LangGraph提供两种不同的API用于构建智能体工作流:Graph API和Functional API。这两种 API 共享相同的底层运行时环境,且可在同一应用中搭配使用,但它们针对不同的使用场景和开发偏好设计。 本文旨在帮助开发者根据自身具体需求,了解何时应使用哪种API。
一、快速决策指南
当你需要以下功能时,使用图 API(Graph API):
- 用于调试和文档记录的复杂工作流可视化
- 支持多节点共享数据的显式状态管理
- 包含多个决策点的条件分支
- 后续需合并的并行执行路径
- 可通过可视化呈现辅助理解的团队协作场景
当你需要以下功能时,使用函数式 API(Functional API):
- 对现有过程式代码的改动最小化
- 标准控制流(if/else 条件判断、循环、函数调用)
- 无需显式状态管理的函数作用域状态
- 更少模板代码(boilerplate)的快速原型开发
- 仅含简单分支逻辑的线性工作流
二、详细对比
2.1 何时使用图 API(Graph API)
图API采用声明式方法(declarative approach),通过定义节点(nodes)、边(edges)和共享状态(shared state)来创建可视化的图结构(visual graph structure)。
1. 复杂决策树与分支逻辑
当你的工作流包含多个依赖于不同条件的决策点(decision points)时,图 API 能让这些分支清晰可见,且易于可视化呈现。
python
# Graph API: Clear visualization of decision paths
from langgraph.graph import StateGraph
from typing import TypedDict
class AgentState(TypedDict):
messages: list
current_tool: str
retry_count: int
def should_continue(state):
if state["retry_count"] > 3:
return "end"
elif state["current_tool"] == "search":
return "process_search"
else:
return "call_llm"
workflow = StateGraph(AgentState)
workflow.add_node("call_llm", call_llm_node)
workflow.add_node("process_search", search_node)
workflow.add_conditional_edges("call_llm", should_continue)
2. 跨多个组件的状态管理
当你需要在工作流的不同部分之间共享并协调状态时,图 API(Graph API)的显式状态管理(explicit state management)机制将发挥重要作用。
python
# Multiple nodes can access and modify shared state
class WorkflowState(TypedDict):
user_input: str
search_results: list
generated_response: str
validation_status: str
def search_node(state):
# Access shared state
results = search(state["user_input"])
return {"search_results": results}
def validation_node(state):
# Access results from previous node
is_valid = validate(state["generated_response"])
return {"validation_status": "valid" if is_valid else "invalid"}
3. 带同步机制的并行处理
当你需要并行运行多个操作,随后再合并它们的结果时,图 API(Graph API)能自然地处理这一需求。
python
# Parallel processing of multiple data sources
workflow.add_node("fetch_news", fetch_news)
workflow.add_node("fetch_weather", fetch_weather)
workflow.add_node("fetch_stocks", fetch_stocks)
workflow.add_node("combine_data", combine_all_data)
# All fetch operations run in parallel
workflow.add_edge(START, "fetch_news")
workflow.add_edge(START, "fetch_weather")
workflow.add_edge(START, "fetch_stocks")
# Combine waits for all parallel operations to complete
workflow.add_edge("fetch_news", "combine_data")
workflow.add_edge("fetch_weather", "combine_data")
workflow.add_edge("fetch_stocks", "combine_data")
4. 团队开发与文档编制
图 API(Graph API)的可视化特性,使得团队更易于理解、记录和维护复杂的工作流。
python
# Clear separation of concerns - each team member can work on different nodes
workflow.add_node("data_ingestion", data_team_function)
workflow.add_node("ml_processing", ml_team_function)
workflow.add_node("business_logic", product_team_function)
workflow.add_node("output_formatting", frontend_team_function)
2.2 何时使用函数式 API(Functional API)
函数式 API 采用命令式方法(imperative approach),可将LangGraph功能集成到标准的过程式代码中。
1. 对现有过程式代码的改动最小化
当你已拥有使用标准控制流(standard control flow)的代码,且希望通过最少的重构(minimal refactoring)为其添加 LangGraph 功能时,适合使用函数式 API。
python
# Functional API: Minimal changes to existing code
from langgraph.func import entrypoint, task
@task
def process_user_input(user_input: str) -> dict:
# Existing function with minimal changes
return {"processed": user_input.lower().strip()}
@entrypoint(checkpointer=checkpointer)
def workflow(user_input: str) -> str:
# Standard Python control flow
processed = process_user_input(user_input).result()
if "urgent" in processed["processed"]:
response = handle_urgent_request(processed).result()
else:
response = handle_normal_request(processed).result()
return response
2. 具有简单逻辑的线性工作流
当你的工作流以顺序执行为主,且仅包含简单的条件逻辑时。
python
@entrypoint(checkpointer=checkpointer)
def essay_workflow(topic: str) -> dict:
# Linear flow with simple branching
outline = create_outline(topic).result()
if len(outline["points"]) < 3:
outline = expand_outline(outline).result()
draft = write_draft(outline).result()
# Human review checkpoint
feedback = interrupt({"draft": draft, "action": "Please review"})
if feedback == "approve":
final_essay = draft
else:
final_essay = revise_essay(draft, feedback).result()
return {"essay": final_essay}
3. 快速原型开发
当你希望快速测试想法,且不想承担定义状态模式(state schemas)和图结构(graph structures)的额外开销时。
python
@entrypoint(checkpointer=checkpointer)
def quick_prototype(data: dict) -> dict:
# Fast iteration - no state schema needed
step1_result = process_step1(data).result()
step2_result = process_step2(step1_result).result()
return {"final_result": step2_result}
4. 函数作用域内的状态管理
当你的状态天然适合限定在单个函数的作用域内,且无需进行大范围共享时。
python
@task
def analyze_document(document: str) -> dict:
# Local state management within function
sections = extract_sections(document)
summaries = [summarize(section) for section in sections]
key_points = extract_key_points(summaries)
return {
"sections": len(sections),
"summaries": summaries,
"key_points": key_points
}
@entrypoint(checkpointer=checkpointer)
def document_processor(document: str) -> dict:
analysis = analyze_document(document).result()
# State is passed between functions as needed
return generate_report(analysis).result()
三、组合使用两种API
你可以在同一个应用中同时使用这两种 API。当系统的不同部分有不同需求时,这种方式会非常实用。
python
from langgraph.graph import StateGraph
from langgraph.func import entrypoint
# Complex multi-agent coordination using Graph API
coordination_graph = StateGraph(CoordinationState)
coordination_graph.add_node("orchestrator", orchestrator_node)
coordination_graph.add_node("agent_a", agent_a_node)
coordination_graph.add_node("agent_b", agent_b_node)
# Simple data processing using Functional API
@entrypoint()
def data_processor(raw_data: dict) -> dict:
cleaned = clean_data(raw_data).result()
transformed = transform_data(cleaned).result()
return transformed
# Use the functional API result in the graph
def orchestrator_node(state):
processed_data = data_processor.invoke(state["raw_data"])
return {"processed_data": processed_data}
四、API间的迁移
4.1 从函数式API迁移至图API
当你的函数式工作流变得复杂时,可按以下方式迁移至图 API:
python
# Before: Functional API
@entrypoint(checkpointer=checkpointer)
def complex_workflow(input_data: dict) -> dict:
step1 = process_step1(input_data).result()
if step1["needs_analysis"]:
analysis = analyze_data(step1).result()
if analysis["confidence"] > 0.8:
result = high_confidence_path(analysis).result()
else:
result = low_confidence_path(analysis).result()
else:
result = simple_path(step1).result()
return result
# After: Graph API
class WorkflowState(TypedDict):
input_data: dict
step1_result: dict
analysis: dict
final_result: dict
def should_analyze(state):
return "analyze" if state["step1_result"]["needs_analysis"] else "simple_path"
def confidence_check(state):
return "high_confidence" if state["analysis"]["confidence"] > 0.8 else "low_confidence"
workflow = StateGraph(WorkflowState)
workflow.add_node("step1", process_step1_node)
workflow.add_conditional_edges("step1", should_analyze)
workflow.add_node("analyze", analyze_data_node)
workflow.add_conditional_edges("analyze", confidence_check)
# ... add remaining nodes and edges
4.2 从图API迁移至函数式API
当对于简单的线性流程而言,你的图结构变得过于复杂时
python
# Before: Over-engineered Graph API
class SimpleState(TypedDict):
input: str
step1: str
step2: str
result: str
# After: Simplified Functional API
@entrypoint(checkpointer=checkpointer)
def simple_workflow(input_data: str) -> str:
step1 = process_step1(input_data).result()
step2 = process_step2(step1).result()
return finalize_result(step2).result()
五、总结
当你需要对工作流结构进行显式控制、处理复杂分支、实现并行处理,或希望借助团队协作优势时,请选择图API(Graph API)。 当你希望以最少的改动为现有代码添加LangGraph功能、处理简单的线性工作流,或需要快速原型开发能力时,请选择函数式API(Functional API)。 两种 API 均提供相同的LangGraph核心功能(包括持久化、流式处理、人机协同、内存管理),但采用不同的范式进行封装,以适配不同的开发风格和使用场景。