Zain Khan This workflow corresponds to n8n.io template #6526 — we link there as the canonical source.
This workflow follows the Documentdefaultdataloader → Google Gemini Embeddings recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"nodes": [
{
"id": "5ad6a510-3c4a-47e4-b8ff-c0e565e25d25",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
368,
944
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "3ff777b7-24bd-420c-af38-62a395f52a1a",
"name": "Extract Page URLs",
"type": "n8n-nodes-base.code",
"position": [
1936,
1392
],
"parameters": {},
"typeVersion": 2
},
{
"id": "6176e651-cef5-44e8-abed-0f6f6b81517b",
"name": "XML Conversion",
"type": "n8n-nodes-base.xml",
"position": [
1792,
1392
],
"parameters": {},
"typeVersion": 1
},
{
"id": "cca1e7e7-32f6-42fd-b23c-3c2586344a50",
"name": "Fetch Sitemap",
"type": "n8n-nodes-base.httpRequest",
"position": [
1632,
1392
],
"parameters": {},
"typeVersion": 4.2
},
{
"id": "520e131d-b5f2-4857-aebd-5724da2a8083",
"name": "Split Pages URL",
"type": "n8n-nodes-base.code",
"position": [
1792,
1216
],
"parameters": {},
"typeVersion": 2
},
{
"id": "7e7fe528-8748-470b-b627-a0c79b5aface",
"name": "Merge URLs",
"type": "n8n-nodes-base.merge",
"position": [
2128,
1232
],
"parameters": {},
"typeVersion": 3.2
},
{
"id": "a0517aaf-6ccd-481d-b97e-b183d305451b",
"name": "Remove Duplicate URLs",
"type": "n8n-nodes-base.removeDuplicates",
"position": [
2272,
1232
],
"parameters": {},
"typeVersion": 2
},
{
"id": "72c85ccf-a9d6-42b1-85a7-76800ba831e5",
"name": "Loop Over Page URLs",
"type": "n8n-nodes-base.splitInBatches",
"position": [
2480,
1232
],
"parameters": {},
"typeVersion": 3
},
{
"id": "73aebd19-60ae-40d1-a747-0b9537d9d67c",
"name": "Extract Content",
"type": "n8n-nodes-base.html",
"position": [
2672,
1136
],
"parameters": {},
"typeVersion": 1.2
},
{
"id": "0dbf70c1-cb57-4691-916f-2a2aa9a4cec0",
"name": "Fetch Page HTML For content",
"type": "n8n-nodes-base.httpRequest",
"position": [
2672,
1328
],
"parameters": {},
"typeVersion": 4.2
},
{
"id": "fa1c18c6-6c29-4e71-905e-0945909af99b",
"name": "Wait 5 sec",
"type": "n8n-nodes-base.wait",
"position": [
2832,
1328
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "2bf3ad7f-a2fd-44f9-b6af-5a500ef80591",
"name": "Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
3264,
1344
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "a86d4c2e-559c-4942-ac0d-2ddcc7eb7f39",
"name": "Gemini Embeddings",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"position": [
3072,
1344
],
"parameters": {},
"typeVersion": 1
},
{
"id": "f46188bd-c0a2-4d49-9b67-0937f891ae36",
"name": "Pinecone KnowledgeBase",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
3072,
1136
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "4f5dc6e3-8f75-46ab-b3e1-49deb7695469",
"name": "Input Sitemap or page urls",
"type": "n8n-nodes-base.formTrigger",
"position": [
1296,
1376
],
"parameters": {},
"typeVersion": 2.2
},
{
"id": "67f6e98a-946c-4460-93d4-707511deb4f5",
"name": "Switch",
"type": "n8n-nodes-base.switch",
"position": [
1440,
1376
],
"parameters": {},
"typeVersion": 3.2
}
],
"connections": {
"Switch": {
"main": [
[
{
"node": "Split Pages URL",
"type": "main",
"index": 0
}
],
[
{
"node": "Fetch Sitemap",
"type": "main",
"index": 0
}
]
]
},
"Merge URLs": {
"main": [
[
{
"node": "Remove Duplicate URLs",
"type": "main",
"index": 0
}
]
]
},
"Wait 5 sec": {
"main": [
[
{
"node": "Loop Over Page URLs",
"type": "main",
"index": 0
}
]
]
},
"Data Loader": {
"ai_document": [
[
{
"node": "Pinecone KnowledgeBase",
"type": "ai_document",
"index": 0
}
]
]
},
"Fetch Sitemap": {
"main": [
[
{
"node": "XML Conversion",
"type": "main",
"index": 0
}
]
]
},
"XML Conversion": {
"main": [
[
{
"node": "Extract Page URLs",
"type": "main",
"index": 0
}
]
]
},
"Extract Content": {
"main": [
[
{
"node": "Pinecone KnowledgeBase",
"type": "main",
"index": 0
}
]
]
},
"Split Pages URL": {
"main": [
[
{
"node": "Merge URLs",
"type": "main",
"index": 0
}
]
]
},
"Extract Page URLs": {
"main": [
[
{
"node": "Merge URLs",
"type": "main",
"index": 1
}
]
]
},
"Gemini Embeddings": {
"ai_embedding": [
[
{
"node": "Pinecone KnowledgeBase",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Loop Over Page URLs": {
"main": [
[
{
"node": "Extract Content",
"type": "main",
"index": 0
}
],
[
{
"node": "Fetch Page HTML For content",
"type": "main",
"index": 0
}
]
]
},
"Remove Duplicate URLs": {
"main": [
[
{
"node": "Loop Over Page URLs",
"type": "main",
"index": 0
}
]
]
},
"Input Sitemap or page urls": {
"main": [
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"Fetch Page HTML For content": {
"main": [
[
{
"node": "Wait 5 sec",
"type": "main",
"index": 0
}
]
]
}
}
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Use cases are many: Populate a custom chatbot's knowledge base, create a powerful search index for your website, or build a comprehensive repository of information for internal tools!
Source: https://n8n.io/workflows/6526/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Categories: Business Automation, Customer Support, AI, Knowledge Management
This template is designed for podcasters, researchers, educators, product teams, and support teams who work with audio content and want to turn it into searchable knowledge. It is especially useful fo
This simple philosophy changes the way we think about automated sales agents. Context changes everything. In this 4-part workflow, we start by creating a knowledge base that will act as context across
My workflow 3. Uses formTrigger, splitInBatches, lmChatGoogleGemini, httpRequest. Event-driven trigger; 36 nodes.
This n8n workflow automates the entire process, from learning based on your website data, documents to a multi-channel chatbot with automated ticket creation. It's the perfect solution for businesses