Fire Enrich - AI 驱动的数据增强工具

将简单的电子邮件列表转换为包含公司概况、融资数据、技术栈等内容的丰富数据集。由 Firecrawl 和多智能体（Multi-agent）AI 系统提供支持。

使用的技术

• Firecrawl: 用于网页抓取和内容聚合
• OpenAI: 用于智能数据提取与综合
• Next.js 15: 现代 React 框架（App Router）

设置

所需 API Keys

服务	用途	获取密钥
Firecrawl	网页抓取与内容聚合	firecrawl.dev/app/api-keys
OpenAI	智能数据提取	platform.openai.com/api-keys

快速开始

1. 克隆此仓库
2. 创建一个 .env.local 文件并填入你的 API keys：

   FIRECRAWL_API_KEY=your_firecrawl_key
   OPENAI_API_KEY=your_openai_key
   

3. 安装依赖：npm install 或 yarn install
4. 运行开发服务器：npm run dev 或 yarn dev
5. 打开 http://localhost:3000

增强示例

转换前：

{
  "email": "erez@wiz.io"
}

转换后：

{
  "email": "erez@wiz.io",
  "companyName": "Wiz",
  "industry": "Cybersecurity",
  "employeeCount": "1001-5000",
  "yearFounded": 2020,
  "headquarters": "New York, NY",
  "fundingStage": "Series D",
  "totalRaised": "$900M",
  "website": "https://www.wiz.io",
  "sources": [
    "https://www.wiz.io/about",
    "https://techcrunch.com/2023/02/27/wiz-confirms-300m-at-a-10b-valuation-to-build-out-its-cloud-security-platform/"
  ]
}

工作原理

架构概览：以 "ericciarla@firecrawl.dev" 为例

让我们看看 Fire Enrich 是如何处理一个真实示例的——即为邮箱 ericciarla@firecrawl.dev 增强数据。

graph TD
    Start["Input: ericciarla@firecrawl.dev - Industry, CEO, Funding Stage, Tech Stack"]:::primary
    
    Start -->|1. Extract Domain| Domain["Domain: firecrawl.dev - Corporate email detected"]:::primary
    
    Domain -->|2. Start Orchestration| Orchestrator["Agent Orchestrator - Executes agents in optimized sequence - Each phase builds on previous data"]:::synthesis

    %% Phase 1: Discovery
    Orchestrator -->|Phase 1| Discovery["Discovery Agent - Finds basic company info first"]:::agent
    
    Discovery -->|Parallel searches| DiscSearch["Parallel Searches: Firecrawl company, firecrawl.dev, What is Firecrawl"]:::search
    
    DiscSearch -->|Firecrawl API| DiscFC["3 concurrent API calls - Returns company website and basic information"]:::firecrawl
    
    DiscFC -->|Extracts| DiscData["Company: Firecrawl - Website: firecrawl.dev - Type: B2B SaaS"]:::source

    %% Phase 2: Company Profile
    DiscData -->|Phase 2| Profile["Company Profile Agent - Uses company name from Phase 1 to find industry details"]:::agent
    
    Profile -->|Parallel searches| ProfSearch["Parallel Searches: Firecrawl industry classification, Firecrawl web scraping API, Developer tools Firecrawl"]:::search
    
    ProfSearch -->|Firecrawl API| ProfFC["3 concurrent API calls - Searches industry-specific sources"]:::firecrawl
    
    ProfFC -->|Extracts| ProfData["Industry: Developer Tools - Sub-category: Web Scraping APIs - Market: B2B SaaS"]:::source

    %% Phase 3: Financial
    ProfData -->|Phase 3| Funding["Financial Intel Agent - Searches for funding using company and industry context"]:::agent
    
    Funding -->|Parallel searches| FundSearch["Parallel Searches: Firecrawl funding rounds, Mendable AI acquisition Firecrawl, Firecrawl investors crunchbase"]:::search
    
    FundSearch -->|Firecrawl API| FundFC["3 concurrent API calls - Checks TechCrunch, Crunchbase, venture news sites"]:::firecrawl
    
    FundFC -->|Extracts| FundData["Funding: Seed Stage - Part of Mendable AI - YC-backed company"]:::source

    %% Phase 4: Tech Stack
    FundData -->|Phase 4| Tech["Tech Stack Agent - Analyzes GitHub and tech docs - HTML source analysis"]:::agent
    
    Tech -->|Parallel searches| TechSearch["Parallel Searches: github.com/mendableai/firecrawl, Firecrawl API documentation, Direct HTML analysis"]:::search
    
    TechSearch -->|Firecrawl API| TechFC["3 concurrent API calls - HTML meta tag analysis - GitHub repo scan"]:::firecrawl
    
    TechFC -->|Extracts| TechData["Tech Stack: Node.js, Python, Redis, Playwright, Kubernetes"]:::source

    %% Phase 5: General
    TechData -->|Phase 5| General["General Purpose Agent - Handles custom field CEO - Uses all previous context"]:::agent
    
    General -->|Targeted search| GenSearch["Focused Search"]