`langchain.chains.structured_output.base`.create_structured_output_runnable¶

langchain.chains.structured_output.base.create_structured_output_runnable(output_schema: Union[Dict[str, Any], Type[BaseModel]], llm: Runnable, prompt: Optional[BasePromptTemplate] = None, *, output_parser: Optional[Union[BaseOutputParser, BaseGenerationOutputParser]] = None, enforce_function_usage: bool = True, return_single: bool = True, mode: Literal['openai-functions', 'openai-tools', 'openai-json'] = 'openai-functions', **kwargs: Any) → Runnable[source]¶

自版本0.1.17以来已弃用：LangChain引入了一种名为with_structured_output的方法，该方法适用于具有工具调用功能的ChatModels。您可以在以下链接中了解更多关于此方法的信息：<https://python.langchain.ac.cn/docs/modules/model_io/chat/structured_output/>。请参考我们的提取用例文档以获取更多关于如何使用LLM进行信息提取的指南。<https://python.langchain.ac.cn/docs/use_cases/extraction/>。如果您发现其他问题，请在此处提供反馈：<https://github.com/langchain-ai/langchain/discussions/18154> 使用 `from langchain_core.pydantic_v1 import BaseModel, Field from langchain_anthropic import ChatAnthropic`。

: setup: str = Field(description="笑话的设置") punchline: str = Field(description="笑话的结尾")

或者任何其他支持工具的聊天模型。请参考结构化输出文档以查看支持 `with_structured_output` 的模型列表。模型文档：<https://python.langchain.ac.cn/docs/modules/model_io/chat/structured_output/>。model = ChatAnthropic(model="claude-3-opus-20240229"，temperature=0) structured_llm = model.with_structured_output(Joke) structured_llm.invoke("Tell me a joke about cats.

Make sure to call the Joke function.”)

“` instead.

创建用于提取结构化输出的可运行实例。

参数

output_schema (Union[Dict[str, Any], Type[BaseModel]]) – 可以是一个字典或pydantic.BaseModel类。如果传入的字典，则假定它已经是有效的JsonSchema。为了获得最佳结果，pydantic.BaseModels应该包含描述该模式内容的docstrings以及描述参数的描述。
llm (Runnable) – 要使用的语言模型。当模式为‘openai-function’时，假定支持OpenAI函数调用API。当模式为‘openai-json’时，假定支持OpenAI的response_format参数。
prompt (Optional[BasePromptTemplate]) – 要传递到模型中的BasePromptTemplate。当模式为‘openai-json’且prompt包含输入变量‘output_schema’时，给定的output_schema将被转换成JsonSchema并插入到提示中。
output_parser (Optional[Union[BaseOutputParser, BaseGenerationOutputParser]]) – 用于解析模型输出的输出解析器。默认情况下，将根据函数类型推导。如果传入pydantic.BaseModel，则OutputParser将尝试使用pydantic类解析输出。否则，模型输出将被解析为JSON。
mode (Literal['openai-functions', 'openai-tools', 'openai-json']) – 从模型中提取结构化输出的方式。如果为‘openai-functions’，则使用已弃用的‘functions’，‘function_call’模式进行OpenAI函数调用。如果为‘openai-tools’，则使用最新的‘tools’，‘tool_choice’模式进行OpenAI函数调用。这比使用‘openai-functions’更为推荐。如果为‘openai-json’，则使用response_format设置为JSON的OpenAI模型。
enforce_function_usage (bool) – 仅在模式为‘openai-tools’或‘openai-functions’时适用。如果为True，则模型将强制使用所提供的输出模式。如果为False，则模型可以选择是否使用输出模式。
return_single (布尔) – 仅当模式为‘openai-tools’时适用。是否返回结构化输出列表或单个输出。如果为 True 且模型未返回任何结构化输出，则链式输出为 None。如果为 False 且模型未返回任何结构化输出，则链式输出为一个空列表。
kwargs (任何类型) – 额外的命名参数。

返回

一个可运行的序列，将返回与给定: output_schema 匹配的结构化输出（s）。

返回类型

可运行

使用 Pydantic 模式 OpenAI 工具示例（mode=’openai-tools’）

from typing import Optional

from langchain.chains import create_structured_output_runnable
from langchain_openai import ChatOpenAI
from langchain_core.pydantic_v1 import BaseModel, Field


class RecordDog(BaseModel):
    '''Record some identifying information about a dog.'''

    name: str = Field(..., description="The dog's name")
    color: str = Field(..., description="The dog's color")
    fav_food: Optional[str] = Field(None, description="The dog's favorite food")

llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "You are an extraction algorithm. Please extract every possible instance"),
        ('human', '{input}')
    ]
)
structured_llm = create_structured_output_runnable(
    RecordDog,
    llm,
    mode="openai-tools",
    enforce_function_usage=True,
    return_single=True
)
structured_llm.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})
# -> RecordDog(name="Harry", color="brown", fav_food="chicken")

使用字典模式 OpenAI 工具示例（mode="openai-tools"）

from typing import Optional

from langchain.chains import create_structured_output_runnable
from langchain_openai import ChatOpenAI


dog_schema = {
    "type": "function",
    "function": {
        "name": "record_dog",
        "description": "Record some identifying information about a dog.",
        "parameters": {
            "type": "object",
            "properties": {
                "name": {
                    "description": "The dog's name",
                    "type": "string"
                },
                "color": {
                    "description": "The dog's color",
                    "type": "string"
                },
                "fav_food": {
                    "description": "The dog's favorite food",
                    "type": "string"
                }
            },
            "required": ["name", "color"]
        }
    }
}


llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm = create_structured_output_runnable(
    dog_schema,
    llm,
    mode="openai-tools",
    enforce_function_usage=True,
    return_single=True
)
structured_llm.invoke("Harry was a chubby brown beagle who loved chicken")
# -> {'name': 'Harry', 'color': 'brown', 'fav_food': 'chicken'}

OpenAI 函数示例（mode="openai-functions"）

from typing import Optional

from langchain.chains import create_structured_output_runnable
from langchain_openai import ChatOpenAI
from langchain_core.pydantic_v1 import BaseModel, Field

class Dog(BaseModel):
    '''Identifying information about a dog.'''

    name: str = Field(..., description="The dog's name")
    color: str = Field(..., description="The dog's color")
    fav_food: Optional[str] = Field(None, description="The dog's favorite food")

llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-functions")
structured_llm.invoke("Harry was a chubby brown beagle who loved chicken")
# -> Dog(name="Harry", color="brown", fav_food="chicken")

带有提示的 OpenAI 函数示例

from typing import Optional

from langchain.chains import create_structured_output_runnable
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.pydantic_v1 import BaseModel, Field

class Dog(BaseModel):
    '''Identifying information about a dog.'''

    name: str = Field(..., description="The dog's name")
    color: str = Field(..., description="The dog's color")
    fav_food: Optional[str] = Field(None, description="The dog's favorite food")

llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-functions")
system = '''Extract information about any dogs mentioned in the user input.'''
prompt = ChatPromptTemplate.from_messages(
    [("system", system), ("human", "{input}"),]
)
chain = prompt | structured_llm
chain.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})
# -> Dog(name="Harry", color="brown", fav_food="chicken")

OpenAI JSON 响应格式示例（mode="openai-json"）

from typing import Optional

from langchain.chains import create_structured_output_runnable
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.pydantic_v1 import BaseModel, Field

class Dog(BaseModel):
    '''Identifying information about a dog.'''

    name: str = Field(..., description="The dog's name")
    color: str = Field(..., description="The dog's color")
    fav_food: Optional[str] = Field(None, description="The dog's favorite food")

llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-json")
system = '''You are a world class assistant for extracting information in structured JSON formats.
Extract a valid JSON blob from the user input that matches the following JSON Schema:

{output_schema}'''
prompt = ChatPromptTemplate.from_messages(
    [("system", system), ("human", "{input}"),]
)
chain = prompt | structured_llm
chain.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})

langchain.chains.structured_output.base.create_structured_output_runnable¶

`langchain.chains.structured_output.base`.create_structured_output_runnable¶