
    from langsmith import wrappers

    client = wrappers.wrap_anthropic(anthropic.Anthropic())

    # Use Anthropic client same as you normally would:
    system = "You are a helpful assistant."
    messages = [
        {
            "role": "user",
            "content": "What physics breakthroughs do you predict will happen by 2300?",
        }
    ]
    completion = client.messages.create(
        model="claude-3-5-sonnet-latest",
        messages=messages,
        max_tokens=1000,
        system=system,
    )
    print(completion.content)

    # You can also use the streaming context manager:
    with client.messages.stream(
        model="claude-3-5-sonnet-latest",
        messages=messages,
        max_tokens=1000,
        system=system,
    ) as stream:
        for text in stream.text_stream:
            print(text, end="", flush=True)
        message = stream.get_final_message()

wrap_openai

wrap_openai(
    client: C,
    *,
    tracing_extra: TracingExtra | None = None,
    chat_name: str = "ChatOpenAI",
    completions_name: str = "OpenAI",
) -> C

修补 OpenAI 客户端，使其可被跟踪。

支持

• 聊天和响应 API
• 同步和异步 OpenAI 客户端
• create() 和 parse() 方法
• 带流和不带流

参数	描述
client	要修补的客户端。 类型： OpenAI | AsyncOpenAI
tracing_extra	额外的跟踪信息。默认为 None。 类型： TracingExtra | None 默认值： None
chat_name	聊天补全端点的运行名称。默认为“ChatOpenAI”。 类型： str 默认值： 'ChatOpenAI'
completions_name	补全端点的运行名称。默认为“OpenAI”。 类型： str 默认值： 'OpenAI'

返回	描述
C	Union[OpenAI, AsyncOpenAI]: 修补后的客户端。

示例

.. code-block:: python

    import openai
    from langsmith import wrappers

    # Use OpenAI client same as you normally would.
    client = wrappers.wrap_openai(openai.OpenAI())

    # Chat API:
    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {
            "role": "user",
            "content": "What physics breakthroughs do you predict will happen by 2300?",
        },
    ]
    completion = client.chat.completions.create(
        model="gpt-4o-mini", messages=messages
    )
    print(completion.choices[0].message.content)

    # Responses API:
    response = client.responses.create(
        model="gpt-4o-mini",
        messages=messages,
    )
    print(response.output_text)

.. versionchanged:: 0.3.16

Support for Responses API added.