AI Incarnation This workflow corresponds to n8n.io template #3192 — 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 →
{
"id": "lC8xkfCSTjIiUhpk",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Google Drive Automation",
"tags": [],
"nodes": [
{
"id": "e7769ee7-a247-426e-b792-c095597ada54",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
320,
700
],
"parameters": {
"text": "={{ $json.prompt }}",
"options": {
"systemMessage": "You are a knowledgeable and helpful assistant. Respond with clear, concise, and detailed answers formatted in markdown. Use proper markdown formatting including headings, bullet points, numbered lists, code blocks, and other structures as needed to improve readability and clarity."
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "72ca46ad-891f-42f2-81d7-00e04e1c6f5f",
"name": "Monitor Google Drive for New Files",
"type": "n8n-nodes-base.googleDriveTrigger",
"position": [
-520,
-240
],
"parameters": {
"event": "fileCreated",
"options": {},
"pollTimes": {
"item": [
{}
]
},
"triggerOn": "specificFolder",
"folderToWatch": {
"__rl": true,
"mode": "list",
"value": "1RQvAHIw8cQbtwI9ZvdVV0k0x6TM6HZwP",
"cachedResultUrl": "https://drive.google.com/drive/folders/1RQvAHIw8cQbtwI9ZvdVV0k0x6TM6HZwP",
"cachedResultName": "RAG_Files"
}
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "03e9dc61-bdba-49d7-859e-73b8adebae41",
"name": "Download File from Google Drive",
"type": "n8n-nodes-base.googleDrive",
"position": [
-300,
-240
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.id }}"
},
"options": {},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "782fc162-0c3f-40fc-af92-455c1250ede0",
"name": "Extract PDF Content",
"type": "n8n-nodes-base.extractFromFile",
"position": [
-80,
-240
],
"parameters": {
"options": {},
"operation": "pdf"
},
"typeVersion": 1
},
{
"id": "b8da9cff-756b-419e-b39a-4ad1020092d0",
"name": "Insert Document into Pinecone Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
360,
-240
],
"parameters": {
"mode": "insert",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "n8n-rag-demo",
"cachedResultName": "n8n-rag-demo"
}
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "f5b93646-b466-4cd7-aec9-6fae62023fa3",
"name": "Generate Document Embeddings (Google Gemini)",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"position": [
260,
20
],
"parameters": {
"modelName": "models/text-embedding-004"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "b5277663-3120-4614-85e3-f7dc05c4e1c2",
"name": "Clean and Normalize PDF Text",
"type": "n8n-nodes-base.code",
"position": [
140,
-240
],
"parameters": {
"jsCode": "const rawData = $json[\"text\"];\nconst cleanedData = rawData\n .replace(/(\\r\\n|\\n|\\r)/gm, \" \") // remove line breaks\n .trim() // remove extra spaces\n .replace(/[^\\w\\s]/gi, \"\"); // remove special characters\nreturn { cleanedData };\n"
},
"typeVersion": 2
},
{
"id": "68aa5515-6b58-4e98-ab08-4d9516e1f2a3",
"name": "Load Document Data for Processing",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
480,
20
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "3f463338-c692-4b7b-a888-8c00d190c441",
"name": "Split Document Text into Chunks",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
380,
240
],
"parameters": {
"options": {},
"chunkSize": 3000,
"chunkOverlap": 300
},
"typeVersion": 1
},
{
"id": "9c4a7ec9-0808-443f-9e12-9ec12c7288b9",
"name": "Chat Message Trigger",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-520,
700
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "ee62efc9-60b2-40ec-a10c-8897d24b1429",
"name": "Retrieve Relevant Documents from Pinecone",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
-260,
700
],
"parameters": {
"mode": "load",
"prompt": "={{ $json.chatInput }}",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "n8n-rag-demo",
"cachedResultName": "n8n-rag-demo"
}
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "8d479b6b-3c87-40c6-8a68-4390e6bafac8",
"name": "Generate Query Embeddings (Google Gemini)",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"position": [
-280,
940
],
"parameters": {
"modelName": "models/text-embedding-004"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "f521d243-1b62-4bc5-972d-736c65c48818",
"name": "Generate Chat Prompt with Context",
"type": "n8n-nodes-base.code",
"position": [
100,
700
],
"parameters": {
"jsCode": "const userQuery = $('Chat Message Trigger').first().json.chatInput\n// Retrieve the user query from the previous node output.\n// Assuming the Pinecone node has passed an array of items where each item has a document and score:\nlet documents = items.map(item => {\n return {\n pageContent: item.json.document.pageContent,\n score: item.json.score\n };\n});\n\n// Sort the documents by their score in descending order.\ndocuments.sort((a, b) => b.score - a.score);\n\n// Pick the top 3 documents to use as context.\nconst topDocuments = documents.slice(0, 3);\n\n// Combine the top documents into one context string.\nconst contextContent = topDocuments\n .map((doc, index) => `Document ${index + 1}:\\n${doc.pageContent}`)\n .join(\"\\n\\n\");\n\n// Build the final prompt that combines the context with the user query.\nconst prompt = `Using the following context from documents:\\n\\n${contextContent}\\n\\nAnswer the following question:\\n${userQuery}\\n\\nAnswer:`;\n\n// Return the prompt so it can be passed to a Chat/AI node for further processing.\nreturn [{ json: { prompt } }];\n"
},
"typeVersion": 2
},
{
"id": "208057c8-8672-41d2-9c99-89e52856a742",
"name": "OpenRouter Chat Model Interface",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
280,
940
],
"parameters": {
"model": "google/gemini-2.0-flash-exp:free",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "43fd0dd9-5ec1-401a-b1c2-368b15c9f0db",
"connections": {
"Extract PDF Content": {
"main": [
[
{
"node": "Clean and Normalize PDF Text",
"type": "main",
"index": 0
}
]
]
},
"Chat Message Trigger": {
"main": [
[
{
"node": "Retrieve Relevant Documents from Pinecone",
"type": "main",
"index": 0
}
]
]
},
"Clean and Normalize PDF Text": {
"main": [
[
{
"node": "Insert Document into Pinecone Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Download File from Google Drive": {
"main": [
[
{
"node": "Extract PDF Content",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter Chat Model Interface": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Split Document Text into Chunks": {
"ai_textSplitter": [
[
{
"node": "Load Document Data for Processing",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Generate Chat Prompt with Context": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Load Document Data for Processing": {
"ai_document": [
[
{
"node": "Insert Document into Pinecone Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Monitor Google Drive for New Files": {
"main": [
[
{
"node": "Download File from Google Drive",
"type": "main",
"index": 0
}
]
]
},
"Generate Query Embeddings (Google Gemini)": {
"ai_embedding": [
[
{
"node": "Retrieve Relevant Documents from Pinecone",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Retrieve Relevant Documents from Pinecone": {
"main": [
[
{
"node": "Generate Chat Prompt with Context",
"type": "main",
"index": 0
}
]
]
},
"Generate Document Embeddings (Google Gemini)": {
"ai_embedding": [
[
{
"node": "Insert Document into Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googleDriveOAuth2ApigooglePalmApiopenRouterApipineconeApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This n8n template empowers IT support teams by automating document ingestion and instant query resolution through a conversational AI. It integrates Google Drive, Pinecone, and a Chat AI agent (using Google Gemini/OpenRouter) to transform static support documents into an…
Source: https://n8n.io/workflows/3192/ — 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 n8n template automatically classifies incoming emails (Sales, Support, Internal, Finance, Promotions) and routes them to a dedicated OpenAI LLM Agent for processing. Depending on the category, th
OpenAI, Gmail, Text Classifier +16
Automate Outreach Prospect automates finding, enriching, and messaging potential partners (like restaurants, malls, and bars) using Apify Google Maps scraping, Perplexity enrichment, OpenAI LLMs, Goog
@Devlikeapro/N8N Nodes Waha, Google Drive Trigger, @Apify/N8N Nodes Apify +14
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
Chat with docs - 5minAI New version. Uses httpRequest, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Event-driven trigger; 62 nodes.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10
I prepared a detailed guide that illustrates the entire process of building an AI agent using Supabase and Google Drive within N8N workflows.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10