惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Forbes - Security
Forbes - Security
A
Arctic Wolf
M
MIT News - Artificial intelligence
T
Threat Research - Cisco Blogs
T
The Exploit Database - CXSecurity.com
C
CERT Recently Published Vulnerability Notes
NISL@THU
NISL@THU
L
Lohrmann on Cybersecurity
Martin Fowler
Martin Fowler
A
About on SuperTechFans
P
Palo Alto Networks Blog
Project Zero
Project Zero
The GitHub Blog
The GitHub Blog
WordPress大学
WordPress大学
Blog — PlanetScale
Blog — PlanetScale
博客园_首页
大猫的无限游戏
大猫的无限游戏
Cisco Talos Blog
Cisco Talos Blog
P
Proofpoint News Feed
D
DataBreaches.Net
Cyberwarzone
Cyberwarzone
T
Tor Project blog
IT之家
IT之家
P
Proofpoint News Feed
Help Net Security
Help Net Security
S
Securelist
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
C
CXSECURITY Database RSS Feed - CXSecurity.com
Microsoft Azure Blog
Microsoft Azure Blog
V2EX - 技术
V2EX - 技术
K
Kaspersky official blog
Hugging Face - Blog
Hugging Face - Blog
MongoDB | Blog
MongoDB | Blog
B
Blog
N
News and Events Feed by Topic
The Cloudflare Blog
S
Schneier on Security
P
Privacy & Cybersecurity Law Blog
T
The Blog of Author Tim Ferriss
Recorded Future
Recorded Future
Last Week in AI
Last Week in AI
The Last Watchdog
The Last Watchdog
Hacker News - Newest:
Hacker News - Newest: "LLM"
L
LangChain Blog
I
InfoQ
F
Full Disclosure
The Register - Security
The Register - Security
阮一峰的网络日志
阮一峰的网络日志
H
Hacker News: Front Page
V
V2EX

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant Common SOC 2 Failures (Real World) Stop Vibe-Checking Your AI App: A Practical Guide to Evals How to Use SonarQube and SonarScanner Locally to Level Up Your Code Quality Your Next To-Do App Is Dead — I Replaced Mine with an OpenClaw AI Sign a Nostr event in 60 lines of Python using coincurve — no nostr-sdk, no nbxplorer, no rust toolchain ITGC Audit Explained Like You’re in Big 4 Patch Tuesday abril 2026: Microsoft parcha 163 vulnerabilidades y un zero-day en SharePoint Stop scraping everything: a better way to track competitor price changes Listing on MCPize + the Official MCP Registry while routing payments OUTSIDE the marketplace — how I kept 100% of my x402 revenue Building an AI-Powered Risk Intelligence System Using Serverless Architecture Why We Ripped Function Overloading Out of Our AI Toolchain Testing AI-Generated Code: How to Actually Know If It Works SaaS Churn Is Killing Your Business. Here Is What to Do About It (Without a Support Team) The Speed of AI Is No Longer Linear - And Self-Improving Models Are Why How to Implement RBAC for MCP Tools: A Practical Guide for Engineering Teams From Standard Quote to Persuasive Proposal: AI Automation for Arborists I built a CLI that scaffolds complete multi-tenant SaaS apps Axios CVE-2025–62718: The Silent SSRF Bug That Could Be Hiding in Your Node.js App Right Now The dashboard that ended our friendship Data Pipelines Explained Simply (and How to Build Them with Python) The Hidden Cost of AI Systems Nobody Talks About. undefined vs undeclared, and how typeof behaves Switching from file-based jobs to NATS/Kafka in Rust without changing code io_uring Adventures: Rust Servers That Love Syscalls Why Agentic AI is Killing the Traditional Database The POUR principles of web accessibility for developers and designers Quantum Neural Network 3D — A Deep Dive into Interactive WebGL Visualization How To Install Caveman In Codex On macOS And Windows Automation Pipeline Reliability: Why Your Workflow Breaks When Nobody Is Watching I Built an 'Open World' AI Coding Agent — It Works From ANY Folder From Freelancing to Product: A Tech Service Company's SaaS Transformation China's AI Giants: Adding Tencent Hunyuan & ByteDance Doubao to AI University (74 Providers) On the Vibe Coders and Their Lies clerk: Auto-Summarize Your Claude Code Sessions AI Weekly — 2026/04/10–04/17 | The Model Lockdown Is Here, but the Toolchain Is the Real Battleground AI 週報 — 2026/04/10–2026/04/17 模型封鎖潮來了,但工具鏈才是真戰場 Maybe this is how Open-Source apps are born... 🚀 Fine-Tune LLMs with LoRA and QLoRA: 2026 Guide tRPC v11 + Next.js App Router: End-to-End Type Safety Without the Boilerplate ShadCN UI in 2026: Why I Stopped Installing Component Libraries and Started Owning My Components SaaS Billing in React Server Components: Stripe + Supabase Without a Single `useEffect` Join our DEV Weekend Challenge — $1,000 in Prizes Across TEN winners! Submissions Due April 20 at 6:59 AM UTC. Implementing FSRS Spaced Repetition in Flutter + Supabase — Adding Memory Science to an AI Learning App "I Texted My Localhost From the Train — Claude Code Fixed the Bug Before I Got Home" I Built a Sales Prep AI and It Went Deeper Than Expected Design to Code #2: One JSON, Eleven Outputs Solving the 100M-Row Problem: A Summary Table Pattern for High-Volume Push Notification Logs Flutter Web With Wasm: What Actually Changes For Developers I Built 50 Royalty-Free Soundtracks for My Side Project in a Weekend Using AI Music Generation The Vibe Coding Security Checklist: 7 Things to Check Before You Ship Stop Letting Googlebot Guess Fix Your React App's SEO Right Desconstruindo o Streaming do LinkedIn: Como Criar um Engine de Extração de Vídeo de Alta Performance com HLS e FFmpeg (EDA Part-1) EDA (Exploratory Data Analysis) Explained With Real Life — Why Looking at Your Data Is the Most Important Step in Machine Learning Brand Relationship Management at Scale: Our 4-Touch Outreach System for 200+ Brands Why String.fromEnvironment() Might Return an Empty String in Dart JGuardrails 1.0.0 — Hardening Java LLM Apps Against Jailbreaks, Toxicity, and Prompt Injection Plan and Schedule a Full Week of Threads Content From One Claude Conversation Coding Cat Oran Ep3, Five Tables Changed Everything Updated: BFF Pattern I'm done watching freelancers get buried by 200 proposals. So I'm building the alternative. This is my first post BFS Algorithm in Java Step by Step Tutorial with Examples Tracking LLM Pricing Monthly: An Open Dataset for 22 AI Models How We Measure Content ROI on a Comparison Site: Revenue Attribution Without Perfect Data Introducing Nova AI Ops: The AI-Native Operating System for SRE Teams I built a free desktop video downloader for Windows — Grabbit How Talkie OCR Helps Vision-Impaired & Dyslexic Users Read the World Around Them VRCFaceTracking安装和iPhone面捕配置教程,有bug Even CrowdStrike Can't See Your Agents The Automation Gold Rush: What n8n Workflows and Claude Are Opening Up for Developers Right Now
LangGraph 워크플로우 템플릿 (v34)
matias yoon · 2026-05-25 · via DEV Community

LangGraph 워크플로우 템플릿 (v34)

Python 개발자를 위한 LangChain/LangGraph 워크플로우 템플릿

1. LangGraph 아키텍처 개요

LangGraph는 상태 기반의 워크플로우 시스템으로, 다음과 같은 핵심 구성 요소로 작동합니다:

  • 노드 (Nodes): 각 단계의 작업을 정의하는 함수
  • 엣지 (Edges): 노드 간의 전이 조건
  • 상태 (State): 모든 노드에서 공유되는 데이터 구조
  • 체크포인팅 (Checkpointing): 상태를 저장하고 복구하는 기능
from typing import TypedDict, Annotated
from langgraph.graph import StateGraph, END
import operator

class AgentState(TypedDict):
    messages: Annotated[list, operator.add]
    user_input: str

# 기본 워크플로우 구성
workflow = StateGraph(AgentState)

2. 템플릿 1: 간단한 RAG 에이전트 (검색 → 생성 → 검증)

실제 문제: 문서 검색 후 생성된 답변의 정확성 검증 필요

from langchain_core.prompts import PromptTemplate
from langchain_openai import ChatOpenAI
from langchain_core.output_parsers import StrOutputParser

# RAG 워크플로우
def retrieve(state):
    # 문서 검색 로직
    vector_store = VectorStore()
    query = state["user_input"]
    retrieved_docs = vector_store.search(query, k=3)
    return {"retrieved_docs": retrieved_docs}

def generate(state):
    # 생성 로직
    prompt = PromptTemplate.from_template(
        "다음 문서를 기반으로 질문에 답하세요: {context}\n질문: {query}"
    )
    chain = prompt | ChatOpenAI(model="gpt-4") | StrOutputParser()

    context = "\n".join([doc.page_content for doc in state["retrieved_docs"]])
    answer = chain.invoke({"context": context, "query": state["user_input"]})

    return {"generated_answer": answer}

def validate(state):
    # 검증 로직
    prompt = PromptTemplate.from_template(
        "다음 답변이 질문에 답하고 있는지 검증하세요:\n질문: {query}\n답변: {answer}\n정답 여부: (예/아니오)"
    )
    chain = prompt | ChatOpenAI(model="gpt-4") | StrOutputParser()

    verdict = chain.invoke({
        "query": state["user_input"], 
        "answer": state["generated_answer"]
    })

    return {"validation": verdict, "valid": "" in verdict}

# 워크플로우 정의
workflow = StateGraph(AgentState)
workflow.add_node("retrieve", retrieve)
workflow.add_node("generate", generate)
workflow.add_node("validate", validate)

# 엣지 정의
workflow.set_entry_point("retrieve")
workflow.add_edge("retrieve", "generate")
workflow.add_edge("generate", "validate")

# 검증 결과에 따라 분기
def route_validation(state):
    if state["valid"]:
        return END
    else:
        return "retrieve"  # 재검색

workflow.add_conditional_edges(
    "validate",
    route_validation,
    {
        "retrieve": "retrieve",
        END: END
    }
)

3. 템플릿 2: 다중 도구 에이전트 (계획 → 실행 → 관찰 → 결정)

실제 문제: 여러 도구를 사용해야 하는 복잡한 작업 처리

from langchain.tools import Tool
from langchain_openai import OpenAI

# 도구 정의
tools = [
    Tool(
        name="search",
        func=lambda query: f"검색 결과: {query}",
        description="웹 검색을 위한 도구"
    ),
    Tool(
        name="calculator",
        func=lambda expression: f"계산 결과: {eval(expression)}",
        description="수학 계산을 위한 도구"
    )
]

class ToolAgentState(TypedDict):
    messages: Annotated[list, operator.add]
    plan: str
    execution_result: str
    observation: str

def plan(state):
    # 작업 계획 생성
    prompt = PromptTemplate.from_template(
        "다음 작업을 위한 계획을 세우세요:\n{task}\n도구 사용 계획:"
    )
    chain = prompt | ChatOpenAI(model="gpt-4") | StrOutputParser()
    plan = chain.invoke({"task": state["user_input"]})
    return {"plan": plan}

def execute(state):
    # 도구 실행
    tools_dict = {tool.name: tool for tool in tools}
    # 간단한 실행 로직 (실제 구현 시 도구 선택 로직 포함)
    tool_result = tools_dict["search"].run(state["user_input"])
    return {"execution_result": tool_result}

def observe(state):
    # 실행 결과 관찰
    return {"observation": f"실행 결과: {state['execution_result']}"}

def decide(state):
    # 결정 로직
    prompt = PromptTemplate.from_template(
        "다음 작업을 고려하세요:\n{task}\n관찰 결과: {observation}\n결정:"
    )
    chain = prompt | ChatOpenAI(model="gpt-4") | StrOutputParser()
    decision = chain.invoke({
        "task": state["user_input"],
        "observation": state["observation"]
    })
    return {"decision": decision}

# 워크플로우 구성
workflow = StateGraph(ToolAgentState)
workflow.add_node("plan", plan)
workflow.add_node("execute", execute)
workflow.add_node("observe", observe)
workflow.add_node("decide", decide)

workflow.set_entry_point("plan")
workflow.add_edge("plan", "execute")
workflow.add_edge("execute", "observe")
workflow.add_edge("observe", "decide")
workflow.add_edge("decide", END)

4. 템플릿 3: 인간-중개 워크플로우 (일시정지 → 검토 → 계속)

실제 문제: 인간의 판단이 필요한 작업에서 자동화와 인간 통제의 균형

from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import StateGraph, END
from datetime import datetime

class HumanInLoopState(TypedDict):
    messages: Annotated[list, operator.add]
    task: str
    human_review: str
    status: str  # "pending", "approved", "rejected"
    timestamp: str

def task_creation(state):
    # 작업 생성
    task = f"사용자 요청: {state['user_input']}"
    return {"task": task, "status": "pending", "timestamp": datetime.now().isoformat()}

def review_request(state):
    # 검토 요청
    return {"messages": state["messages"] + [{"role": "assistant", "content": 
        f"작업을 검토해 주세요:\n{state['task']}\n[승인/거부]"}]}

def human_review(state):
    # 인간 검토
    review = state["human_review"]  # 사용자 입력
    status = "approved" if "승인" in review else "rejected"
    return {"status": status, "messages": state["messages"] + [{"role": "user", "content": review}]}

def handle_rejection(state):
    # 거부 시 재작업
    return {"messages": state["messages"] + [{"role": "assistant", "content": 
        "작업이 거부되었습니다. 새로운 요청을 주세요"}]}

# 워크플로우 정의
workflow = StateGraph(HumanInLoopState)
workflow.add_node("create_task", task_creation)
workflow.add_node("request_review", review_request)
workflow.add_node("human_review", human_review)
workflow.add_node("handle_rejection", handle_rejection)

workflow.set_entry_point("create_task")
workflow.add_edge("create_task", "request_review")
workflow.add_edge("request_review", "human_review")

def route_review(state):
    if state["status"] == "approved":
        return "END"
    else:
        return "handle_rejection"

workflow.add_conditional_edges(
    "human_review",
    route_review,
    {
        "handle_rejection": "handle_rejection",
        "END": END
    }
)

5. 템플릿 5: 병렬 실행 에이전트 (팬아웃 → 처리 → 집계)

실제 문제: 여러 데이터 소스를 동시에 처리하고 결과를 통합하는 작업


python
import asyncio
from concurrent.futures import ThreadPoolExecutor

class ParallelProcessingState(TypedDict):
    messages: Annotated[list, operator.add]
    data_sources: list
    processed_results: list
    aggregated_result: str

def fan_out(state):
    # 데이터 소스 분산
    sources = state["data_sources"]
    return {"processed_results": []}

async def process_async(data_source):
    # 비동기 처리 로직
    await asyncio.sleep(1)  # 실제 API 호출
    return f"처리된 {data_source}"

def process_parallel(state):
    # 병렬 처리
    with ThreadPoolExecutor(max

---

📥 **Get the full guide on Gumroad**: https://gumroad.com/l/auto ($5)