函数式 API
entrypoint ¶
使用 entrypoint 装饰器定义 LangGraph 工作流。
函数签名¶
被装饰的函数必须接受一个单一参数，该参数用作函数的输入。此输入参数可以是任何类型。使用字典向函数传递多个参数。
可注入参数¶
被装饰的函数可以请求访问将在运行时自动注入的其他参数。这些参数包括
| 参数 | 描述 |
|---|---|
store |
BaseStore 的实例。用于长期记忆。 |
writer |
用于将自定义数据写入流的 StreamWriter 实例。 |
config |
配置对象（又名 RunnableConfig），其中包含运行时配置值。 |
previous |
给定线程的先前返回值（仅当提供检查点程序时可用）。 |
entrypoint 装饰器可以应用于同步函数或异步函数。
状态管理¶
previous 参数可用于访问同一线程 ID 上 entrypoint 先前调用的返回值。仅当提供检查点程序时，此值才可用。
如果您希望 previous 与返回值不同，则可以使用 entrypoint.final 对象返回值，同时将不同的值保存到检查点。
参数
-
checkpointer(Optional [BaseCheckpointSaver ]None) –指定检查点程序以创建可以跨运行持久化其状态的工作流。
-
store(Optional [BaseStore ]None) –通用的键值存储。某些实现可能通过可选的
index配置支持语义搜索功能。 -
config_schema(Optional [type [Any ]]None) –指定将传递给工作流的配置对象的模式。
使用 entrypoint 和任务
import time
from langgraph.func import entrypoint, task
from langgraph.types import interrupt, Command
from langgraph.checkpoint.memory import MemorySaver
@task
def compose_essay(topic: str) -> str:
time.sleep(1.0) # Simulate slow operation
return f"An essay about {topic}"
@entrypoint(checkpointer=MemorySaver())
def review_workflow(topic: str) -> dict:
"""Manages the workflow for generating and reviewing an essay.
The workflow includes:
1. Generating an essay about the given topic.
2. Interrupting the workflow for human review of the generated essay.
Upon resuming the workflow, compose_essay task will not be re-executed
as its result is cached by the checkpointer.
Args:
topic (str): The subject of the essay.
Returns:
dict: A dictionary containing the generated essay and the human review.
"""
essay_future = compose_essay(topic)
essay = essay_future.result()
human_review = interrupt({
"question": "Please provide a review",
"essay": essay
})
return {
"essay": essay,
"review": human_review,
}
# Example configuration for the workflow
config = {
"configurable": {
"thread_id": "some_thread"
}
}
# Topic for the essay
topic = "cats"
# Stream the workflow to generate the essay and await human review
for result in review_workflow.stream(topic, config):
print(result)
# Example human review provided after the interrupt
human_review = "This essay is great."
# Resume the workflow with the provided human review
for result in review_workflow.stream(Command(resume=human_review), config):
print(result)
访问先前的返回值
启用检查点程序后，函数可以访问同一线程 ID 上先前调用的先前返回值。
from langgraph.checkpoint.memory import MemorySaver
from langgraph.func import entrypoint
@entrypoint(checkpointer=MemorySaver())
def my_workflow(input_data: str, previous: Optional[str] = None) -> str:
return "world"
config = {
"configurable": {
"thread_id": "some_thread"
}
}
my_workflow.invoke("hello")
使用 entrypoint.final 保存值
entrypoint.final 对象允许您返回值，同时将不同的值保存到检查点。只要使用相同的线程 ID，此值将在下次调用 entrypoint 时通过 previous 参数访问。
from langgraph.checkpoint.memory import MemorySaver
from langgraph.func import entrypoint
@entrypoint(checkpointer=MemorySaver())
def my_workflow(number: int, *, previous: Any = None) -> entrypoint.final[int, int]:
previous = previous or 0
# This will return the previous value to the caller, saving
# 2 * number to the checkpoint, which will be used in the next invocation
# for the `previous` parameter.
return entrypoint.final(value=previous, save=2 * number)
config = {
"configurable": {
"thread_id": "some_thread"
}
}
my_workflow.invoke(3, config) # 0 (previous was None)
my_workflow.invoke(1, config) # 6 (previous was 3 * 2 from the previous invocation)
final dataclass ¶
基类:
可以从 entrypoint 返回的原语。
此原语允许将值保存到检查点程序，这与 entrypoint 的返回值不同。
解耦返回值和保存值
from langgraph.checkpoint.memory import MemorySaver
from langgraph.func import entrypoint
@entrypoint(checkpointer=MemorySaver())
def my_workflow(number: int, *, previous: Any = None) -> entrypoint.final[int, int]:
previous = previous or 0
# This will return the previous value to the caller, saving
# 2 * number to the checkpoint, which will be used in the next invocation
# for the `previous` parameter.
return entrypoint.final(value=previous, save=2 * number)
config = {
"configurable": {
"thread_id": "1"
}
}
my_workflow.invoke(3, config) # 0 (previous was None)
my_workflow.invoke(1, config) # 6 (previous was 3 * 2 from the previous invocation)
__init__(checkpointer: Optional[BaseCheckpointSaver] = None, store: Optional[BaseStore] = None, config_schema: Optional[type[Any]] = None) -> None ¶
初始化 entrypoint 装饰器。
__call__(func: Callable[..., Any]) -> Pregel ¶
将函数转换为 Pregel 图。
参数
-
func(Callable [...,Any ]要转换的函数。支持同步和异步函数。
返回值
-
Pregel Pregel 图。
task(__func_or_none__: Optional[Union[Callable[P, Awaitable[T]], Callable[P, T]]] = None, *, name: Optional[str] = None, retry: Optional[RetryPolicy] = None) -> Union[Callable[[Union[Callable[P, Awaitable[T]], Callable[P, T]]], Callable[P, SyncAsyncFuture[T]]], Callable[P, SyncAsyncFuture[T]]] ¶
使用 task 装饰器定义 LangGraph 任务。
异步函数需要 Python 3.11 或更高版本
task 装饰器同时支持同步和异步函数。要使用异步函数，请确保您使用的是 Python 3.11 或更高版本。
任务只能从 entrypoint 或 StateGraph 中调用。可以像调用常规函数一样调用任务，但有以下区别
- 启用检查点程序后，函数输入和输出必须是可序列化的。
- 只能从 entrypoint 或 StateGraph 中调用被装饰的函数。
- 调用该函数会产生一个 future。这使得并行化任务变得容易。
参数
-
retry(Optional [RetryPolicy ]None) –用于任务失败时的可选重试策略。
返回值
-
Union [Callable [[Union [Callable [P ,Awaitable [T ]],Callable [P ,T ]]],Callable [P ,SyncAsyncFuture [T ]]],Callable [P ,SyncAsyncFuture [T ]]]用作装饰器时的可调用函数。
同步任务
from langgraph.func import entrypoint, task
@task
def add_one(a: int) -> int:
return a + 1
@entrypoint()
def add_one(numbers: list[int]) -> list[int]:
futures = [add_one(n) for n in numbers]
results = [f.result() for f in futures]
return results
# Call the entrypoint
add_one.invoke([1, 2, 3]) # Returns [2, 3, 4]
异步任务
import asyncio
from langgraph.func import entrypoint, task
@task
async def add_one(a: int) -> int:
return a + 1
@entrypoint()
async def add_one(numbers: list[int]) -> list[int]:
futures = [add_one(n) for n in numbers]
return asyncio.gather(*futures)
# Call the entrypoint
await add_one.ainvoke([1, 2, 3]) # Returns [2, 3, 4]