{
  "id": "pexxaVEwqIYmTXud",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "Crunchbase B2B Lead Discovery Pipeline with Bright Data & OpenAI",
  "tags": [
    {
      "id": "Kujft2FOjmOVQAmJ",
      "name": "Engineering",
      "createdAt": "2025-04-09T01:31:00.558Z",
      "updatedAt": "2025-04-09T01:31:00.558Z"
    },
    {
      "id": "ZOwtAMLepQaGW76t",
      "name": "Building Blocks",
      "createdAt": "2025-04-13T15:23:40.462Z",
      "updatedAt": "2025-04-13T15:23:40.462Z"
    },
    {
      "id": "ddPkw7Hg5dZhQu2w",
      "name": "AI",
      "createdAt": "2025-04-13T05:38:08.053Z",
      "updatedAt": "2025-04-13T05:38:08.053Z"
    }
  ],
  "nodes": [
    {
      "id": "7ed032ae-3f0c-4666-be5f-fbe5acf109a6",
      "name": "When clicking \u2018Test workflow\u2019",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -1700,
        -80
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "592205af-c46a-45c3-8662-6bdae78b6465",
      "name": "Set URL and Bright Data Zone",
      "type": "n8n-nodes-base.set",
      "position": [
        -1480,
        -80
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "3aedba66-f447-4d7a-93c0-8158c5e795f9",
              "name": "url",
              "type": "string",
              "value": "https://www.crunchbase.com/organization/stripe"
            },
            {
              "id": "4e7ee31d-da89-422f-8079-2ff2d357a0ba",
              "name": "zone",
              "type": "string",
              "value": "web_unlocker1"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "01126593-b23e-4a85-b09e-d6f10dac5a76",
      "name": "Perform Bright Data Web Request",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -1260,
        -80
      ],
      "parameters": {
        "url": "https://api.brightdata.com/request",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "zone",
              "value": "={{ $json.zone }}"
            },
            {
              "name": "url",
              "value": "={{ $json.url }}"
            },
            {
              "name": "format",
              "value": "raw"
            },
            {
              "name": "data_format",
              "value": "markdown"
            }
          ]
        },
        "genericAuthType": "httpHeaderAuth",
        "headerParameters": {
          "parameters": [
            {}
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "f716c1e6-0001-4cbf-a5a5-78509d02d55e",
      "name": "Markdown to Textual Data Extractor",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        -1040,
        -80
      ],
      "parameters": {
        "text": "=You need to analyze the below markdown and convert to textual data. Please do not output with your own thoughts. Make sure to output with textual data only with no links, scripts, css etc.\n\n{{ $json.data }}",
        "messages": {
          "messageValues": [
            {
              "message": "You are a markdown expert"
            }
          ]
        },
        "promptType": "define"
      },
      "typeVersion": 1.6
    },
    {
      "id": "5e54e7e9-b0d1-41a9-a828-f94c852b7b20",
      "name": "Google Sheets",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        -220,
        80
      ],
      "parameters": {
        "columns": {
          "value": {},
          "schema": [
            {
              "id": "output",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "output",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "autoMapInputData",
          "matchingColumns": [
            "Structured Data"
          ],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "appendOrUpdate",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "gid=0",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/15JBt1NjWELZVwcCAaD8B4JwjOojPf-HJ4D_F68etiOo/edit#gid=0",
          "cachedResultName": "Sheet1"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "15JBt1NjWELZVwcCAaD8B4JwjOojPf-HJ4D_F68etiOo",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/15JBt1NjWELZVwcCAaD8B4JwjOojPf-HJ4D_F68etiOo/edit?usp=drivesdk",
          "cachedResultName": "B2B Discovery"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "f71f7108-7439-458d-80eb-1ca96c8f621a",
      "name": "Structured Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        -400,
        500
      ],
      "parameters": {
        "jsonSchemaExample": "{\n  \"organization\": {\n    \"name\": \"string\",\n    \"about\": \"string\",\n    \"headquartersLocation\": \"string\",\n    \"headquartersRegions\": \"string\",\n    \"numberOfEmployees\": \"string\",\n    \"lastFundingType\": \"string\",\n    \"ipoStatus\": \"string\",\n    \"website\": \"string\",\n    \"cbRankCompany\": \"string\",\n    \"totalAcquisitions\": \"integer\",\n    \"totalInvestmentsMade\": \"integer\",\n    \"totalCrunchbaseContacts\": \"integer\",\n    \"totalEmployeeProfiles\": \"integer\",\n    \"industries\": [\"string\"],\n    \"foundedDate\": \"string\",\n    \"founders\": [\"string\"],\n    \"operatingStatus\": \"string\",\n    \"legalName\": \"string\",\n    \"relatedHubs\": [\"string\"],\n    \"hubTags\": [\"string\"],\n    \"companyType\": \"string\",\n    \"contactEmail\": \"string\",\n    \"phoneNumber\": \"string\",\n    \"recentNews\": [\n      {\n        \"date\": \"string\",\n        \"source\": \"string\",\n        \"title\": \"string\"\n      }\n    ],\n    \"productsAndServices\": [\n      {\n        \"productName\": \"string\",\n        \"productDescription\": \"string\"\n      }\n    ],\n    \"listsFeaturingThisCompany\": [\n      {\n        \"listName\": \"string\",\n        \"numberOfOrganizations\": \"string\",\n        \"totalFundingAmount\": \"string\",\n        \"numberOfInvestors\": \"string\"\n      }\n    ]\n  }\n}\n"
      },
      "typeVersion": 1.2
    },
    {
      "id": "3ec3c998-c674-45c8-bcbb-6a9e382e25aa",
      "name": "Structured Data Extractor",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        -580,
        280
      ],
      "parameters": {
        "text": "=Extract the structured info from the below content.\n\nHere's the Content:  {{ $json.text }}",
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 1.6
    },
    {
      "id": "3a9d7bb0-e63a-454f-86f1-cf86379255b9",
      "name": "Create a binary data for Summarization",
      "type": "n8n-nodes-base.function",
      "position": [
        -220,
        -320
      ],
      "parameters": {
        "functionCode": "items[0].binary = {\n  data: {\n    data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n  }\n};\nreturn items;"
      },
      "typeVersion": 1
    },
    {
      "id": "029bb734-b422-43bb-96da-a8a47e22dc49",
      "name": "Create a binary data for Structured Data Extract",
      "type": "n8n-nodes-base.function",
      "position": [
        -220,
        280
      ],
      "parameters": {
        "functionCode": "items[0].binary = {\n  data: {\n    data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n  }\n};\nreturn items;"
      },
      "typeVersion": 1
    },
    {
      "id": "9e9cc726-9004-4ca0-bc0f-a20f7c2ed2a1",
      "name": "Write the summarized content to disk",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        0,
        -320
      ],
      "parameters": {
        "options": {},
        "fileName": "=d:\\Crunchbase-Summary.json",
        "operation": "write"
      },
      "typeVersion": 1
    },
    {
      "id": "a9736eb9-8b01-40fd-b856-5a6311e007d3",
      "name": "Write the structured content to disk",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        0,
        280
      ],
      "parameters": {
        "options": {},
        "fileName": "=d:\\Crunchbase-Summary.json",
        "operation": "write"
      },
      "typeVersion": 1
    },
    {
      "id": "481b2c05-76c8-424f-9f7c-c172428dc865",
      "name": "Initiate a Webhook Notification for the extracted data",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -220,
        480
      ],
      "parameters": {
        "url": "https://webhook.site/7b5380a0-0544-48dc-be43-0116cb2d52c2",
        "options": {},
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "summary",
              "value": "={{ $json.output }}"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "0b94f3f7-5961-43c6-a092-19662581430d",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1720,
        -420
      ],
      "parameters": {
        "width": 400,
        "height": 300,
        "content": "## Note\n\nDeals with the Crunchbase B2B Lead Discovery  by utilizing the Bright Data Web Unlocker Product.\n\n**Please make sure to set the crunch base URL with the Bright Data zone name. Also update the Webhook Notification URL of your interest**\n\n**Please make sure to update the Google Sheets node credentials with your account**"
      },
      "typeVersion": 1
    },
    {
      "id": "2bd7450f-9e3e-4df9-9a22-f6a5db2ea7bf",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1280,
        -420
      ],
      "parameters": {
        "width": 480,
        "height": 300,
        "content": "## LLM Usages\n\nOpenAI GPT 4o model is being used.\n\nBasic LLM Chain for converting the markdown to textual content. Also perform the structured data extraction.\n\nSummarization Chain is being used for creating a summary of the extracted Crunchbase textual content."
      },
      "typeVersion": 1
    },
    {
      "id": "c5246dc6-ce52-45c2-886c-1898508f71d8",
      "name": "Summarize the content",
      "type": "@n8n/n8n-nodes-langchain.chainSummarization",
      "position": [
        -600,
        -420
      ],
      "parameters": {
        "options": {},
        "chunkingMode": "advanced"
      },
      "typeVersion": 2
    },
    {
      "id": "388023f6-710b-468c-a7c3-593818cfa87c",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -660,
        20
      ],
      "parameters": {
        "color": 6,
        "width": 860,
        "height": 660,
        "content": "## Structured Data Extract"
      },
      "typeVersion": 1
    },
    {
      "id": "38ccdc64-6d2f-4581-94d2-751095f39e48",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -660,
        -520
      ],
      "parameters": {
        "color": 4,
        "width": 860,
        "height": 480,
        "content": "## Summarization"
      },
      "typeVersion": 1
    },
    {
      "id": "8e159838-7c02-4f54-b56a-885f5912a384",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1720,
        -880
      ],
      "parameters": {
        "color": 7,
        "width": 400,
        "height": 400,
        "content": "## Logo\n\n\n![logo](https://images.seeklogo.com/logo-png/43/1/brightdata-logo-png_seeklogo-439974.png)\n"
      },
      "typeVersion": 1
    },
    {
      "id": "f4541bbd-d1e8-430d-8ee1-aea78db73eb8",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -1020,
        140
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "072ee9ed-f24a-4bf8-b23a-4d26d74ba6c8",
      "name": "OpenAI Chat Model1",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -560,
        -200
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "fa17f3f4-54cc-4e28-93ac-67c5d120a6da",
      "name": "OpenAI Chat Model2",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -580,
        480
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "675b44fd-e258-4f63-9d6b-c40a25c3bf19",
  "connections": {
    "Google Sheets": {
      "main": [
        []
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Markdown to Textual Data Extractor",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "Summarize the content",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model2": {
      "ai_languageModel": [
        [
          {
            "node": "Structured Data Extractor",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Summarize the content": {
      "main": [
        [
          {
            "node": "Create a binary data for Summarization",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Structured Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "Structured Data Extractor",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Structured Data Extractor": {
      "main": [
        [
          {
            "node": "Google Sheets",
            "type": "main",
            "index": 0
          },
          {
            "node": "Create a binary data for Structured Data Extract",
            "type": "main",
            "index": 0
          },
          {
            "node": "Initiate a Webhook Notification for the extracted data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set URL and Bright Data Zone": {
      "main": [
        [
          {
            "node": "Perform Bright Data Web Request",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Perform Bright Data Web Request": {
      "main": [
        [
          {
            "node": "Markdown to Textual Data Extractor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking \u2018Test workflow\u2019": {
      "main": [
        [
          {
            "node": "Set URL and Bright Data Zone",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Markdown to Textual Data Extractor": {
      "main": [
        [
          {
            "node": "Summarize the content",
            "type": "main",
            "index": 0
          },
          {
            "node": "Structured Data Extractor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create a binary data for Summarization": {
      "main": [
        [
          {
            "node": "Write the summarized content to disk",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create a binary data for Structured Data Extract": {
      "main": [
        [
          {
            "node": "Write the structured content to disk",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}