SourceSync.ai

SourceSync.ai é uma plataforma de Retrieval Augmented Generation como serviço (RAGaaS) que ajuda você a criar aplicações de IA com seus próprios dados. Este guia explica como usar o Firecrawl com o SourceSync.ai para recursos de raspagem da web.

Configuração

Primeiro, obtenha sua chave de API do Firecrawl no dashboard do Firecrawl.
Configure seu namespace do SourceSync.ai para usar o Firecrawl como provedor de web scraping:

curl -X PATCH https://api.sourcesync.ai/v1/namespaces/YOUR_NAMESPACE_ID \
  -H "Authorization: Bearer YOUR_SOURCE_SYNC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "webScraperConfig": {
      "provider": "FIRECRAWL",
      "apiKey": "YOUR_FIRECRAWL_API_KEY"
    }
  }'

const response = await fetch(
  'https://api.sourcesync.ai/v1/namespaces/YOUR_NAMESPACE_ID',
  {
    method: 'PATCH',
    headers: {
      Authorization: `Bearer ${SOURCE_SYNC_API_KEY}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      webScraperConfig: {
        provider: 'FIRECRAWL',
        apiKey: 'YOUR_FIRECRAWL_API_KEY',
      },
    }),
  }
)

import requests

response = requests.patch(
    'https://api.sourcesync.ai/v1/namespaces/YOUR_NAMESPACE_ID',
    headers={
        'Authorization': f'Bearer {SOURCE_SYNC_API_KEY}',
        'Content-Type': 'application/json',
    },
    json={
        'webScraperConfig': {
            'provider': 'FIRECRAWL',
        'apiKey': 'YOUR_FIRECRAWL_API_KEY',
        },
    },
)

Uso

Depois de configurar, você pode usar os endpoints de web scraping do SourceSync.ai com os recursos do Firecrawl. Estes são os principais métodos de ingestão:

Ingestão de lista de URLs

Raspe URLs específicas:

curl -X POST https://api.sourcesync.ai/v1/ingest/urls \
  -H "Authorization: Bearer YOUR_SOURCE_SYNC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "namespaceId": "YOUR_NAMESPACE_ID",
    "ingestConfig": {
      "source": "URLS_LIST",
      "config": {
        "urls": [
          "https://example.com/page1",
          "https://example.com/page2"
        ],
        "scrapeOptions": {
          "includeSelectors": ["article", "main"],
          "excludeSelectors": [".navigation", ".footer"]
        }
      }
    }
  }'

const response = await fetch('https://api.sourcesync.ai/v1/ingest/urls', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${SOURCE_SYNC_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    namespaceId: 'YOUR_NAMESPACE_ID',
    ingestConfig: {
      source: 'URLS_LIST',
      config: {
        urls: ['https://example.com/page1', 'https://example.com/page2'],
        scrapeOptions: {
          includeSelectors: ['article', 'main'],
          excludeSelectors: ['.navigation', '.footer'],
        },
      },
    },
  }),
})

response = requests.post(
    'https://api.sourcesync.ai/v1/ingest/urls',
    headers={
        'Authorization': f'Bearer {SOURCE_SYNC_API_KEY}',
        'Content-Type': 'application/json',
    },
    json={
        'namespaceId': 'YOUR_NAMESPACE_ID',
        'ingestConfig': {
            'source': 'URLS_LIST',
            'config': {
                'urls': ['https://example.com/page1', 'https://example.com/page2'],
                'scrapeOptions': {
                    'includeSelectors': ['article', 'main'],
                    'excludeSelectors': ['.navigation', '.footer'],
                },
            },
        },
    },
)

Rastreamento de site

Rastreie um site inteiro com regras personalizadas:

curl -X POST https://api.sourcesync.ai/v1/ingest/website \
  -H "Authorization: Bearer YOUR_SOURCE_SYNC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "namespaceId": "YOUR_NAMESPACE_ID",
    "ingestConfig": {
      "source": "WEBSITE",
      "config": {
        "url": "https://example.com",
        "maxDepth": 3,
        "maxLinks": 100,
        "includePaths": ["/docs", "/blog"],
        "excludePaths": ["/admin"],
        "scrapeOptions": {
          "includeSelectors": ["article", "main"],
          "excludeSelectors": [".navigation", ".footer"]
        }
      }
    }
  }'

const response = await fetch('https://api.sourcesync.ai/v1/ingest/website', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${SOURCE_SYNC_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    namespaceId: 'YOUR_NAMESPACE_ID',
    ingestConfig: {
      source: 'WEBSITE',
      config: {
        url: 'https://example.com',
        maxDepth: 3,
        maxLinks: 100,
        includePaths: ['/docs', '/blog'],
        excludePaths: ['/admin'],
        scrapeOptions: {
          includeSelectors: ['article', 'main'],
          excludeSelectors: ['.navigation', '.footer'],
        },
      },
    },
  }),
})

response = requests.post(
    'https://api.sourcesync.ai/v1/ingest/website',
    headers={
        'Authorization': f'Bearer {SOURCE_SYNC_API_KEY}',
        'Content-Type': 'application/json',
    },
    json={
        'namespaceId': 'YOUR_NAMESPACE_ID',
        'ingestConfig': {
            'source': 'WEBSITE',
            'config': {
                'url': 'https://example.com',
                'maxDepth': 3,
                'maxLinks': 100,
                'includePaths': ['/docs', '/blog'],
                'excludePaths': ['/admin'],
                'scrapeOptions': {
                    'includeSelectors': ['article', 'main'],
                    'excludeSelectors': ['.navigation', '.footer'],
                },
            },
        },
    },
)

Processamento de sitemap

Processe todas as URLs de um sitemap:

curl -X POST https://api.sourcesync.ai/v1/ingest/sitemap \
  -H "Authorization: Bearer YOUR_SOURCE_SYNC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "namespaceId": "YOUR_NAMESPACE_ID",
    "ingestConfig": {
      "source": "SITEMAP",
      "config": {
        "url": "https://example.com/sitemap.xml",
        "scrapeOptions": {
          "includeSelectors": ["article", "main"],
          "excludeSelectors": [".navigation", ".footer"]
        }
      }
    }
  }'

const response = await fetch('https://api.sourcesync.ai/v1/ingest/sitemap', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${SOURCE_SYNC_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    namespaceId: 'YOUR_NAMESPACE_ID',
    ingestConfig: {
      source: 'SITEMAP',
      config: {
        url: 'https://example.com/sitemap.xml',
        scrapeOptions: {
          includeSelectors: ['article', 'main'],
          excludeSelectors: ['.navigation', '.footer'],
        },
      },
    },
  }),
})

response = requests.post(
    'https://api.sourcesync.ai/v1/ingest/sitemap',
    headers={
        'Authorization': f'Bearer {SOURCE_SYNC_API_KEY}',
        'Content-Type': 'application/json',
    },
    json={
        'namespaceId': 'YOUR_NAMESPACE_ID',
        'ingestConfig': {
            'source': 'SITEMAP',
            'config': {
                'url': 'https://example.com/sitemap.xml',
                'scrapeOptions': {
                    'includeSelectors': ['article', 'main'],
                    'excludeSelectors': ['.navigation', '.footer'],
                },
            },
        },
    },
)

Recursos

Ao usar o Firecrawl com o SourceSync.ai, você tem acesso a:

Suporte à renderização de JavaScript
Limitação automática de taxa
Extração de conteúdo com seletores CSS
Rastreamento recursivo com controle de profundidade
Processamento de sitemaps

Recursos

Para suporte adicional:

E-mail: support@sourcesync.ai
Discord: Participe da nossa comunidade

Primeiros passos

Endpoints principais

Mais

Guias de início rápido

Guias para desenvolvedores

Webhooks

Casos de uso

Outros

Como contribuir

Configuração

Uso

Ingestão de lista de URLs

Rastreamento de site

Processamento de sitemap

Recursos

Recursos

​Configuração

​Uso

​Ingestão de lista de URLs

​Rastreamento de site

​Processamento de sitemap

​Recursos

​Recursos

Configuração

Uso

Ingestão de lista de URLs

Rastreamento de site

Processamento de sitemap

Recursos

Recursos