langchain_core.beta.runnables.context.Context

class langchain_core.beta.runnables.context.Context

用于可运行对象的上下文。

Context 类提供了在可运行对象中创建上下文范围、获取器和设置器的方法。它允许在程序执行过程中管理和访问上下文信息。

示例：

from langchain_core.beta.runnables.context import Context
from langchain_core.runnables.passthrough import RunnablePassthrough
from langchain_core.prompts.prompt import PromptTemplate
from langchain_core.output_parsers.string import StrOutputParser
from tests.unit_tests.fake.llm import FakeListLLM

chain = (
    Context.setter("input")
    | {
        "context": RunnablePassthrough()
                | Context.setter("context"),
        "question": RunnablePassthrough(),
    }
    | PromptTemplate.from_template("{context} {question}")
    | FakeListLLM(responses=["hello"])
    | StrOutputParser()
    | {
        "result": RunnablePassthrough(),
        "context": Context.getter("context"),
        "input": Context.getter("input"),
    }
)

# 使用链
output = chain.invoke("What's your name?")
print(output["result"])  # 输出: "hello"
print(output["context"])  # 输出: "What's your name?"
print(output["input"])  # 输出: "What's your name?

Methods

__init__()
create_scope(scope, /)	创建一个上下文范围。
getter(key, /)
setter([_key, _value])

__init__()

static create_scope(scope: str, /) → PrefixContext

创建一个上下文范围。

参数:

scope: 范围。

返回:

上下文范围。

Parameters

scope (str) –

Return type

PrefixContext

static getter(key: Union[str, List[str]], /) → ContextGet

Parameters

key (Union[str, List[str]]) –

Return type

ContextGet

static setter(_key: Optional[str] = None, _value: Optional[Union[Runnable[Input, Output], Callable[[Input], Output], Callable[[Input], Awaitable[Output]], Any]] = None, /, **kwargs: Union[Runnable[Input, Output], Callable[[Input], Output], Callable[[Input], Awaitable[Output]], Any]) → ContextSet

Parameters

• _key (Optional[str]) –

• _value (Optional[Union[Runnable[Input, Output], Callable[[Input], Output], Callable[[Input], Awaitable[Output]], Any]]) –

• kwargs (Union[Runnable[Input, Output], Callable[[Input], Output], Callable[[Input], Awaitable[Output]], Any]) –

Return type

ContextSet