David Roberts This workflow corresponds to n8n.io template #1960 — 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "1f2bb917-6d65-4cfa-9474-fc3b19a8c3bd",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-440,
-120
],
"parameters": {
"color": 7,
"width": 918,
"height": 627,
"content": "### Load data into database\nFetch file from Google Drive, split it into chunks and insert into Pinecone index"
},
"typeVersion": 1
},
{
"id": "eabbc944-5b62-4959-8ea4-879f28e19ab8",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
740,
-120
],
"parameters": {
"color": 7,
"width": 534,
"height": 627,
"content": "### Chat with database\nEmbed the incoming chat message and use it retrieve relevant chunks from the vector store. These are passed to the model to formulate an answer "
},
"typeVersion": 1
},
{
"id": "ab577f4d-8906-4e0c-bc62-e8a4b2610551",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-720,
240
],
"parameters": {
"height": 264.61498034081166,
"content": "## Try me out\n1. In Pinecone, create an index with 1536 dimensions and select it in *both* Pinecone nodes\n2. Click 'test workflow' at the bottom of the canvas to load data into the vector store\n3. Click 'chat' at the bottom of the canvas to ask questions about the data"
},
"typeVersion": 1
},
{
"id": "6f074b77-3441-4026-a13a-ed891a1c959b",
"name": "When clicking 'Test Workflow' button",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-700,
-20
],
"parameters": {},
"typeVersion": 1
},
{
"id": "0a6f8b88-9c62-4e3e-82cb-a7028bdcac45",
"name": "Pinecone Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
80,
-20
],
"parameters": {
"mode": "insert",
"options": {
"clearNamespace": true
},
"pineconeIndex": {
"__rl": true,
"mode": "id",
"value": "test-index"
}
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "ae426fdc-0d58-46a6-bfe6-0f25c0e70cf1",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
560,
-20
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "9388b413-f133-45a6-8066-cf71c0fb826c",
"name": "Question & Answer",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
800,
-20
],
"parameters": {
"options": {}
},
"typeVersion": 1.8
},
{
"id": "c50e8f9b-8254-495e-9e13-62f42d22c9b0",
"name": "Set Google Drive file URL",
"type": "n8n-nodes-base.set",
"position": [
-380,
-20
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "d08ef1f5-932b-4bbb-bb02-0cbdff26a636",
"name": "file_url",
"type": "string",
"value": "https://drive.google.com/file/d/11Koq9q53nkk0F5Y8eZgaWJUVR03I4-MM/view"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "d97920ad-6b36-4981-8b9d-9d470b5c769a",
"name": "Google Drive",
"type": "n8n-nodes-base.googleDrive",
"position": [
-180,
-20
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "url",
"value": "={{ $json.file_url }}"
},
"options": {},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "742beb54-8b89-49a3-afe5-fd7e73b37044",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
180,
200
],
"parameters": {
"options": {},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "f75e31e9-f752-45d1-bc44-75097ec85ce6",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
260,
320
],
"parameters": {
"options": {},
"chunkSize": 3000,
"chunkOverlap": 200
},
"typeVersion": 1
},
{
"id": "034a2b72-f728-4978-bc18-c950f0f2c24c",
"name": "Embeddings OpenAI1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1000,
320
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "bac883c8-4c1f-466b-b20f-d0fdf6acfc42",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
60,
200
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "7b6cdba3-906b-44dd-85be-1d515337972b",
"name": "Pinecone Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
920,
200
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "bitcoin_paper",
"pineconeIndex": {
"__rl": true,
"mode": "id",
"value": "test-index"
},
"toolDescription": "Call this tool to retrieve facts from the bitcoin whitepaper",
"includeDocumentMetadata": false
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "cf9d18a9-4c1e-4a67-8149-961b3eee374d",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
800,
200
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
}
],
"connections": {
"Google Drive": {
"main": [
[
{
"node": "Pinecone Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Question & Answer",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Pinecone Vector Store1": {
"ai_tool": [
[
{
"node": "Question & Answer",
"type": "ai_tool",
"index": 0
}
]
]
},
"Set Google Drive file URL": {
"main": [
[
{
"node": "Google Drive",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Question & Answer",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"When clicking 'Test Workflow' button": {
"main": [
[
{
"node": "Set Google Drive file URL",
"type": "main",
"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.
googleDriveOAuth2ApiopenAiApipineconeApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to…
Source: https://n8n.io/workflows/1960/ — 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.
Your AI workforce is ready. Are you?
This advanced n8n workflow automates the full lead enrichment, qualification, and personalized outreach process tailored specifically for the B2B real estate sector. Integrating top platforms like Api
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
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
Chat with docs - 5minAI New version. Uses httpRequest, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Event-driven trigger; 62 nodes.