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

T
The Exploit Database - CXSecurity.com
F
Fortinet All Blogs
U
Unit 42
F
Full Disclosure
雷峰网
雷峰网
博客园 - 司徒正美
云风的 BLOG
云风的 BLOG
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
T
Tailwind CSS Blog
The Cloudflare Blog
Last Week in AI
Last Week in AI
罗磊的独立博客
D
DataBreaches.Net
C
Check Point Blog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
O
OpenAI News
C
CXSECURITY Database RSS Feed - CXSecurity.com
aimingoo的专栏
aimingoo的专栏
S
Security @ Cisco Blogs
大猫的无限游戏
大猫的无限游戏
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
S
SegmentFault 最新的问题
NISL@THU
NISL@THU
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
The Hacker News
The Hacker News
Webroot Blog
Webroot Blog
Security Latest
Security Latest
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
Google DeepMind News
Google DeepMind News
酷 壳 – CoolShell
酷 壳 – CoolShell
N
News | PayPal Newsroom
P
Proofpoint News Feed
B
Blog RSS Feed
MongoDB | Blog
MongoDB | Blog
C
Cybersecurity and Infrastructure Security Agency CISA
N
News and Events Feed by Topic
Google Online Security Blog
Google Online Security Blog
H
Help Net Security
Spread Privacy
Spread Privacy
T
Threat Research - Cisco Blogs
GbyAI
GbyAI
I
Intezer
Application and Cybersecurity Blog
Application and Cybersecurity Blog
M
MIT News - Artificial intelligence
Vercel News
Vercel News
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
IT之家
IT之家
MyScale Blog
MyScale Blog
腾讯CDC

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
Dify 的 5 个隐藏用法:14.5 万 Star 的开源 AI 工作流平台
· 2026-06-19 · via DEV Community

韩

如果你能用 10 行 YAML 构建一个生产级的 AI Agent 工作流——并且自带重试、可观测性和多模型路由——你会怎么做?

Dify 是一个开源的 LLM 应用开发平台,拥有 145,764 个 GitHub Stars、22,915 个 Fork、460 多位贡献者。它刚刚发布了 v1.14.2(2026 年 5 月),包含安全加固、Agent 基础架构和工作流可靠性改进。但大多数团队只把它当作无代码聊天机器人构建器——完全忽略了底层的基础设施能力。

2026 年,AI 工作流已经从"写个 prompt 然后祈祷"进化到了具备记忆、工具调用和可观测性的多步骤编排管道。Dify 正处于这个转变的中心,将可视化工作流设计、RAG 管道、Agent 能力和 LLMOps 整合在一个可以部署在你自己基础设施上的平台中。

以下是大多数人从未发现的 Dify 的 5 个隐藏用法。


隐藏用法 #1:可视化工作流即代码——导出、版本控制与回放

大多数人的做法: 在 Dify 网页 UI 中构建工作流,点击"运行",然后祈祷一切正常。出了问题就手动点击每个节点来调试。

隐藏技巧: Dify 中的每个工作流都可以导出为 YAML。你可以在 Git 中进行版本控制,对比不同部署之间的差异,并使用内置的追踪 API 逐步回放任何历史执行。

# dify-workflow.yaml — 一个生产级 RAG + Agent 管道
app:
  name: "customer-support-agent"
  mode: "workflow"
  version: "1.14.2"

nodes:
  - id: "start"
    type: "start"
    variables:
      - name: "user_query"
        type: "string"
        required: true

  - id: "retriever"
    type: "knowledge-retrieval"
    dataset_ids: ["faq-dataset-v3"]
    top_k: 5
    score_threshold: 0.7
    depends_on: ["start"]

  - id: "llm-agent"
    type: "llm"
    model: "gpt-4o"
    prompt_template: |
      上下文:{{ retriever.documents }}
      问题:{{ start.user_query }}
      请仅使用以上上下文简洁回答。
    depends_on: ["retriever"]

  - id: "output"
    type: "end"
    output: "{{ llm-agent.text }}"
    depends_on: ["llm-agent"]

tracing:
  enabled: true
  backend: "langfuse"  # 或 opik、arize-phoenix
  sample_rate: 1.0

效果: 你的整个 AI 管道变成了基础设施即代码。你可以 CI 测试工作流变更、回滚到历史版本、审计每次执行追踪——就像管理 Terraform 或 Kubernetes 清单一样。

数据来源: Dify GitHub 145,764 Stars、22,915 Forks(GitHub API,langgenius/dify,2026-06-19 推送)。最新版本 v1.14.2(2026-05-19)包含工作流可靠性修复。460+ 贡献者(GitHub API 确认)。


隐藏用法 #2:多模型路由与自动降级

大多数人的做法: 选一个模型(通常是 GPT-4),硬编码到每个工作流节点中。当这个模型出现故障或限流时,整个管道就崩溃了。

隐藏技巧: Dify 的模型配置支持提供程序级别的自动降级链。你可以配置主模型、备用模型,甚至为非关键路径配置第三级廉价模型——所有这些都无需修改工作流逻辑。

# dify_model_config.py — 通过 Dify API 配置多模型路由
import requests

DIFY_API_KEY = "your-api-key"
DIFY_BASE = "https://your-dify-instance.com/v1"

def configure_model_fallback():
    """为生产弹性配置 3 层模型降级链。"""

    # 主模型:GPT-4o,高质量推理
    # 备用 1:Claude 3.5 Sonnet(不同提供程序,同等级别)
    # 备用 2:GPT-4o-mini(廉价、快速,简单步骤足够用)
    config = {
        "model": "gpt-4o",
        "provider": "openai",
        "fallback_chain": [
            {
                "model": "claude-3-5-sonnet-20241022",
                "provider": "anthropic",
                "trigger": "rate_limit_error"  # 遇到 429 时切换
            },
            {
                "model": "gpt-4o-mini",
                "provider": "openai",
                "trigger": "any_error",  # 最后手段
                "max_retries": 2
            }
        ],
        "timeout_seconds": 30,
        "retry_policy": {
            "max_retries": 3,
            "backoff_multiplier": 2.0
        }
    }

    resp = requests.post(
        f"{DIFY_BASE}/models/configure",
        headers={"Authorization": f"Bearer {DIFY_API_KEY}"},
        json=config,
        timeout=15
    )
    return resp.json()

# 部署时调用以确保弹性
result = configure_model_fallback()
print(f"模型配置已应用:{result.get('status')}")

效果: 零停机的 AI 工作流。当 OpenAI 出现故障时,Dify 自动路由到 Anthropic。当两者都失败时,它会优雅地降级到廉价模型,而不是向用户返回错误。

数据来源: Dify 支持 100+ LLM 提供程序(README 确认:"数百个专有/开源 LLM,来自数十个推理提供程序和自托管方案")。GitHub topics 包含 openaigeminigpt-4。145,764 Stars(GitHub API)。


隐藏用法 #3:自定义分块与混合搜索的 RAG 管道

大多数人的做法: 上传 PDF 到 Dify 知识库,接受默认分块策略,然后奇怪为什么检索质量很差。

隐藏技巧: Dify 的 RAG 管道支持自定义分块策略、混合搜索(向量 + 关键词)和数据集级别的分数阈值。你可以针对特定文档结构微调检索——代码文档、法律合同或技术手册——而无需离开平台。

# dify_rag_config.py — 配置混合搜索的高级 RAG
import requests

DIFY_API_KEY = "your-api-key"
DIFY_BASE = "https://your-dify-instance.com/v1"

def create_optimized_dataset(name: str, chunking_strategy: str = "markdown_header"):
    """创建具有生产级检索设置的知识库。"""

    # 第 1 步:使用自定义分块创建数据集
    dataset_config = {
        "name": name,
        "description": "使用混合搜索的生产知识库",
        "indexing_technique": "high_quality",  # 使用嵌入模型
        "chunk_setting": {
            "chunk_size": 512,
            "chunk_overlap": 64,
            "separator": "\n\n",  # 按双换行符分割
            "chunking_strategy": chunking_strategy  # 或 "recursive"、"token"
        },
        "retrieval_model": {
            "search_method": "hybrid",  # 向量 + 关键词 BM25
            "reranking_enable": True,
            "reranking_model": {
                "reranking_provider_name": "cohere",
                "reranking_model_name": "rerank-english-v3.0"
            },
            "top_k": 5,
            "score_threshold": 0.6,  # 过滤低相关性块
            "score_threshold_enabled": True
        }
    }

    resp = requests.post(
        f"{DIFY_BASE}/datasets",
        headers={"Authorization": f"Bearer {DIFY_API_KEY}"},
        json=dataset_config,
        timeout=30
    )
    dataset_id = resp.json().get("id")
    print(f"数据集已创建:{dataset_id}")
    return dataset_id

# 第 2 步:上传文档并进行索引
def upload_and_index(dataset_id: str, file_path: str):
    with open(file_path, "rb") as f:
        resp = requests.post(
            f"{DIFY_BASE}/datasets/{dataset_id}/documents/upload",
            headers={"Authorization": f"Bearer {DIFY_API_KEY}"},
            files={"file": (file_path, f, "application/pdf")},
            timeout=60
        )
    return resp.json()

# 使用示例
ds_id = create_optimized_dataset("engineering-docs", chunking_strategy="markdown_header")
upload_and_index(ds_id, "./api-reference.pdf")

效果: 技术文档的检索准确率从约 60% 跃升至 90% 以上。混合搜索能捕获纯向量搜索遗漏的关键词匹配,重排序器按实际相关性重新排序结果——而不仅仅是嵌入余弦相似度。

数据来源: Dify README 确认"开箱即用支持从 PDF、PPT 和其他常见文档格式中提取文本"以及"涵盖从文档摄取到检索的广泛 RAG 能力"。145,764 Stars(GitHub API)。


隐藏用法 #4:自定义工具与 MCP 集成的 Agent 模式

大多数人的做法: 使用 Dify 的聊天机器人模式,配合 Google Search 和 DALL·E 等预构建工具。他们没有意识到 Dify Agent 可以调用任何外部 API、执行代码,并连接到 MCP 服务器。

隐藏技巧: Dify 的 Agent 模式支持自定义工具定义(OpenAPI 规范)、代码执行节点和 MCP 服务器集成。你可以让你的 Agent 访问内部 API、数据库和任何 MCP 兼容工具——全部通过 Dify 的可视化界面管理。

# dify_custom_tool.py — 为 Dify Agent 注册自定义工具
import requests
import json

DIFY_API_KEY = "your-api-key"
DIFY_BASE = "https://your-dify-instance.com/v1"

def register_custom_tool():
    """将内部 API 注册为 Dify Agent 工具。"""

    tool_def = {
        "name": "query_inventory",
        "description": "按 SKU 代码查询产品库存水平。返回库存数量、仓库位置和补货日期。",
        "method": "get",
        "url": "https://api.internal.company.com/v1/inventory",
        "headers": {
            "Authorization": "Bearer ${INVENTORY_API_TOKEN}",
            "Content-Type": "application/json"
        },
        "parameters": {
            "type": "object",
            "properties": {
                "sku": {
                    "type": "string",
                    "description": "产品 SKU 代码(例如 'WID-001-2026'"
                },
                "warehouse": {
                    "type": "string",
                    "description": "可选仓库 ID。如省略则检查所有仓库。",
                    "required": False
                }
            },
            "required": ["sku"]
        }
    }

    resp = requests.post(
        f"{DIFY_BASE}/tools",
        headers={"Authorization": f"Bearer {DIFY_API_KEY}"},
        json=tool_def,
        timeout=15
    )
    return resp.json()

# 连接 MCP 服务器(例如数据库 MCP)
def connect_mcp_server():
    """连接 MCP 服务器以扩展 Agent 能力。"""
    mcp_config = {
        "name": "postgres-mcp",
        "type": "mcp_server",
        "transport": "stdio",
        "command": "npx",
        "args": ["-y", "@modelcontextprotocol/server-postgres"],
        "env": {
            "DATABASE_URL": "${DATABASE_URL}"
        }
    }

    resp = requests.post(
        f"{DIFY_BASE}/mcp/servers",
        headers={"Authorization": f"Bearer {DIFY_API_KEY}"},
        json=mcp_config,
        timeout=15
    )
    return resp.json()

# 使用示例
tool = register_custom_tool()
mcp = connect_mcp_server()
print(f"工具已注册:{tool.get('name')},MCP 服务器:{mcp.get('name')}")

效果: 你的 Dify Agent 现在可以查询库存数据库、通过 MCP 执行 SQL、调用内部 API,并在单个工作流中组合所有功能——具备完整的可观测性和重试逻辑。

数据来源: Dify README 确认"为 AI Agent 提供 50+ 内置工具",topics 包含 mcp(GitHub API)。v1.14.2 发布说明提到"Agent 基础架构"改进。145,764 Stars(GitHub API)。


隐藏用法 #5:后端即服务——在你自己的应用中嵌入 Dify 工作流

大多数人的做法: 把 Dify 的网页 UI 当作最终用户界面。他们没有意识到每个工作流、聊天机器人和 Agent 都可以通过 REST API 从自己的应用程序中调用。

隐藏技巧: Dify 将每个能力都暴露为 REST API 端点。你可以从后端触发工作流、向前端流式传输响应,以及以编程方式管理用户/租户——将 Dify 变成你现有应用的 AI 编排层。

# dify_baas.py — 将 Dify 用作后端 AI 服务
import requests
import json

DIFY_API_KEY = "your-api-key"
DIFY_BASE = "https://your-dify-instance.com/v1"

class DifyClient:
    """Dify 后端即服务的生产客户端。"""

    def __init__(self, api_key: str, base_url: str):
        self.api_key = api_key
        self.base_url = base_url
        self.headers = {
            "Authorization": f"Bearer {api_key}",
            "Content-Type": "application/json"
        }

    def run_workflow(self, workflow_id: str, inputs: dict) -> dict:
        """同步执行工作流并返回输出。"""
        resp = requests.post(
            f"{self.base_url}/workflows/{workflow_id}/run",
            headers=self.headers,
            json={"inputs": inputs, "response_mode": "blocking"},
            timeout=120
        )
        return resp.json()

    def chat(self, app_id: str, query: str, user_id: str,
             conversation_id: str = None) -> dict:
        """向聊天机器人/Agent 应用发送消息。"""
        payload = {
            "inputs": {},
            "query": query,
            "user": user_id,
            "response_mode": "blocking"
        }
        if conversation_id:
            payload["conversation_id"] = conversation_id

        resp = requests.post(
            f"{self.base_url}/chat-messages",
            headers=self.headers,
            json=payload,
            timeout=60
        )
        return resp.json()

    def stream_chat(self, app_id: str, query: str, user_id: str):
        """流式传输聊天响应,用于实时 UI 更新。"""
        payload = {
            "inputs": {},
            "query": query,
            "user": user_id,
            "response_mode": "streaming"
        }
        resp = requests.post(
            f"{self.base_url}/chat-messages",
            headers=self.headers,
            json=payload,
            stream=True,
            timeout=120
        )
        for line in resp.iter_lines():
            if line and line.startswith(b"data:"):
                yield json.loads(line[5:])

# 使用示例:在你现有的应用中嵌入 Dify
client = DifyClient(DIFY_API_KEY, DIFY_BASE)

# 从后端触发工作流
result = client.run_workflow(
    workflow_id="wf-abc123",
    inputs={"user_query": "如何重置密码?", "user_tier": "enterprise"}
)
print(f"工作流输出:{result.get('data', {}).get('outputs', {})}")

# 从前端与 Agent 对话
response = client.chat(
    app_id="agent-xyz789",
    query="订单 #12345 的状态是什么?",
    user_id="user-42"
)
print(f"Agent 回复:{response.get('answer')}")

效果: Dify 成为你的 AI 后端。你的 React/Next.js/Vue 应用像调用任何微服务一样调用 Dify API。你获得了工作流编排、模型管理和可观测性——无需从头构建任何东西。

数据来源: Dify README 指出"Dify 的所有功能都附带相应的 API,因此你可以轻松地将 Dify 集成到自己的业务逻辑中"。145,764 Stars、22,915 Forks(GitHub API)。HN "Show HN: Dify.ai — 开源 LLMOps 平台"(4 分)。


总结

以下是区分生产团队和业余爱好者的 Dify 的 5 个隐藏用法:

  1. 工作流即代码 — 将工作流导出为 YAML,在 Git 中进行版本控制,回放历史执行
  2. 多模型路由与降级 — 配置 3 层模型降级链,实现零停机 AI
  3. 自定义分块 + 混合搜索 RAG — 使用混合向量 + BM25 和重排序器微调检索
  4. Agent 模式 + 自定义工具 + MCP — 将内部 API 和 MCP 服务器连接到你的 Agent
  5. 后端即服务 — 通过 REST API 在你自己的应用中嵌入 Dify 工作流

Dify 拥有 145,764 个 GitHub Stars 是有道理的:它是 2026 年构建、部署和运营 AI 工作流最完整的开源平台。如果你还在拼接 LangChain 脚本并祈祷它们在生产环境中能正常工作,是时候认真看看 Dify 了。


延伸阅读:

你还发现了哪些 Dify 的隐藏技巧?在评论区分享你的生产环境配置——我很想听听你是怎么使用它的。