{
  "name": "Populate a Pinecone vector database from a website",
  "nodes": [
    {
      "parameters": {
        "model": "text-embedding-3-large",
        "options": {},
        "requestOptions": {}
      },
      "id": "856f2426-b4b5-4180-a422-d26692844afb",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "typeVersion": 1,
      "position": [
        80,
        1040
      ],
      "credentials": {
        "openAiApi": {
          "id": "tW3bkXa0SAK0OzvR",
          "name": "OpenAi account Debs"
        }
      }
    },
    {
      "parameters": {
        "options": {},
        "requestOptions": {}
      },
      "id": "1e702984-6f79-416e-981a-6728d4b3c233",
      "name": "Default Data Loader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "typeVersion": 1,
      "position": [
        260,
        960
      ]
    },
    {
      "parameters": {
        "options": {
          "splitCode": "markdown"
        },
        "requestOptions": {}
      },
      "id": "2d1f30fd-f251-4389-8f6d-2c950018a91f",
      "name": "Recursive Character Text Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "typeVersion": 1,
      "position": [
        300,
        1160
      ]
    },
    {
      "parameters": {
        "batchSize": 10,
        "options": {}
      },
      "id": "4e8a9d4c-6009-4d9b-b603-0438c65ba9df",
      "name": "Loop Over Items",
      "type": "n8n-nodes-base.splitInBatches",
      "typeVersion": 3,
      "position": [
        -840,
        1040
      ]
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "gpt-4o",
          "mode": "list",
          "cachedResultName": "gpt-4o"
        },
        "options": {},
        "requestOptions": {}
      },
      "id": "e7967355-41b4-4bc5-b192-c8bc0699e925",
      "name": "OpenAI Model",
      "type": "@n8n/n8n-nodes-langchain.lmOpenAi",
      "typeVersion": 1,
      "position": [
        -1320,
        1680
      ],
      "credentials": {
        "openAiApi": {
          "id": "tW3bkXa0SAK0OzvR",
          "name": "OpenAi account Debs"
        }
      }
    },
    {
      "parameters": {
        "url": "https://n8n-io.github.io/n8n-demo-website/sitemap.xml",
        "options": {}
      },
      "id": "5fb88663-f28b-4da2-acd9-1cbb0c5d28e7",
      "name": "Get sitemap",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        -1480,
        740
      ]
    },
    {
      "parameters": {
        "options": {
          "explicitRoot": false,
          "ignoreAttrs": true
        }
      },
      "id": "0e6287b8-9a65-4af0-8e69-3aae3648fd13",
      "name": "Turn XML sitemap into JSON",
      "type": "n8n-nodes-base.xml",
      "typeVersion": 1,
      "position": [
        -1260,
        740
      ]
    },
    {
      "parameters": {
        "fieldToSplitOut": "url",
        "options": {}
      },
      "id": "acd3e717-99f5-4238-aa4d-795caef660b1",
      "name": "Turn the URL array into multiple items",
      "type": "n8n-nodes-base.splitOut",
      "typeVersion": 1,
      "position": [
        -1040,
        740
      ]
    },
    {
      "parameters": {},
      "id": "f3b4ad5e-b261-4b97-9077-3b9259d5b37d",
      "name": "Wait 5 seconds",
      "type": "n8n-nodes-base.wait",
      "typeVersion": 1.1,
      "position": [
        -320,
        1060
      ],
      "webhookId": "f4e7dead-77ad-4216-a5a0-ef95914bf3ab"
    },
    {
      "parameters": {
        "url": "={{ $json.loc }}",
        "options": {}
      },
      "id": "361b2a70-d0c5-4498-8a70-0688710e76e6",
      "name": "Get pages listed in the sitemap",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        -580,
        1060
      ]
    },
    {
      "parameters": {},
      "id": "14ddd282-9bf0-459f-9595-5154e16f9cc0",
      "name": "Chat Trigger",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1,
      "position": [
        -1620,
        1420
      ],
      "webhookId": "4b338d3c-b03f-42f2-94c1-9353d0f1fbc2"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "={{ $('Chat Trigger').item.json.chatInput }}"
      },
      "id": "263585e6-02bb-4940-9bb3-15f32b0f8079",
      "name": "Question and Answer Chain",
      "type": "@n8n/n8n-nodes-langchain.chainRetrievalQa",
      "typeVersion": 1.3,
      "position": [
        -1280,
        1420
      ]
    },
    {
      "parameters": {
        "topK": 10,
        "requestOptions": {}
      },
      "id": "91ad53ec-a761-43f6-a6f1-835263222e0c",
      "name": "Vector Store Retriever",
      "type": "@n8n/n8n-nodes-langchain.retrieverVectorStore",
      "typeVersion": 1,
      "position": [
        -1080,
        1620
      ]
    },
    {
      "parameters": {
        "model": "text-embedding-3-large",
        "options": {},
        "requestOptions": {}
      },
      "id": "5c55cb38-be26-405d-bd39-d29e0a33b683",
      "name": "Embeddings OpenAI2",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "typeVersion": 1,
      "position": [
        -780,
        2040
      ],
      "credentials": {
        "openAiApi": {
          "id": "tW3bkXa0SAK0OzvR",
          "name": "OpenAi account Debs"
        }
      }
    },
    {
      "parameters": {
        "fieldsToAggregate": {
          "fieldToAggregate": [
            {
              "fieldToAggregate": "content"
            }
          ]
        },
        "options": {}
      },
      "id": "48dbd7f7-1ca1-41e2-9fd5-e916ea76589b",
      "name": "Aggregate",
      "type": "n8n-nodes-base.aggregate",
      "typeVersion": 1,
      "position": [
        -100,
        740
      ]
    },
    {
      "parameters": {
        "content": "**Aggregate into one item**\n\nThe Pinecone node loops over each input item. This is standard n8n node behavior.\n\nThis means if you want to use the **Clear namespace** setting in the Pinecone node, you need to input a single item.",
        "height": 381.66422439067196,
        "color": 5
      },
      "id": "5b70d4ae-1889-43d3-b92d-bf73e43236bd",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -160,
        520
      ]
    },
    {
      "parameters": {
        "content": "### Workflow to scrape data and send it to Pinecone",
        "height": 878.8927796727229,
        "width": 2382.6739342193496,
        "color": 7
      },
      "id": "e9b5d557-51af-48d1-af33-8783f9ca3718",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -1856.703373323493,
        480
      ]
    },
    {
      "parameters": {
        "content": "### Workflow to chat and get answers from the Pinecone vector database",
        "height": 825.9872504327399,
        "width": 1181.407211476183,
        "color": 7
      },
      "id": "7efa097b-d4f2-49a4-9da5-4fcf6b83be3b",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -1680,
        1380
      ]
    },
    {
      "parameters": {
        "content": "## Try it out \n\n1. Set credentials and choose your Pinecone vector database. See the notes on individual nodes for details.\n2. Select **Execute workflow** to run the main workflow and load data into Pinecone.\n3. Select **Chat** and try asking:\n\n_What is the purpose of the n8n demo website?_",
        "height": 326.49681260818465,
        "color": 4
      },
      "id": "f21bc32b-a405-4d71-b6c9-7bffbb6faed9",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -2040,
        560
      ]
    },
    {
      "parameters": {
        "content": "**Setup**\n\n1. In Pinecone, create a vector database. Set **Dimensions** to `3072` and **Metric** to `cosine`. You can use the free starter plan.\n2. In the Pinecone node, set your credentials.\n3. Select your Pinecone index.",
        "height": 381.3701016273242,
        "width": 304.1011298750183,
        "color": 2
      },
      "id": "4be87782-f811-418f-b4b5-9e12c4cf7970",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        140,
        520
      ]
    },
    {
      "parameters": {
        "mode": "insert",
        "pineconeIndex": {
        },
        "options": {
          "clearNamespace": true,
          "pineconeNamespace": "test-web-scraper"
        }
      },
      "id": "94035a97-5a09-493c-aaae-dcba7bbf8526",
      "name": "Pinecone Vector Store",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "typeVersion": 1,
      "position": [
        160,
        740
      ],
      "credentials": {
        "pineconeApi": {
          "id": "lruA9GaKZSEY8dky",
          "name": "Debs Pinecone"
        }
      }
    },
    {
      "parameters": {
        "content": "## Next steps\n\nLearn more about [Advanced AI in n8n](https://docs.n8n.io/advanced-ai/)",
        "width": 331.8066536811489
      },
      "id": "2be1433b-0488-4c7e-8c10-e771d4dd4686",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        460,
        1280
      ]
    },
    {
      "parameters": {
        "content": "**Set your credentials**",
        "height": 206.68134932939768,
        "width": 182.42633582707612,
        "color": 2
      },
      "id": "fffbb04d-6d61-4dfa-bfd3-46b8c92a36d5",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        20,
        1000
      ]
    },
    {
      "parameters": {
        "content": "**Set your credentials**",
        "height": 184.89671964234537,
        "width": 173.09006596119673,
        "color": 2
      },
      "id": "810ac5e1-d730-47af-9282-64ab0b4fca16",
      "name": "Sticky Note7",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -1369.107685156473,
        1620.2285847094058
      ]
    },
    {
      "parameters": {
        "content": "**Set your credentials**",
        "height": 192.67694453057842,
        "width": 221.3274602682409,
        "color": 2
      },
      "id": "2cecc8ac-3c65-4294-8a5d-2842bc07d10a",
      "name": "Sticky Note8",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -860,
        1980
      ]
    },
    {
      "parameters": {
        "pineconeIndex": {
          "__rl": true,
          "value": "debs-test",
          "mode": "list",
          "cachedResultName": "debs-test"
        },
        "options": {
          "pineconeNamespace": "test-web-scraper"
        }
      },
      "id": "e673c46e-0815-4b58-9a8f-2fb86445b578",
      "name": "Pinecone Vector Store2",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "typeVersion": 1,
      "position": [
        -980,
        1840
      ],
      "credentials": {
        "pineconeApi": {
          "id": "lruA9GaKZSEY8dky",
          "name": "Debs Pinecone"
        }
      }
    },
    {
      "parameters": {
        "content": "**Set your credentials**\n\n**Select your Pinecone index***",
        "width": 367.59568816702017,
        "color": 2
      },
      "id": "ca4499ae-4e27-4848-9654-f7e744c081e7",
      "name": "Sticky Note9",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -1080,
        1760
      ]
    },
    {
      "parameters": {},
      "id": "b43ddbd1-adfd-4bba-bee5-4b81229e88dd",
      "name": "Start the workflow by clicking \"Execute workflow\"",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        -1700,
        740
      ]
    },
    {
      "parameters": {
        "operation": "extractHtmlContent",
        "extractionValues": {
          "values": [
            {
              "key": "content",
              "cssSelector": ".md-content",
              "returnValue": "html"
            }
          ]
        },
        "options": {
          "trimValues": true,
          "cleanUpText": true
        }
      },
      "id": "d39624d7-93c0-4452-81b1-ffa04b216ceb",
      "name": "Extract main content",
      "type": "n8n-nodes-base.html",
      "typeVersion": 1.2,
      "position": [
        -380,
        740
      ]
    },
    {
      "parameters": {
        "content": "**Batch the calls to the website**\n\nFor the small demo website in this example, this is not essential. If you want to use this example with a larger website, batching like this helps avoid timeouts. Using the Wait node between batches avoids hitting the website with too many requests too fast.",
        "height": 298.48800301054644,
        "width": 316.2462039046831,
        "color": 5
      },
      "id": "9825926d-ce6d-429e-9006-6ff5fd1f46ca",
      "name": "Sticky Note10",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -1220,
        1020
      ]
    },
    {
      "parameters": {
        "content": "## How to scrape a different website\n\nThis workflow uses a small example website provided by n8n. To use a different site:\n\n1. Change the sitemap URL in **Get sitemap**.\n2. Update **Extract main content** according to the HTML structure of the website you're scraping.",
        "height": 356.06166718347
      },
      "id": "7c2e4bde-3900-49b0-9bee-704e34664163",
      "name": "Sticky Note11",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -2040,
        960
      ]
    }
  ],
  "pinData": {},
  "connections": {
    "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
          }
        ]
      ]
    },
    "Recursive Character Text Splitter": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [
          {
            "node": "Extract main content",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Get pages listed in the sitemap",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get sitemap": {
      "main": [
        [
          {
            "node": "Turn XML sitemap into JSON",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Turn XML sitemap into JSON": {
      "main": [
        [
          {
            "node": "Turn the URL array into multiple items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Turn the URL array into multiple items": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait 5 seconds": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get pages listed in the sitemap": {
      "main": [
        [
          {
            "node": "Wait 5 seconds",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Chat Trigger": {
      "main": [
        [
          {
            "node": "Question and Answer Chain",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Model": {
      "ai_languageModel": [
        [
          {
            "node": "Question and Answer Chain",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Vector Store Retriever": {
      "ai_retriever": [
        [
          {
            "node": "Question and Answer Chain",
            "type": "ai_retriever",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI2": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store2",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Aggregate": {
      "main": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store2": {
      "ai_vectorStore": [
        [
          {
            "node": "Vector Store Retriever",
            "type": "ai_vectorStore",
            "index": 0
          }
        ]
      ]
    },
    "Start the workflow by clicking \"Execute workflow\"": {
      "main": [
        [
          {
            "node": "Get sitemap",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract main content": {
      "main": [
        [
          {
            "node": "Aggregate",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}