使用 n8n、Scrapeless 和 Claude 构建 AI 驱动的网络数据管道

• •可能需要目标 API 的认证凭证

{
  "id": "tTMZ2w3OvZFF1qDX",
  "meta": {
    "instanceId": "00078a12eb9132a267d925042ab574964c429326494199b73fefad612cec4111"
  },
  "name": "使用 n8n、Scrapeless 和 Claude 构建 AI 驱动的网络数据管道",
  "tags": [
    {
      "id": "Cu2uFDtw5wsdcHBH",
      "name": "Building Blocks",
      "createdAt": "2025-05-19T02:37:48.404Z",
      "updatedAt": "2025-05-19T02:37:48.404Z"
    },
    {
      "id": "PBConYPLh7mnOKsG",
      "name": "AI",
      "createdAt": "2025-05-19T02:37:48.399Z",
      "updatedAt": "2025-05-19T02:37:48.399Z"
    },
    {
      "id": "vhgqzFa23bYmJ6xM",
      "name": "Engineering",
      "createdAt": "2025-05-19T02:37:48.394Z",
      "updatedAt": "2025-05-19T02:37:48.394Z"
    }
  ],
  "nodes": [
    {
      "id": "05f02bd8-01d5-49fa-a6cf-989499d1b299",
      "name": "当点击\"测试工作流\"时",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -600,
        160
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "0102acf2-84f4-4bdb-939a-1f6653abd61f",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -420,
        500
      ],
      "parameters": {
        "width": 480,
        "height": 353,
        "content": "## 注意"
      },
      "typeVersion": 1
    },
    {
      "id": "279c7fef-a0fa-40c6-84e0-3f47c64f61d0",
      "name": "设置字段 - URL 和 Webhook URL",
      "type": "n8n-nodes-base.set",
      "notes": "Configure URL, webhook Discord, and Scrapeless parameters",
      "position": [
        140,
        200
      ],
      "parameters": {
        "options": {}
      },
      "notesInFlow": true,
      "typeVersion": 3.4
    },
    {
      "id": "9f4ae239-db55-418a-9984-0b7291432484",
      "name": "Scrapeless 网络请求",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        600,
        260
      ],
      "parameters": {
        "url": "https://api.scrapeless.com/api/v1/unlocker/request",
        "method": "POST",
        "options": {},
        "jsonBody": "{\n  \"actor\": \"unlocker.webunlocker\",\n  \"proxy\": {\n    \"country\": \"ANY\"\n  },\n  \"input\": {\n    \"url\": \"https://news.ycombinator.com/\",\n    \"method\": \"GET\",\n    \"redirect\": true,\n    \"js_render\": true,\n    \"js_instructions\": [\n      {\n        \"wait\": 100\n      }\n    ],\n    \"block\": {\n      \"resources\": [\n        \"image\",\n        \"font\",\n        \"script\"\n      ]\n    }\n  }\n}",
        "sendBody": true,
        "sendHeaders": true,
        "specifyBody": "json",
        "headerParameters": {
          "parameters": [
            {
              "name": "x-api-token",
              "value": "scrapeless_api_key"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "d3592464-2890-4a78-ad00-1f2744c33cb3",
      "name": "便签1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1000,
        220
      ],
      "parameters": {
        "width": 299.4593773279841,
        "height": 275.17733400027635,
        "content": "## AI 数据格式化器"
      },
      "typeVersion": 1
    },
    {
      "id": "d1660d56-623b-4a13-b527-95f8304a7193",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1820,
        640
      ],
      "parameters": {
        "color": 4,
        "width": 691.0849556663684,
        "height": 430.23565450317744,
        "content": "## 向量数据库持久化"
      },
      "typeVersion": 1
    },
    {
      "id": "e9cd437d-478a-40f4-9a27-df9f6ef84b3f",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1840,
        160
      ],
      "parameters": {
        "color": 3,
        "width": 636.0351499864845,
        "height": 305.42311858115056,
        "content": "## Webhook Discord 处理器"
      },
      "typeVersion": 1
    },
    {
      "id": "d78741da-460d-4c27-9e9a-64be81c76513",
      "name": "便签4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1040,
        680
      ],
      "parameters": {
        "color": 5,
        "width": 720,
        "height": 392.5761165830749,
        "content": "## 使用 Claude AI Agent 进行数据提取/格式化"
      },
      "typeVersion": 1
    },
    {
      "id": "4bde24dc-931f-40ef-9453-7978fd04fc1a",
      "name": "格式化 Claude 输出",
      "type": "n8n-nodes-base.code",
      "position": [
        1620,
        860
      ],
      "parameters": {
        "jsCode": "// Format Claude Output - Parse and structure Claude response\n// Second node: Formats Claude API response for Qdrant and workflow\n\nconst claudeResponse = items[0].json;\n\nif (claudeResponse.error) {\n  console.error('❌ Received error from Claude extractor:', claudeResponse.message);\n  return [{\n    json: {\n      id: Math.random().toString(36).substr(2, 9),\n      page_type: \"error\",\n      metadata: {\n        title: \"Extraction Error\",\n        description: `Error during extraction: ${claudeResponse.message}`,\n        url: \"Unknown\",\n        extracted_at: new Date().toISOString(),\n        error: true\n      },\n      content: {\n        main_text: `Processing failed: ${claudeResponse.message}`,\n        summary: \"Data extraction failed\"\n      },\n      vector_ready: false,\n      processing_error: claudeResponse\n    }\n  }];\n}\n\nlet extractedData = {};\n\ntry {\n  if (claudeResponse.content && Array.isArray(claudeResponse.content)) {\n    const responseText = claudeResponse.content[0].text;\n    console.log('🔍 Processing Claude response text...');\n    \n    const jsonMatch = responseText.match(/```json\\n([\\s\\S]*?)\\n```/) || responseText.match(/\\{[\\s\\S]*\\}/);\n    \n    if (jsonMatch) {\n      try {\n        extractedData = JSON.parse(jsonMatch[1] || jsonMatch[0]);\n        console.log('✅ Successfully parsed Claude JSON response');\n      } catch (parseError) {\n        console.error('❌ JSON parsing error:', parseError);\n        \n        extractedData = {\n          page_type: \"parse_error\",\n          metadata: {\n            title: \"JSON Parse Error\",\n            description: \"Failed to parse Claude response as JSON\",\n            url: \"Unknown\",\n            extracted_at: new Date().toISOString(),\n            parse_error: parseError.message\n          },\n          content: {\n            main_text: responseText,\n            summary: \"Raw Claude response (unparseable)\",\n            raw_response: responseText\n          }\n        };\n      }\n    } else {\n      console.warn('⚠️ No JSON structure found in Claude response');\n      \n      extractedData = {\n        page_type: \"unstructured\",\n        metadata: {\n          title: \"Unstructured Response\",\n          description: \"Claude response without JSON structure\",\n          url: \"Unknown\",\n          extracted_at: new Date().toISOString()\n        },\n        content: {\n          main_text: responseText,\n          summary: \"Unstructured content from Claude\",\n          raw_response: responseText\n        }\n      };\n    }\n  } else {\n    throw new Error('Unexpected Claude response format');\n  }\n\n  if (!extractedData.id) {\n    extractedData.id = Math.random().toString(36).substr(2, 9);\n  }\n\n  extractedData.technical_metadata = {\n    extraction_source: \"scrapeless\",\n    ai_processor: \"claude-3-7-sonnet-20250219\",\n    processing_timestamp: new Date().toISOString(),\n    workflow_version: \"n8n-v2\",\n    data_quality: extractedData.page_type !== \"error\" && extractedData.page_type !== \"parse_error\" ? \"high\" : \"low\"\n  };\n\n  extractedData.vector_ready = extractedData.content && extractedData.content.main_text ? true : false;\n\n  if (extractedData.content && extractedData.content.main_text) {\n    if (extractedData.content.main_text.length < 50) {\n      extractedData.technical_metadata.content_warning = \"Content too short for meaningful vectorization\";\n    }\n    \n    extractedData.searchable_content = [\n      extractedData.metadata?.title || '',\n      extractedData.metadata?.description || '',\n      extractedData.content.main_text || '',\n      extractedData.content.summary || '',\n      (extractedData.content.key_points || []).join(' '),\n      (extractedData.entities?.topics || []).join(' ')\n    ].filter(text => text.length > 0).join(' ');\n  }\n\n  console.log('✅ Format processing complete:', {\n    page_type: extractedData.page_type,\n    has_content: !!extractedData.content?.main_text,\n    vector_ready: extractedData.vector_ready,\n    id: extractedData.id\n  });\n\n  return [{ json: extractedData }];\n\n} catch (error) {\n  console.error('❌ Error during Claude response formatting:', error);\n  \n  return [{\n    json: {\n      id: Math.random().toString(36).substr(2, 9),\n      page_type: \"format_error\",\n      metadata: {\n        title: \"Formatting Error\",\n        description: `Error during response formatting: ${error.message}`,\n        url: \"Unknown\",\n        extracted_at: new Date().toISOString(),\n        error: true\n      },\n      content: {\n        main_text: `Formatting failed: ${error.message}`,\n        summary: \"Failed to format Claude response\"\n      },\n      technical_metadata: {\n        extraction_source: \"claude_formatter\",\n        error_details: error.message,\n        raw_claude_response: claudeResponse,\n        processing_timestamp: new Date().toISOString()\n      },\n      vector_ready: false\n    }\n  }];\n}"
      },
      "typeVersion": 2
    },
    {
      "id": "9b524862-ed1b-4601-bfa6-928fbebde0f9",
      "name": "检查集合是否存在",
      "type": "n8n-nodes-base.httpRequest",
      "onError": "continueRegularOutput",
      "position": [
        -420,
        20
      ],
      "parameters": {
        "url": "http://localhost:6333/collections/hacker-news",
        "options": {},
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        }
      },
      "typeVersion": 4.2,
      "alwaysOutputData": true
    },
    {
      "id": "0c6d1977-4812-4cd9-aa0a-b5c7adeb7e16",
      "name": "集合存在检查",
      "type": "n8n-nodes-base.if",
      "position": [
        -240,
        20
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 1,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "64e5c63b-c488-44cc-9d26-2027e059c4b2",
              "operator": {
                "name": "filter.operator.equals",
                "type": "string",
                "operation": "equals"
              },
              "leftValue": "={{ $node['Check Collection Exists'].json.result ? $node['Check Collection Exists'].json.status : 'not_found' }}",
              "rightValue": "ok"
            }
          ]
        }
      },
      "typeVersion": 2
    },
    {
      "id": "22104741-3314-42fb-bc94-3a742af94245",
      "name": "创建 Qdrant 集合",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        0,
        0
      ],
      "parameters": {
        "url": "http://localhost:6333/collections/hacker-news",
        "method": "PUT",
        "options": {},
        "sendBody": true,
        "sendHeaders": true,
        "bodyParameters": {
          "parameters": [
            {}
          ]
        },
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "2b7c493b-cb8f-45e3-9167-159ec5f8aa8b",
      "name": "Scrapeless 配置信息",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        440,
        80
      ],
      "parameters": {
        "color": 6,
        "width": 441.35610553772244,
        "height": 368.2417530681812,
        "content": "## Scrapeless 配置"
      },
      "typeVersion": 1
    },
    {
      "id": "0431e4e1-d5fe-404b-8891-e8b4dc157d5f",
      "name": "Claude 数据提取器",
      "type": "n8n-nodes-base.code",
      "position": [
        1080,
        860
      ],
      "parameters": {
        "jsCode": "// Claude Data Extractor - Raw extraction from HTML\n// First node: Makes API call to Claude for content extraction\n\nconst inputData = items[0].json;\n\nlet htmlContent = '';\nif (inputData.data && inputData.data.html) {\n  htmlContent = inputData.data.html;\n} else if (inputData.data && inputData.data.content) {\n  htmlContent = inputData.data.content;\n} else if (inputData.content) {\n  htmlContent = inputData.content;\n} else {\n  htmlContent = JSON.stringify(inputData);\n}\n\nconst pageUrl = inputData.url || inputData.data?.url || 'Unknown URL';\n\nconst extractionPrompt = `You are an expert web content extractor. Analyze this HTML content and extract important information in a structured JSON format.\n\n**INSTRUCTIONS:**\n1. Identify the content type (article, e-commerce, blog, news, documentation, etc.)\n2. Extract relevant information based on the type\n3. Create structured and consistent JSON output\n4. Ignore technical HTML (menus, ads, footers, etc.)\n\n**REQUIRED OUTPUT FORMAT:**\n\\`\\`\\`json\n{\n  \"page_type\": \"article|product|blog|news|documentation|listing|other\",\n  \"metadata\": {\n    \"title\": \"Main page title\",\n    \"description\": \"Description or summary\",\n    \"url\": \"${pageUrl}\",\n    \"extracted_at\": \"${new Date().toISOString()}\",\n    \"language\": \"en|fr|es|...\",\n    \"author\": \"Author if available\",\n    \"date_published\": \"Date if available\",\n    \"tags\": [\"tag1\", \"tag2\"]\n  },\n  \"content\": {\n    \"main_text\": \"Main content extracted and cleaned\",\n    \"summary\": \"Summary in 2-3 sentences\",\n    \"key_points\": [\"Point 1\", \"Point 2\", \"Point 3\"],\n    \"sections\": [\n      {\n        \"title\": \"Section 1\",\n        \"content\": \"Section content\"\n      }\n    ]\n  },\n  \"structured_data\": {\n    // For e-commerce\n    \"price\": \"Price if product\",\n    \"currency\": \"EUR|USD|...\",\n    \"availability\": \"In stock/Out of stock\",\n    \"rating\": \"Rating if available\",\n    \n    // For articles/news\n    \"category\": \"Category\",\n    \"reading_time\": \"Estimated reading time\",\n    \n    // For all types\n    \"images\": [\"Image URL 1\", \"Image URL 2\"],\n    \"links\": [\n      {\"text\": \"Link text\", \"url\": \"Link URL\"}\n    ]\n  },\n  \"entities\": {\n    \"people\": [\"Names of people mentioned\"],\n    \"organizations\": [\"Organizations/companies\"],\n    \"locations\": [\"Places mentioned\"],\n    \"technologies\": [\"Technologies/tools mentioned\"],\n    \"topics\": [\"Main topics\"]\n  }\n}\n\\`\\`\\`\n\n**HTML TO ANALYZE:**\n${htmlContent.substring(0, 15000)} ${htmlContent.length > 15000 ? '...[TRUNCATED]' : ''}\n\nReturn ONLY the structured JSON, without additional explanations.`;\n\nconst claudePayload = {\n  model: \"claude-3-7-sonnet-20250219\",\n  max_tokens: 4096,\n  messages: [\n    {\n      role: \"user\",\n      content: extractionPrompt\n    }\n  ]\n};\n\ntry {\n  const options = {\n    method: 'POST',\n    url: 'https://api.anthropic.com/v1/messages',\n    headers: {\n      'x-api-key': 'YOUR-API-KEY',\n      'content-type': 'application/json'\n    },\n    body: claudePayload,\n    json: true\n  };\n\n  const claudeResponse = await this.helpers.request(options);\n  console.log('✅ Claude extraction call successful');\n  \n  return [{ json: claudeResponse }];\n\n} catch (error) {\n  console.error('❌ Error during Claude extraction:', error);\n  \n  return [{\n    json: {\n      error: true,\n      message: error.message,\n      original_data: inputData,\n      timestamp: new Date().toISOString()\n    }\n  }];\n}"
      },
      "typeVersion": 2
    },
    {
      "id": "b04dfca9-ebf0-46f7-b1e5-93ddf79e2451",
      "name": "Ollama 嵌入",
      "type": "n8n-nodes-base.code",
      "position": [
        1920,
        860
      ],
      "parameters": {
        "jsCode": "// Simple Ollama Embeddings\n// Gets text embeddings from Ollama using the all-minilm model (you can use other models)\n\nconst inputData = items[0].json;\n\nlet textToEmbed = '';\n\nif (inputData.content && typeof inputData.content === 'string') {\n  textToEmbed = inputData.content;\n} else if (inputData.content && inputData.content.main_text) {\n  textToEmbed = inputData.content.main_text;\n  \n  if (inputData.content.summary) {\n    textToEmbed += ' ' + inputData.content.summary;\n  }\n} else if (inputData.searchable_content) {\n  textToEmbed = inputData.searchable_content;\n} else if (inputData.metadata && inputData.metadata.title) {\n  textToEmbed = inputData.metadata.title;\n  if (inputData.metadata.description) {\n    textToEmbed += ' ' + inputData.metadata.description;\n  }\n} else {\n  textToEmbed = JSON.stringify(inputData).substring(0, 1000);\n}\n\ntextToEmbed = textToEmbed.substring(0, 2000);\n\ntry {\n  console.log('🔍 Getting embeddings for:', textToEmbed.substring(0, 100) + '...');\n  \n  const response = await this.helpers.request({\n    method: 'POST',\n    url: 'http://127.0.0.1:11434/api/embeddings',\n    headers: {\n      'Content-Type': 'application/json'\n    },\n    body: {\n      model: \"all-minilm\",\n      prompt: textToEmbed\n    },\n    json: true\n  });\n  \n  if (!response.embedding || !Array.isArray(response.embedding)) {\n    throw new Error('No valid embedding returned from Ollama');\n  }\n  \n  console.log(`✅ Got embedding with ${response.embedding.length} dimensions`);\n  \n  return [{\n    json: {\n      ...inputData,\n      vector: response.embedding,\n      vector_info: {\n        dimensions: response.embedding.length,\n        model: \"all-minilm\",\n        created_at: new Date().toISOString()\n      }\n    }\n  }];\n  \n} catch (error) {\n  console.error('❌ Error getting embeddings:', error);\n  \n  return [{\n    json: {\n      ...inputData,\n      error: true,\n      error_message: error.message,\n      error_type: 'embedding_failed',\n      error_time: new Date().toISOString()\n    }\n  }];\n}"
      },
      "typeVersion": 2
    },
    {
      "id": "17a38e65-1f04-4c2d-9fc7-fd05c2d7c14d",
      "name": "Qdrant 向量存储",
      "type": "n8n-nodes-base.code",
      "position": [
        2220,
        860
      ],
      "parameters": {
        "jsCode": "// Simple Qdrant Storage\n// Stores vectors in Qdrant\n\n// Get data with vector from Ollama\nconst inputData = items[0].json;\n\n// 1. Generate a valid Qdrant ID (must be integer)\nconst pointId = Math.floor(Math.random() * 1000000000);\n\n// 2. Extract basic metadata\nconst title = \n  (inputData.metadata && inputData.metadata.title) || \n  inputData.title || \n  'Untitled';\n\nconst url = \n  (inputData.metadata && inputData.metadata.url) || \n  inputData.url || \n  '';\n\n// 3. Check if we have a vector\nconst hasVector = inputData.vector && Array.isArray(inputData.vector) && inputData.vector.length > 0;\n\nif (!hasVector) {\n  console.error('❌ No valid vector found in input');\n  return [{\n    json: {\n      error: true,\n      message: 'No valid vector found',\n      id: pointId,\n      title: title\n    }\n  }];\n}\n\n// 4. Create Qdrant payload\nconst qdrantPayload = {\n  points: [\n    {\n      id: pointId,         \n      vector: inputData.vector,\n      payload: {\n        title: title,\n        url: url,\n        original_id: inputData.id || '',\n        \n        // Content\n        page_type: inputData.page_type || 'unknown',\n        content: typeof inputData.content === 'string' \n          ? inputData.content.substring(0, 1000) \n          : (inputData.content && inputData.content.main_text \n              ? inputData.content.main_text.substring(0, 1000) \n              : ''),\n        \n        author: (inputData.metadata && inputData.metadata.author) || '',\n        language: (inputData.metadata && inputData.metadata.language) || 'en',\n        tags: (inputData.metadata && inputData.metadata.tags) || [],\n        \n        vector_dimensions: inputData.vector.length,\n        stored_at: new Date().toISOString()\n      }\n    }\n  ]\n};\n\n// 5. Store in Qdrant\ntry {\n  console.log(`💾 Storing document \"${title}\" with ID ${pointId} in Qdrant`);\n  \n  const response = await this.helpers.request({\n    method: 'PUT',\n    url: 'http://127.0.0.1:6333/collections/hacker-news/points',\n    headers: {\n      'Content-Type': 'application/json'\n    },\n    body: qdrantPayload,\n    json: true\n  });\n  \n  console.log('✅ Successfully stored in Qdrant:', response);\n  \n  return [{\n    json: {\n      success: true,\n      id: pointId,\n      title: title,\n      vector_dimensions: inputData.vector.length,\n      qdrant_response: response,\n      timestamp: new Date().toISOString()\n    }\n  }];\n  \n} catch (error) {\n  console.error('❌ Error storing in Qdrant:', error);\n  \n  // Check if collection doesn't exist\n  if (error.message && (error.message.includes('404') || \n                         error.message.includes('collection not found'))) {\n    try {\n      // we already check if collection exist before but in case we verify it one more time\n      console.log('🔧 Creating collection \"hacker-news\"...');\n      \n      await this.helpers.request({\n        method: 'PUT',\n        url: 'http://127.0.0.1:6333/collections/hacker-news',\n        headers: {\n          'Content-Type': 'application/json'\n        },\n        body: {\n          vectors: {\n            size: inputData.vector.length,\n            distance: \"Cosine\"\n          }\n        },\n        json: true\n      });\n      \n      console.log('✅ Collection created, retrying storage...');\n      \n      const response = await this.helpers.request({\n        method: 'PUT',\n        url: 'http://127.0.0.1:6333/collections/hacker-news/points',\n        headers: {\n          'Content-Type': 'application/json'\n        },\n        body: qdrantPayload,\n        json: true\n      });\n      \n      return [{\n        json: {\n          success: true,\n          collection_created: true,\n          id: pointId,\n          title: title,\n          vector_dimensions: inputData.vector.length,\n          qdrant_response: response,\n          timestamp: new Date().toISOString()\n        }\n      }];\n      \n    } catch (retryError) {\n      console.error('❌ Error creating collection:', retryError);\n      \n      return [{\n        json: {\n          error: true,\n          message: 'Failed to create collection: ' + retryError.message,\n          id: pointId,\n          title: title\n        }\n      }];\n    }\n  }\n  \n  return [{\n    json: {\n      error: true,\n      message: error.message,\n      id: pointId,\n      title: title,\n      timestamp: new Date().toISOString()\n    }\n  }];\n}"
      },
      "typeVersion": 2
    },
    {
      "id": "c0939f66-cee8-44c2-9766-f33c1306dd45",
      "name": "Claude AI Agent",
      "type": "n8n-nodes-base.code",
      "position": [
        1360,
        920
      ],
      "parameters": {
        "jsCode": "// AI Agent - Enhanced Data Validation & Correction\n// Between Claude Data Extractor and Format Claude Output\n// Validates, enriches and corrects raw extraction\n\nconst claudeResponse = items[0].json;\n\nif (claudeResponse.error) {\n  console.log('⚠️ Received error from Claude Data Extractor, passing through...');\n  return [{ json: claudeResponse }];\n}\n\nlet extractedContent = '';\nif (claudeResponse.content && Array.isArray(claudeResponse.content)) {\n  extractedContent = claudeResponse.content[0].text;\n} else {\n  extractedContent = JSON.stringify(claudeResponse);\n}\n\nconst validationPrompt = `You are an AI data validator and enhancer. Analyze this raw extraction result and improve it.\n\n**ORIGINAL EXTRACTION RESULT:**\n${extractedContent}\n\n**YOUR TASKS:**\n1. **Validate the JSON Structure**: Ensure the extraction is valid JSON\n2. **Fix Parsing Errors**: Correct any malformed JSON or missing fields\n3. **Enhance Missing Data**: Fill in missing metadata when possible\n4. **Standardize Format**: Ensure consistent structure\n5. **Quality Check**: Verify content makes sense\n\n**VALIDATION & ENHANCEMENT RULES:**\n- If JSON is malformed, fix the syntax\n- If required fields are missing, add them with reasonable defaults\n- If content is too short, extract more from the raw data if available\n- If page_type is wrong, correct it based on content analysis\n- If dates are malformed, standardize them to ISO format\n- If URLs are partial, make them complete when possible\n\n**REQUIRED OUTPUT FORMAT:**\nReturn a VALID JSON object with this exact structure:\n\\`\\`\\`json\n{\n  \"page_type\": \"article|product|blog|news|documentation|listing|other\",\n  \"metadata\": {\n    \"title\": \"Actual page title (required)\",\n    \"description\": \"Actual description (required)\",\n    \"url\": \"Complete URL if available\",\n    \"extracted_at\": \"ISO timestamp\",\n    \"language\": \"en|fr|es|...\",\n    \"author\": \"Author name if found\",\n    \"date_published\": \"ISO date if found\",\n    \"tags\": [\"relevant\", \"tags\"]\n  },\n  \"content\": {\n    \"main_text\": \"Clean, readable main content (required)\",\n    \"summary\": \"2-3 sentence summary (required)\",\n    \"key_points\": [\"Important point 1\", \"Important point 2\"],\n    \"sections\": [\n      {\n        \"title\": \"Section title\",\n        \"content\": \"Section content\"\n      }\n    ]\n  },\n  \"structured_data\": {\n    \"price\": \"Product price if applicable\",\n    \"currency\": \"Currency code if applicable\", \n    \"availability\": \"Stock status if applicable\",\n    \"rating\": \"Rating if applicable\",\n    \"category\": \"Content category\",\n    \"reading_time\": \"Estimated reading time\",\n    \"images\": [\"Image URLs\"],\n    \"links\": [{\"text\": \"Link text\", \"url\": \"Link URL\"}]\n  },\n  \"entities\": {\n    \"people\": [\"Person names\"],\n    \"organizations\": [\"Company names\"],\n    \"locations\": [\"Place names\"],\n    \"technologies\": [\"Tech terms\"],\n    \"topics\": [\"Main topics\"]\n  },\n  \"validation_info\": {\n    \"original_valid\": true/false,\n    \"corrections_made\": [\"List of fixes applied\"],\n    \"confidence_score\": 0.0-1.0,\n    \"quality_issues\": [\"Any remaining issues\"]\n  }\n}\n\\`\\`\\`\n\n**IMPORTANT:**\n- Return ONLY the corrected JSON, no explanations\n- Ensure ALL required fields have meaningful values\n- Fix any syntax errors in the original\n- If original is completely invalid, create a reasonable structure from available data`;\n\nconst enhancementPayload = {\n  model: \"claude-3-7-sonnet-20250219\",\n  max_tokens: 4096,\n  messages: [\n    {\n      role: \"user\",\n      content: validationPrompt\n    }\n  ]\n};\n\ntry {\n  const options = {\n    method: 'POST',\n    url: 'https://api.anthropic.com/v1/messages',\n    headers: {\n      'x-api-key': 'YOUR-API-KEY',\n      'content-type': 'application/json'\n    },\n    body: enhancementPayload,\n    json: true\n  };\n\n  console.log('🔍 AI Agent validating and enhancing extraction...');\n  \n  const aiResponse = await this.helpers.request(options);\n  \n  if (aiResponse.content && Array.isArray(aiResponse.content)) {\n    const enhancedText = aiResponse.content[0].text;\n    \n    const jsonMatch = enhancedText.match(/```json\\n([\\s\\S]*?)\\n```/) || enhancedText.match(/\\{[\\s\\S]*\\}/);\n    \n    if (jsonMatch) {\n      try {\n        const enhancedData = JSON.parse(jsonMatch[1] || jsonMatch[0]);\n        \n        enhancedData.ai_processing = {\n          processed_by: \"claude-ai-agent\",\n          processing_timestamp: new Date().toISOString(),\n          original_extraction_valid: !claudeResponse.error,\n          enhancements_applied: true\n        };\n        \n        console.log('✅ AI Agent enhancement successful:', {\n          page_type: enhancedData.page_type,\n          title: enhancedData.metadata?.title?.substring(0, 50) + '...',\n          confidence: enhancedData.validation_info?.confidence_score || 'unknown',\n          corrections: enhancedData.validation_info?.corrections_made?.length || 0\n        });\n        \n        return [{\n          json: {\n            content: [\n              {\n                text: JSON.stringify(enhancedData, null, 2)\n              }\n            ],\n            model: \"claude-3-7-sonnet-ai-agent\",\n            usage: aiResponse.usage || {}\n          }\n        }];\n        \n      } catch (parseError) {\n        console.error('❌ Failed to parse AI Agent response:', parseError);\n        return [{ json: claudeResponse }];\n      }\n    } else {\n      console.warn('⚠️ No JSON found in AI Agent response');\n      return [{ json: claudeResponse }];\n    }\n  } else {\n    throw new Error('Invalid AI Agent response format');\n  }\n\n} catch (error) {\n  console.error('❌ AI Agent error:', error);\n  \n  return [{\n    json: {\n      ...claudeResponse,\n      ai_agent_error: true,\n      ai_agent_error_message: error.message,\n      ai_agent_timestamp: new Date().toISOString()\n    }\n  }];\n}"
      },
      "typeVersion": 2
    },
    {
      "id": "0cb93f10-3e59-4e38-bbc2-4bd7c809db27",
      "name": "用于结构化 AI agent 响应的 Webhook",
      "type": "n8n-nodes-base.code",
      "position": [
        2260,
        300
      ],
      "parameters": {
        "jsCode": "// Webhook Notification - Data Stored Success/Error\n\n// Get data from Qdrant Vector Store\nconst qdrantResult = items[0].json;\n\nconsole.log('📝 Qdrant result structure:', Object.keys(qdrantResult));\nconsole.log('📝 Full Qdrant result for debugging:', JSON.stringify(qdrantResult, null, 2).substring(0, 1000) + '...');\n\n// Configuration for webhooks - Add your URLs here\nconst webhooks = {\n  discord: \"\",\n  slack: \"\", \n  teams: \"\",\n  telegram: \"\",\n  custom: \"\"\n};\n\nlet isSuccess = false;\nlet errorDetails = {};\n\nif (qdrantResult.success === true) {\n  isSuccess = true;\n} else if (qdrantResult.qdrant_response && \n           qdrantResult.qdrant_response.status && \n           qdrantResult.qdrant_response.status.status === \"ok\") {\n  isSuccess = true;\n} else if (qdrantResult.status && qdrantResult.status.status === \"ok\") {\n  isSuccess = true;\n} else if (qdrantResult.qdrant_response && qdrantResult.qdrant_response.result) {\n  isSuccess = true;\n}\n\nif (!isSuccess) {\n  errorDetails = {\n    error_message: qdrantResult.message || qdrantResult.error_message || \"Unknown error\",\n    error_details: qdrantResult.error_details || {},\n    status_code: qdrantResult.status_code || qdrantResult.qdrant_response?.status_code,\n    raw_error: qdrantResult.error || qdrantResult.qdrant_response?.error || \"No specific error found\"\n  };\n  \n  console.log('❌ Detected error in Qdrant result:', errorDetails);\n}\n\nconst pointId = qdrantResult.point_info?.id || \n               (qdrantResult.qdrant_response?.result?.ids && qdrantResult.qdrant_response.result.ids[0]) || \n               qdrantResult.id ||\n               (isSuccess ? \"stored-but-no-id\" : \"not-stored\");\n\nconst itemTitle = qdrantResult.point_info?.title || \n                 qdrantResult.original_data?.title || \n                 qdrantResult.original_data?.metadata?.title ||\n                 qdrantResult.payload?.title ||\n                 qdrantResult.points?.[0]?.payload?.title ||\n                 (qdrantResult.points?.[0] ? \"Data without title\" : \"Untitled\");\n\nconst itemUrl = qdrantResult.original_data?.metadata?.url ||\n               qdrantResult.payload?.url ||\n               qdrantResult.points?.[0]?.payload?.url ||\n               qdrantResult.url ||\n               \"No URL available\";\n\nconst vectorDimensions = qdrantResult.point_info?.vector_dimensions || \n                        qdrantResult.vector?.length ||\n                        qdrantResult.points?.[0]?.vector?.length ||\n                        (qdrantResult.qdrant_response?.result?.vector_size) || \n                        \"unknown\";\n\nconst collectionName = qdrantResult.collection || \n                      (qdrantResult.qdrant_response?.collection_name) || \n                      \"hacker-news\";\n\nconst timestamp = new Date().toISOString();\nconst notificationData = {\n  status: isSuccess ? \"success\" : \"error\",\n  message: isSuccess \n    ? \"✅ Data successfully scraped and stored in vector database\" \n    : \"❌ Error storing data in vector database\",\n  details: {\n    id: pointId,\n    title: itemTitle?.substring(0, 100) + (itemTitle?.length > 100 ? \"...\" : \"\") || \"No title\",\n    url: itemUrl,\n    vector_size: vectorDimensions,\n    timestamp: timestamp,\n    collection: collectionName\n  },\n  error: !isSuccess ? errorDetails : undefined\n};\n\nfunction createMessageForPlatform(platform, data) {\n  switch (platform) {\n    case 'discord':\n      const fields = [\n        {\n          name: \"Item ID\",\n          value: data.details.id,\n          inline: true\n        },\n        {\n          name: \"Title\",\n          value: data.details.title || \"No title\",\n          inline: true\n        },\n        {\n          name: \"Collection\",\n          value: data.details.collection,\n          inline: true\n        },\n        {\n          name: \"Vector Size\",\n          value: `${data.details.vector_size} dimensions`,\n          inline: true\n        }\n      ];\n      \n      if (data.details.url && data.details.url !== \"No URL available\") {\n        fields.push({\n          name: \"URL\",\n          value: data.details.url,\n          inline: false\n        });\n      }\n      \n      if (data.error) {\n        fields.push({\n          name: \"Error Message\",\n          value: data.error.error_message || \"Unknown error\",\n          inline: false\n        });\n        \n        const errorDetailsStr = JSON.stringify(data.error.error_details, null, 2);\n        if (errorDetailsStr && errorDetailsStr !== \"{}\" && errorDetailsStr.length < 1000) {\n          fields.push({\n            name: \"Error Details\",\n            value: \"```json\\n\" + errorDetailsStr + \"\\n```\",\n            inline: false\n          });\n        }\n      }\n      \n      return {\n        embeds: [{\n          title: data.status === \"success\" ? \"✅ Vector Storage Success\" : \"❌ Vector Storage Error\",\n          description: data.message,\n          color: data.status === \"success\" ? 0x00ff00 : 0xff0000,\n          fields: fields,\n          timestamp: data.details.timestamp,\n          footer: {\n            text: \"n8n Workflow - Vector DB\"\n          }\n        }]\n      };\n      \n    case 'slack':\n      const blocks = [\n        {\n          type: \"section\",\n          text: {\n            type: \"mrkdwn\",\n            text: `*${data.status === \"success\" ? \"✅ Vector Storage Success\" : \"❌ Vector Storage Error\"}*\\n${data.message}`\n          }\n        },\n        {\n          type: \"section\",\n          fields: [\n            {\n              type: \"mrkdwn\",\n              text: `*ID:*\\n${data.details.id}`\n            },\n            {\n              type: \"mrkdwn\",\n              text: `*Title:*\\n${data.details.title}`\n            },\n            {\n              type: \"mrkdwn\",\n              text: `*Collection:*\\n${data.details.collection}`\n            },\n            {\n              type: \"mrkdwn\",\n              text: `*Vector:*\\n${data.details.vector_size} dimensions`\n            }\n          ]\n        }\n      ];\n      \n      if (data.details.url && data.details.url !== \"No URL available\") {\n        blocks.push({\n          type: \"section\",\n          text: {\n            type: \"mrkdwn\",\n            text: `*URL:*\\n${data.details.url}`\n          }\n        });\n      }\n      \n      if (data.error) {\n        blocks.push({\n          type: \"section\",\n          text: {\n            type: \"mrkdwn\",\n            text: `*Error:*\\n${data.error.error_message}`\n          }\n        });\n      }\n      \n      blocks.push({\n        type: \"context\",\n        elements: [\n          {\n            type: \"mrkdwn\",\n            text: `⏰ ${data.details.timestamp}`\n          }\n        ]\n      });\n      \n      return { blocks };\n      \n    case 'teams':\n      const facts = [\n        {\n          name: \"ID\",\n          value: data.details.id\n        },\n        {\n          name: \"Title\",\n          value: data.details.title\n        },\n        {\n          name: \"Collection\",\n          value: data.details.collection\n        },\n        {\n          name: \"Vector Size\",\n          value: `${data.details.vector_size} dimensions`\n        },\n        {\n          name: \"Timestamp\",\n          value: data.details.timestamp\n        }\n      ];\n      \n      if (data.details.url && data.details.url !== \"No URL available\") {\n        facts.push({\n          name: \"URL\",\n          value: data.details.url\n        });\n      }\n      \n      if (data.error) {\n        facts.push({\n          name: \"Error\",\n          value: data.error.error_message\n        });\n      }\n      \n      return {\n        \"@type\": \"MessageCard\",\n        \"@context\": \"http://schema.org/extensions\",\n        \"themeColor\": data.status === \"success\" ? \"00FF00\" : \"FF0000\",\n        \"summary\": data.message,\n        \"sections\": [{\n          \"activityTitle\": data.status === \"success\" ? \"✅ Vector Storage Success\" : \"❌ Vector Storage Error\",\n          \"activitySubtitle\": data.message,\n          \"facts\": facts\n        }]\n      };\n      \n    default:\n      return {\n        status: data.status,\n        message: data.message,\n        details: data.details,\n        error: data.error,\n        timestamp: data.details.timestamp\n      };\n  }\n}\n\nasync function sendToWebhook(platform, webhookUrl, data) {\n  if (!webhookUrl || webhookUrl.trim() === \"\") {\n    console.log(`⚠️ No webhook URL for ${platform} - skipping`);\n    return { skipped: true, platform };\n  }\n  \n  try {\n    const message = createMessageForPlatform(platform, data);\n    \n    const options = {\n      method: 'POST',\n      url: webhookUrl,\n      headers: {\n        'Content-Type': 'application/json'\n      },\n      body: message,\n      json: true\n    };\n    \n    const response = await this.helpers.request(options);\n    console.log(`✅ Sent notification to ${platform}`);\n    \n    return {\n      success: true,\n      platform,\n      response: response\n    };\n  } catch (error) {\n    console.error(`❌ Error sending to ${platform}:`, error);\n    \n    return {\n      error: true,\n      platform,\n      message: error.message\n    };\n  }\n}\n\nasync function sendAllNotifications() {\n  const results = [];\n  \n  for (const [platform, webhookUrl] of Object.entries(webhooks)) {\n    const result = await sendToWebhook(platform, webhookUrl, notificationData);\n    results.push(result);\n  }\n  \n  return results;\n}\n\ntry {\n  const notificationResults = await sendAllNotifications();\n  \n  console.log('✅ Notification summary:', {\n    total: notificationResults.length,\n    success: notificationResults.filter(r => r.success).length,\n    skipped: notificationResults.filter(r => r.skipped).length,\n    errors: notificationResults.filter(r => r.error).length\n  });\n  \n  return [{\n    json: {\n      original_qdrant_result: qdrantResult,\n      notification_results: notificationResults,\n      notification_data: notificationData,\n      is_success: isSuccess,\n      timestamp: new Date().toISOString()\n    }\n  }];\n  \n} catch (error) {\n  console.error('❌ Error in webhook notifications:', error);\n  \n  try {\n    const errorData = {\n      status: \"error\",\n      message: \"❌ Critical error in webhook notification\",\n      details: {\n        id: \"webhook-error\",\n        title: error.message,\n        url: \"N/A\",\n        vector_size: \"N/A\",\n        timestamp: new Date().toISOString(),\n        collection: \"N/A\"\n      },\n      error: {\n        error_message: error.message,\n        error_stack: error.stack\n      }\n    };\n    \n    if (webhooks.discord) {\n      const message = createMessageForPlatform('discord', errorData);\n      await this.helpers.request({\n        method: 'POST',\n        url: webhooks.discord,\n        headers: { 'Content-Type': 'application/json' },\n        body: message,\n        json: true\n      });\n    }\n  } catch (webhookError) {\n    console.error('💥 Critical error in error handler:', webhookError);\n  }\n  \n  return [{\n    json: {\n      error: true,\n      message: error.message,\n      original_data: qdrantResult\n    }\n  }];\n}"
      },
      "typeVersion": 2
    },
    {
      "id": "257f6f96-d02a-4fba-bd26-baf5aa3c3d89",
      "name": "导出数据 webhook",
      "type": "n8n-nodes-base.code",
      "position": [
        1900,
        320
      ],
      "parameters": {
        "jsCode": "const inputData = items[0].json;\n\nconst webhooks = {\n  discord: \"\",\n  slack: \"\",\n  linear: \"\",\n  teams: \"\",\n  telegram: \"\"\n};\n\nlet formattedData = {};\ntry {\n  if (inputData.content && Array.isArray(inputData.content)) {\n    const claudeText = inputData.content[0].text;\n    const jsonMatch = claudeText.match(/\\{[\\s\\S]*\\}/);\n    if (jsonMatch) {\n      formattedData = JSON.parse(jsonMatch[0]);\n    } else {\n      formattedData = { content: claudeText };\n    }\n  } else {\n    formattedData = inputData;\n  }\n} catch (parseError) {\n  console.error('Error parsing Claude response:', parseError);\n  formattedData = { \n    error: \"Parse error\", \n    raw_content: inputData \n  };\n}\n\nconst timestamp = new Date().toISOString().replace(/[:.]/g, '-');\nconst filename = `extracted-data-${timestamp}.txt`;\n\nconst fileContent = `🤖 EXTRACTED AND FORMATTED DATA\n=======================================\nTimestamp: ${new Date().toISOString()}\nSource: n8n Workflow (Scrapeless + Claude)\n=======================================\n\n📊 STRUCTURED DATA:\n${JSON.stringify(formattedData, null, 2)}\n\n=======================================\n🔍 RAW DATA (Debug):\n${JSON.stringify(inputData, null, 2)}\n=======================================`;\n\nasync function sendFileToWebhook(platform, webhookUrl, fileContent, filename) {\n  if (!webhookUrl || webhookUrl.trim() === \"\") {\n    console.log(`⚠️ ${platform} webhook URL empty - skipping`);\n    return { skipped: true, platform };\n  }\n  \n  try {\n    let formData;\n    let contentType;\n    \n    switch (platform) {\n      case 'discord':\n        formData = {\n          content: `🤖 **Extracted Data** - ${timestamp}`,\n          file: {\n            value: Buffer.from(fileContent, 'utf8'),\n            options: {\n              filename: filename,\n              contentType: 'text/plain'\n            }\n          }\n        };\n        contentType = 'multipart/form-data';\n        break;\n        \n      case 'slack':\n        const slackMessage = {\n          text: `🤖 Extracted Data - ${timestamp}`,\n          blocks: [\n            {\n              type: \"section\",\n              text: {\n                type: \"mrkdwn\",\n                text: \"*📊 Extracted and Formatted Data*\"\n              }\n            },\n            {\n              type: \"section\",\n              text: {\n                type: \"mrkdwn\",\n                text: `\\`\\`\\`${fileContent.substring(0, 2800)}\\`\\`\\``\n              }\n            }\n          ]\n        };\n        \n        const response = await this.helpers.request({\n          method: 'POST',\n          url: webhookUrl,\n          headers: { 'Content-Type': 'application/json' },\n          body: slackMessage,\n          json: true\n        });\n        \n        return { success: true, platform, response, method: 'json_message' };\n        \n      case 'telegram':\n        formData = {\n          document: {\n            value: Buffer.from(fileContent, 'utf8'),\n            options: {\n              filename: filename,\n              contentType: 'text/plain'\n            }\n          },\n          caption: `🤖 Extracted Data - ${timestamp}`\n        };\n        contentType = 'multipart/form-data';\n        break;\n        \n      default:\n        const jsonMessage = {\n          text: `🤖 Extracted Data - ${timestamp}`,\n          attachment: {\n            filename: filename,\n            content: fileContent\n          },\n          metadata: {\n            timestamp: timestamp,\n            platform: platform\n          }\n        };\n        \n        const jsonResponse = await this.helpers.request({\n          method: 'POST',\n          url: webhookUrl,\n          headers: { 'Content-Type': 'application/json' },\n          body: jsonMessage,\n          json: true\n        });\n        \n        return { success: true, platform, response: jsonResponse, method: 'json_fallback' };\n    }\n    \n    if (formData && contentType === 'multipart/form-data') {\n      const response = await this.helpers.request({\n        method: 'POST',\n        url: webhookUrl,\n        formData: formData,\n        headers: {}\n      });\n      \n      console.log(`✅ ${platform} file sent successfully`);\n      return { \n        success: true, \n        platform, \n        response: response,\n        method: 'file_upload',\n        filename: filename\n      };\n    }\n    \n  } catch (error) {\n    console.error(`❌ Error ${platform} webhook:`, error);\n    return { \n      error: true, \n      platform, \n      message: error.message || 'Unknown error'\n    };\n  }\n}\n\nconst results = [];\n\nfor (const [platform, webhookUrl] of Object.entries(webhooks)) {\n  const result = await sendFileToWebhook(platform, webhookUrl, fileContent, filename);\n  results.push(result);\n}\n\nreturn [{\n  json: {\n    webhook_results: results,\n    file_info: {\n      filename: filename,\n      size_bytes: Buffer.byteLength(fileContent, 'utf8'),\n      content_preview: fileContent.substring(0, 200) + '...'\n    },\n    formatted_data: formattedData,\n    timestamp: new Date().toISOString(),\n    summary: {\n      total_platforms: Object.keys(webhooks).length,\n      sent_successfully: results.filter(r => r.success).length,\n      skipped: results.filter(r => r.skipped).length,\n      errors: results.filter(r => r.error).length,\n      file_uploads: results.filter(r => r.method === 'file_upload').length,\n      json_messages: results.filter(r => r.method === 'json_message' || r.method === 'json_fallback').length\n    }\n  }\n}];"
      },
      "typeVersion": 2
    },
    {
      "id": "f704e1d8-2177-45f3-a34a-5e53b5fbe248",
      "name": "AI 数据检查器",
      "type": "n8n-nodes-base.code",
      "position": [
        1100,
        320
      ],
      "parameters": {
        "jsCode": "const inputData = items[0].json;\n\nlet htmlContent = '';\nif (inputData.data && inputData.data.html) {\n  htmlContent = inputData.data.html;\n} else if (inputData.data && inputData.data.content) {\n  htmlContent = inputData.data.content;\n} else if (inputData.content) {\n  htmlContent = inputData.content;\n} else if (inputData.data) {\n  htmlContent = JSON.stringify(inputData.data);\n} else {\n  htmlContent = JSON.stringify(inputData);\n}\n\nconst claudePayload = {\n  model: \"claude-3-7-sonnet-20250219\",\n  max_tokens: 4096,\n  messages: [\n    {\n      role: \"user\",\n      content: `Extract and format this HTML content into structured JSON. Focus on main articles, titles, and content. Return the data in this format:\n{\n  \"search_result\": {\n    \"title\": \"Page title or main heading\",\n    \"articles\": [\n      {\n        \"title\": \"Article title\",\n        \"content\": \"Article content/summary\",\n        \"url\": \"Article URL if available\"\n      }\n    ],\n    \"extracted_at\": \"${new Date().toISOString()}\"\n  }\n}\n\n\n\nHTML Content:\n${htmlContent}`\n    }\n  ]\n};\n\ntry {\n  const options = {\n    method: 'POST',\n    url: 'https://api.anthropic.com/v1/messages',\n    headers: {\n      'x-api-key': 'YOUR-API-KEY',\n      'content-type': 'application/json'\n    },\n    body: claudePayload,\n    json: true\n  };\n\n  const claudeResponse = await this.helpers.request(options);\n  \n  console.log('Claude Response:', JSON.stringify(claudeResponse, null, 2));\n  \n  return [{ json: claudeResponse }];\n  \n} catch (error) {\n  console.error('Error calling Claude API:', error);\n  \n  return [{\n    json: {\n      error: true,\n      message: error.message,\n      input_data: inputData\n    }\n  }];\n}"
      },
      "typeVersion": 2
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "107aa993-f9c8-46a7-aafa-b75db5f66780",
  "connections": {
    "AI Data Checker": {
      "main": [
        [
          {
            "node": "Expot data webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Claude AI Agent": {
      "main": [
        [
          {
            "node": "Format Claude Output",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Ollama Embeddings": {
      "main": [
        [
          {
            "node": "Qdrant Vector store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Qdrant Vector store": {
      "main": [
        [
          {
            "node": "Webhook for structured AI agent response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Claude Output": {
      "main": [
        [
          {
            "node": "Ollama Embeddings",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Claude Data extractor": {
      "main": [
        [
          {
            "node": "Claude AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Scrapeless Web Request": {
      "main": [
        [
          {
            "node": "AI Data Checker",
            "type": "main",
            "index": 0
          },
          {
            "node": "Claude Data extractor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check Collection Exists": {
      "main": [
        [
          {
            "node": "Collection Exists Check",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Collection Exists Check": {
      "main": [
        [
          {
            "node": "Set Fields - URL and Webhook URL",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Create Qdrant Collection",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create Qdrant Collection": {
      "main": [
        [
          {
            "node": "Set Fields - URL and Webhook URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking 'Test workflow'": {
      "main": [
        [
          {
            "node": "Check Collection Exists",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set Fields - URL and Webhook URL": {
      "main": [
        [
          {
            "node": "Scrapeless Web Request",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}