{
  "name": "tepto-vector-storing-shop",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.3,
      "position": [
        -1072,
        256
      ],
      "id": "3f2411cd-7cdf-4b37-91cb-43afa0fa611c",
      "name": "When chat message received",
      "webhookId": "cc00d5d8-2f31-4af5-a50a-0bfbcee955f3"
    },
    {
      "parameters": {
        "url": "={{ $json.chatInput }}/robots.txt",
        "sendQuery": true,
        "queryParameters": {
          "parameters": [
            {}
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        -784,
        256
      ],
      "id": "fcc3a522-e4da-4974-93bb-65f7c81941c4",
      "name": "Check for robots.txt",
      "onError": "continueErrorOutput"
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://crawl4ai:11235/crawl",
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "urls",
              "value": "={{ [$json.chatInput] }}"
            },
            {
              "name": "priority",
              "value": "10"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        -288,
        448
      ],
      "id": "17b9227e-8f21-48e6-aaa7-0e2c46aea61f",
      "name": "Crawl with Crawl4ai"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "=Look at the following data below and return only a json in the format of the example below. \ndata: {{ $json.data }} \n\nexample:\n{\"sitemap_found\":\"true\", \"sitemap_url_count\": \"1\", \"sitemap_url\":[\"https://example.com/sitemap.xml\"]}",
        "hasOutputParser": true,
        "messages": {
          "messageValues": [
            {
              "message": "You are an assistant to read robots.txt and find out about sitemap xml."
            },
            {
              "type": "HumanMessagePromptTemplate",
              "message": "=Look at the following data below and only a json in the format of the example below. \ndata: {{ $json.data }} \n\nexample:\n{\"sitemap_found\":\"true\", \"sitemap_url_count\": \"1\", \"sitemap_url\":[\"https://example.com/sitemap.xml\"]}"
            }
          ]
        },
        "batching": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "typeVersion": 1.7,
      "position": [
        -384,
        -160
      ],
      "id": "c32c974d-8da0-4110-adb2-1b4890834ef3",
      "name": "Basic LLM Chain"
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "gpt-4o-mini",
          "mode": "list",
          "cachedResultName": "gpt-4o-mini"
        },
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1.2,
      "position": [
        -416,
        64
      ],
      "id": "68e21a9e-ca9c-4757-99dd-46d8067bf8a4",
      "name": "OpenAI Chat Model2",
      "credentials": {
        "openAiApi": {
          "id": "n8YEc2Yc3MsrQ9g2",
          "name": "OpenAi account"
        }
      }
    },
    {
      "parameters": {
        "jsonSchemaExample": "{\"sitemap_found\":\"true\", \"sitemap_url_count\": \"1\", \"sitemap_url\":[\"https://example.com/sitemap.xml\"]}",
        "autoFix": true
      },
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "typeVersion": 1.3,
      "position": [
        -288,
        64
      ],
      "id": "fd52fc51-53a7-4951-b51e-6a437fa4da7e",
      "name": "Structured Output Parser"
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "gpt-4o-mini",
          "mode": "list",
          "cachedResultName": "gpt-4o-mini"
        },
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1.2,
      "position": [
        -208,
        272
      ],
      "id": "f817f562-e5b0-476c-a9ca-a91f27196209",
      "name": "OpenAI Chat Model3",
      "credentials": {
        "openAiApi": {
          "id": "n8YEc2Yc3MsrQ9g2",
          "name": "OpenAi account"
        }
      }
    },
    {
      "parameters": {
        "url": "={{ $json['output.sitemap_url'] }}",
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        752,
        -32
      ],
      "id": "3145274b-1581-4a92-88a9-1f2e0b23f41d",
      "name": "HTTP Request"
    },
    {
      "parameters": {
        "dataPropertyName": "=data",
        "options": {}
      },
      "type": "n8n-nodes-base.xml",
      "typeVersion": 1,
      "position": [
        976,
        -32
      ],
      "id": "8b251af5-30c1-429b-b934-f679936e8e4c",
      "name": "XML"
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "strict",
            "version": 2
          },
          "conditions": [
            {
              "id": "15b424f0-b279-4b28-8df1-a602304bcef8",
              "leftValue": "={{ $json.sitemapindex.sitemap.loc }}",
              "rightValue": ".gz",
              "operator": {
                "type": "string",
                "operation": "endsWith"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "type": "n8n-nodes-base.if",
      "typeVersion": 2.2,
      "position": [
        1200,
        -32
      ],
      "id": "4b5de457-31af-461c-9d44-40a183aa1e73",
      "name": "If"
    },
    {
      "parameters": {
        "url": "={{ $json.sitemapindex.sitemap.loc }}",
        "options": {
          "response": {
            "response": {
              "responseFormat": "file"
            }
          }
        }
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        1424,
        -32
      ],
      "id": "0f8e4e87-30e1-4ed6-9802-b7a03ac7e9b4",
      "name": "HTTP Request1"
    },
    {
      "parameters": {
        "mode": "insert",
        "pineconeIndex": {
          "__rl": true,
          "value": "tepto-n8n-workflow",
          "mode": "list",
          "cachedResultName": "tepto-n8n-workflow"
        },
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "typeVersion": 1.3,
      "position": [
        3248,
        48
      ],
      "id": "20699b80-88eb-4056-a0c4-1b39d14c388a",
      "name": "Pinecone Vector Store",
      "credentials": {
        "pineconeApi": {
          "id": "MsOEOyi31OS8GY2t",
          "name": "PineconeApi account"
        }
      }
    },
    {
      "parameters": {
        "model": "text-embedding-3-large",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "typeVersion": 1.2,
      "position": [
        3216,
        272
      ],
      "id": "842e5826-8c87-4367-b5ba-a6c9df97e792",
      "name": "Embeddings OpenAI",
      "credentials": {
        "openAiApi": {
          "id": "n8YEc2Yc3MsrQ9g2",
          "name": "OpenAi account"
        }
      }
    },
    {
      "parameters": {
        "textSplittingMode": "custom",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "typeVersion": 1.1,
      "position": [
        3344,
        272
      ],
      "id": "e34b06b3-8fb2-4dab-9e5f-dbd0df6597b0",
      "name": "Default Data Loader"
    },
    {
      "parameters": {
        "chunkSize": 350,
        "chunkOverlap": 50
      },
      "type": "@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter",
      "typeVersion": 1,
      "position": [
        3424,
        480
      ],
      "id": "18d17989-7b27-4dce-9be2-b31cc6847d65",
      "name": "Character Text Splitter"
    },
    {
      "parameters": {
        "content": "# Check for robots.txt",
        "height": 480,
        "width": 272
      },
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -880,
        32
      ],
      "typeVersion": 1,
      "id": "3d5e8145-ac02-4b80-ad4d-6b181cabe307",
      "name": "Sticky Note"
    },
    {
      "parameters": {
        "content": "# Get sitemap.xml",
        "height": 640,
        "width": 464
      },
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -448,
        -240
      ],
      "typeVersion": 1,
      "id": "f14023dd-00f2-466d-b0ea-d450554fb548",
      "name": "Sticky Note1"
    },
    {
      "parameters": {
        "content": "# Vector storing process",
        "height": 736,
        "width": 464
      },
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        3136,
        -64
      ],
      "typeVersion": 1,
      "id": "b151cb65-e90b-4749-8652-a14bda25bf3c",
      "name": "Sticky Note2"
    },
    {
      "parameters": {
        "content": "# Unpacking .xml.gz and looping through all xml documents to get the html content\n",
        "height": 304,
        "width": 2608
      },
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        496,
        -160
      ],
      "typeVersion": 1,
      "id": "239e2c30-b757-49e6-8a6a-047a284c1229",
      "name": "Sticky Note3"
    },
    {
      "parameters": {
        "content": "# Check for robots.txt",
        "height": 480,
        "width": 272
      },
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1488,
        16
      ],
      "typeVersion": 1,
      "id": "57a41e8b-398f-4523-82a4-997eaf790a37",
      "name": "Sticky Note4"
    },
    {
      "parameters": {
        "fieldToSplitOut": "output.sitemap_url",
        "options": {}
      },
      "type": "n8n-nodes-base.splitOut",
      "typeVersion": 1,
      "position": [
        80,
        48
      ],
      "id": "46141b15-6ec4-4e52-8e98-3d75e5cb25b4",
      "name": "Split out sitemap.xml url"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "n8n-nodes-base.splitInBatches",
      "typeVersion": 3,
      "position": [
        304,
        48
      ],
      "id": "aa7fdca2-3288-4a20-a2ab-c2bc31d57c28",
      "name": "Loop Over XML URLs"
    },
    {
      "parameters": {
        "amount": 1.5
      },
      "type": "n8n-nodes-base.wait",
      "typeVersion": 1.1,
      "position": [
        528,
        -32
      ],
      "id": "2696dbe2-f99c-4368-bf87-6e38eee15432",
      "name": "Wait",
      "webhookId": "8d09ff79-c9e5-4cc7-89ce-d4c08d8b7b8f"
    },
    {
      "parameters": {
        "amount": 1.5
      },
      "type": "n8n-nodes-base.wait",
      "typeVersion": 1.1,
      "position": [
        2768,
        -32
      ],
      "id": "165447bc-5901-4ee6-a7d8-7b36d53edbc2",
      "name": "Wait2",
      "webhookId": "ec67f4bf-d70d-47ac-89b9-23939918311c"
    },
    {
      "parameters": {},
      "type": "n8n-nodes-base.compression",
      "typeVersion": 1.1,
      "position": [
        1648,
        -32
      ],
      "id": "0fafd398-3d87-4ee9-a48f-89120c7ec186",
      "name": "Decompress gzip file"
    },
    {
      "parameters": {
        "operation": "xml",
        "binaryPropertyName": "file_0",
        "options": {}
      },
      "type": "n8n-nodes-base.extractFromFile",
      "typeVersion": 1,
      "position": [
        1872,
        -32
      ],
      "id": "d94db85f-8c1d-4adb-882c-fb59679f1b64",
      "name": "Extract xml content"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "n8n-nodes-base.xml",
      "typeVersion": 1,
      "position": [
        2096,
        -32
      ],
      "id": "8fcfbf31-ac20-4541-8a53-7cf8f61ab36b",
      "name": "Convert XML to JSON"
    },
    {
      "parameters": {
        "fieldToSplitOut": "urlset.url",
        "options": {}
      },
      "type": "n8n-nodes-base.splitOut",
      "typeVersion": 1,
      "position": [
        2320,
        -32
      ],
      "id": "73d28f87-a3fd-4cfa-ae9b-86cc183e148c",
      "name": "Split Out XML URLs from decompressed gzip"
    },
    {
      "parameters": {
        "options": {
          "reset": "="
        }
      },
      "type": "n8n-nodes-base.splitInBatches",
      "typeVersion": 3,
      "position": [
        2544,
        48
      ],
      "id": "ed5bb42d-4fd2-48c0-83f4-fb9c7e7c5816",
      "name": "Loop Over all XML URLs",
      "executeOnce": false
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://crawl4ai:11235/crawl",
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "urls",
              "value": "={{ [$json.loc] }}"
            },
            {
              "name": "priority",
              "value": "10"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        2992,
        -32
      ],
      "id": "6044642f-9c8f-40b3-8d3e-daefa79f820a",
      "name": "Crawl with Crawl4ai-2"
    }
  ],
  "pinData": {},
  "connections": {
    "When chat message received": {
      "main": [
        [
          {
            "node": "Check for robots.txt",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check for robots.txt": {
      "main": [
        [
          {
            "node": "Basic LLM Chain",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Crawl with Crawl4ai",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Basic LLM Chain": {
      "main": [
        [
          {
            "node": "Split out sitemap.xml url",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model2": {
      "ai_languageModel": [
        [
          {
            "node": "Basic LLM Chain",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Structured Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "Basic LLM Chain",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model3": {
      "ai_languageModel": [
        [
          {
            "node": "Structured Output Parser",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "HTTP Request": {
      "main": [
        [
          {
            "node": "XML",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "XML": {
      "main": [
        [
          {
            "node": "If",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "If": {
      "main": [
        [
          {
            "node": "HTTP Request1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "HTTP Request1": {
      "main": [
        [
          {
            "node": "Decompress gzip file",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store": {
      "main": [
        [
          {
            "node": "Loop Over all XML URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Default Data Loader": {
      "ai_document": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Character Text Splitter": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "Split out sitemap.xml url": {
      "main": [
        [
          {
            "node": "Loop Over XML URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over XML URLs": {
      "main": [
        [],
        [
          {
            "node": "Wait",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait": {
      "main": [
        [
          {
            "node": "HTTP Request",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait2": {
      "main": [
        [
          {
            "node": "Crawl with Crawl4ai-2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Decompress gzip file": {
      "main": [
        [
          {
            "node": "Extract xml content",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract xml content": {
      "main": [
        [
          {
            "node": "Convert XML to JSON",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Convert XML to JSON": {
      "main": [
        [
          {
            "node": "Split Out XML URLs from decompressed gzip",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split Out XML URLs from decompressed gzip": {
      "main": [
        [
          {
            "node": "Loop Over all XML URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over all XML URLs": {
      "main": [
        [
          {
            "node": "Loop Over XML URLs",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Wait2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Crawl with Crawl4ai-2": {
      "main": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "b337dd9a-99f0-4d0f-b782-39afa8b62e0c",
  "meta": {
    "templateCredsSetupCompleted": true,
    "instanceId": "09eb18af5dccac351cf0268b293a762f1ecd59086e605300f34309f080a1382a"
  },
  "id": "kCNlJS2UNnNebhIz",
  "tags": []
}