Zain Khan This workflow corresponds to n8n.io template #12146 — we link there as the canonical source.
This workflow follows the Agent → Chat Trigger 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": "ef6899c9-4229-414b-9874-6bfd8091563a",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-112,
112
],
"parameters": {
"width": 960,
"height": 800,
"content": "# AI Chatbot for businesses using Decodo, Pinecone, and Google Gemini\n\nThis n8n workflow provides an end-to-end solution for AI-powered customer support. It automates the process of scraping website data into a Pinecone knowledge base and provides a web-ready chat interface powered by Google Gemini.\n\n## 1. Data Ingestion & Knowledge Base Creation\n* This section gathers and refines website content to build the AI's \"memory.\"\n* URL Input & Consolidation: Accepts sitemaps or specific page URLs via a form, cleans the data, and removes duplicates.\n* Decodo Content Extraction: Fetches HTML for each URL and extracts the main text content, ensuring a clean dataset for the AI.\n* Embedding & Storage: Converts text into high-dimensional vectors using gemini-embedding-001 and stores them in the \"supportbot\" Pinecone index.\n\n## 2. AI Chat Interface (RAG Implementation)\n* This section handles the real-time interaction with users, using the knowledge base to answer questions.\n* Chat Trigger (Webhook): A public-facing node that allows the chatbot to be embedded on any website (typically appearing as a widget in the bottom-right corner).\n* AI Agent (LangChain): The central brain that coordinates between the user's question, the chat history, and the knowledge base.\n* Google Gemini Chat Model: Uses Gemini as the core LLM to generate natural, context-aware responses.\n* Window Buffer Memory: Maintains the last 10 exchanges of the conversation, allowing the AI to understand follow-up questions and maintain context.\n\n## 3. Vector Store Retrieval Tool\n* This bridges the chat interface with your stored data.\n* Pinecone Retrieval Tool: Configured as a tool for the AI Agent. When a user asks a question, the agent searches the \"supportbot\" index for relevant business information.\n* Gemini Embeddings: Converts the user\u2019s live chat query into a vector to find the most mathematically relevant matches within the Pinecone database."
},
"typeVersion": 1
},
{
"id": "8fd9561e-0dc8-45b1-a932-9b2bc5f9faa8",
"name": "Extract Page URLs",
"type": "n8n-nodes-base.code",
"position": [
1568,
448
],
"parameters": {
"jsCode": "const items = []\nfor (const item of $input.first().json.urlset.url) {\n items.push({ url: item.loc })\n}\n\nreturn items;"
},
"typeVersion": 2
},
{
"id": "1f5bc7b4-ad49-4fe9-9432-d353e1aae0f8",
"name": "XML Conversion",
"type": "n8n-nodes-base.xml",
"position": [
1424,
448
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "9885fdc2-d7ed-4d96-8f4d-fadd5deb0ed6",
"name": "Fetch Sitemap",
"type": "n8n-nodes-base.httpRequest",
"position": [
1264,
448
],
"parameters": {
"url": "={{ $json['Sitemap URL'] }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "ede19831-b7ab-42fa-a30a-e642282b139f",
"name": "Split Pages URL",
"type": "n8n-nodes-base.code",
"position": [
1424,
272
],
"parameters": {
"jsCode": "function addTrailingSlash(str) {\n if (typeof str !== 'string') {\n return str; // Or throw an error, handle non-string inputs\n }\n if (!str.endsWith('/')) {\n return str + '/';\n }\n return str;\n}\n\nconst urls = []\nfor (const item of $input.first().json['Page URLs'].split(',')) {\n urls.push({ url: addTrailingSlash(item).trim()})\n}\n\nreturn urls;"
},
"typeVersion": 2
},
{
"id": "5ca54dbb-a1c3-467b-be2f-1331f83dd408",
"name": "Merge URLs",
"type": "n8n-nodes-base.merge",
"position": [
1760,
288
],
"parameters": {},
"typeVersion": 3.2
},
{
"id": "6de3aa8c-6f41-46b4-adea-ee8f77e8dec5",
"name": "Remove Duplicate URLs",
"type": "n8n-nodes-base.removeDuplicates",
"position": [
1904,
288
],
"parameters": {
"options": {}
},
"typeVersion": 2
},
{
"id": "13033722-6fe1-4b10-9739-5c858de5c1f1",
"name": "Loop Over Page URLs",
"type": "n8n-nodes-base.splitInBatches",
"position": [
2112,
288
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "59f936d1-d8f6-4eb0-b329-ffe9059859d3",
"name": "Extract Content",
"type": "n8n-nodes-base.html",
"position": [
2512,
192
],
"parameters": {
"options": {
"cleanUpText": true
},
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "content",
"cssSelector": "body",
"skipSelectors": "img"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "cdfdf6ea-7e45-4460-8a30-81f723dd0b27",
"name": "Wait 5 sec",
"type": "n8n-nodes-base.wait",
"position": [
2512,
384
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "63ff031a-d48b-43ca-b784-0be36215eb68",
"name": "Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
3104,
400
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "e196c8e3-6831-49b8-916a-cf6d2e466423",
"name": "Gemini Embeddings",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"position": [
2912,
400
],
"parameters": {
"modelName": "models/gemini-embedding-001"
},
"typeVersion": 1
},
{
"id": "4b0fcd8c-127e-4cf5-9177-a50ad8bd23e6",
"name": "Pinecone KnowledgeBase",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
2912,
192
],
"parameters": {
"mode": "insert",
"options": {
"clearNamespace": true
},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "supportbot",
"cachedResultName": "supportbot"
}
},
"typeVersion": 1.3
},
{
"id": "ed948a05-fe45-4aa4-988d-c20916d5b224",
"name": "Input Sitemap or page urls",
"type": "n8n-nodes-base.formTrigger",
"position": [
928,
432
],
"parameters": {
"options": {},
"formTitle": "Agent Knowledge Base Input",
"formFields": {
"values": [
{
"fieldLabel": "Sitemap URL",
"placeholder": "https://website.com/page-sitemap.xml"
},
{
"fieldType": "textarea",
"fieldLabel": "Page URLs",
"placeholder": "https://website.com/about, https://website.com/contact"
}
]
},
"formDescription": "This form is to input the page sitemap or pages of your website"
},
"typeVersion": 2.2
},
{
"id": "39c6786e-f724-4484-af6c-845f1829a0c8",
"name": "Switch",
"type": "n8n-nodes-base.switch",
"position": [
1072,
432
],
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "2af7e15b-2e56-40e5-addc-74bd0b4de214",
"operator": {
"type": "string",
"operation": "notEmpty",
"singleValue": true
},
"leftValue": "={{ $json['Page URLs'] }}",
"rightValue": ""
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "02899ab6-0c0b-4c0f-89ad-ec5787da36eb",
"operator": {
"type": "string",
"operation": "endsWith"
},
"leftValue": "={{ $json['Sitemap URL'] }}",
"rightValue": "xml"
}
]
}
}
]
},
"options": {
"allMatchingOutputs": true
}
},
"typeVersion": 3.2
},
{
"id": "d8423b14-305b-49f4-a158-8e472499c11c",
"name": "Decodo",
"type": "@decodo/n8n-nodes-decodo.decodo",
"position": [
2320,
384
],
"parameters": {
"url": "={{ $json.url }}"
},
"typeVersion": 1
},
{
"id": "34f9ca84-ca77-4abf-89c0-514039b39b99",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
1296,
848
],
"parameters": {
"mode": "webhook",
"public": true,
"options": {
"allowedOrigins": "*",
"loadPreviousSession": "memory"
}
},
"typeVersion": 1.4
},
{
"id": "2bee1969-2704-4ff1-b485-2113370fb633",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
1440,
1120
],
"parameters": {
"contextWindowLength": 10
},
"typeVersion": 1.3
},
{
"id": "c8a5e2f3-89fc-465b-8c20-458fd352db73",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1712,
848
],
"parameters": {
"options": {}
},
"typeVersion": 3.1
},
{
"id": "ce663f8f-2e39-4620-9c84-e0221964ba3b",
"name": "Simple Memory1",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
1808,
1120
],
"parameters": {
"contextWindowLength": 10
},
"typeVersion": 1.3
},
{
"id": "243df850-90cf-4e30-a881-e3743cf4d22a",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1648,
1120
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "551156bb-949a-40a4-b519-b266b9485434",
"name": "Pinecone Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
2000,
1120
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "supportbot",
"cachedResultName": "supportbot"
},
"toolDescription": "Business information related to a business"
},
"typeVersion": 1.3
},
{
"id": "5414b57b-dcf6-4712-9910-858d636e4aa1",
"name": "Embeddings Google Gemini",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"position": [
2112,
1280
],
"parameters": {
"modelName": "models/embedding-001"
},
"typeVersion": 1
},
{
"id": "8ddfb5ba-461d-47d0-abf0-4ceb018c8832",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
2048,
112
],
"parameters": {
"color": 6,
"width": 624,
"height": 512,
"content": "## Extracting HTML from a web page using Decodo with JS Rendering"
},
"typeVersion": 1
},
{
"id": "3c04259f-d8e7-4592-8009-e0ac99246683",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
2688,
112
],
"parameters": {
"color": 2,
"width": 624,
"height": 512,
"content": "## Saving Content in Pinecone Vector Database"
},
"typeVersion": 1
},
{
"id": "6176a797-96fe-4ca2-88e6-92e15ebc5ea5",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1216,
112
],
"parameters": {
"color": 5,
"width": 816,
"height": 512,
"content": "## Processing Page URLs"
},
"typeVersion": 1
},
{
"id": "5a8065c6-3f6b-4637-b0fe-a85e778189f1",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1216,
736
],
"parameters": {
"color": 5,
"width": 1072,
"height": 720,
"content": "## Chatbot which can be embedded to any website, will show on the bottom right side, and will work perfectly"
},
"typeVersion": 1
}
],
"connections": {
"Decodo": {
"main": [
[
{
"node": "Wait 5 sec",
"type": "main",
"index": 0
}
]
]
},
"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
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "When chat message received",
"type": "ai_memory",
"index": 0
}
]
]
},
"Simple Memory1": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"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": "Decodo",
"type": "main",
"index": 0
}
]
]
},
"Pinecone Vector Store": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Remove Duplicate URLs": {
"main": [
[
{
"node": "Loop Over Page URLs",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Google Gemini": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Input Sitemap or page urls": {
"main": [
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Categories: Business Automation, Customer Support, AI, Knowledge Management
Source: https://n8n.io/workflows/12146/ — 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.
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
Pinecone Vector Store, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +12
This template is a complete, hands-on tutorial for building a RAG (Retrieval-Augmented Generation) pipeline. In simple terms, you'll teach an AI to become an expert on a specific topic—in this case, t
Memory Buffer Window, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +7
This workflow helps users find the most relevant n8n templates using AI.
HTTP Request, Qdrant Vector Store, Google Gemini Embeddings +5
My workflow 3. Uses formTrigger, splitInBatches, lmChatGoogleGemini, httpRequest. Event-driven trigger; 36 nodes.
Form Trigger, Google Gemini Chat, HTTP Request +10
This n8n workflow implements a fully automated Retrieval-Augmented Generation (RAG) pipeline powered by Google Drive, OpenAI embeddings, and Pinecone.
Pinecone Vector Store, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10