This workflow follows the Agent → Chainllm 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": "3Lih0LVosR8dZbla",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Create AI-Ready Vector Datasets for LLMs with Bright Data, Gemini & Pinecone",
"tags": [
{
"id": "Kujft2FOjmOVQAmJ",
"name": "Engineering",
"createdAt": "2025-04-09T01:31:00.558Z",
"updatedAt": "2025-04-09T01:31:00.558Z"
},
{
"id": "ZOwtAMLepQaGW76t",
"name": "Building Blocks",
"createdAt": "2025-04-13T15:23:40.462Z",
"updatedAt": "2025-04-13T15:23:40.462Z"
},
{
"id": "ddPkw7Hg5dZhQu2w",
"name": "AI",
"createdAt": "2025-04-13T05:38:08.053Z",
"updatedAt": "2025-04-13T05:38:08.053Z"
}
],
"nodes": [
{
"id": "0a468953-e348-420e-a6b3-c55fb20d3cbf",
"name": "When clicking \u2018Test workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
200,
-710
],
"parameters": {},
"typeVersion": 1
},
{
"id": "3725e480-246f-4f32-b0a7-b946cacbe830",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1236,
-60
],
"parameters": {
"text": "=Format the below search result\n\n{{ $json.output.search_result }}",
"options": {},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.8
},
{
"id": "30a12b8e-02f5-4b2e-bf9f-20fd9658405e",
"name": "Pinecone Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
1628,
-10
],
"parameters": {
"mode": "insert",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "hacker-news",
"cachedResultName": "hacker-news"
}
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "1738dea6-fa4f-4a8d-a6fb-2f01feb1a6d5",
"name": "Embeddings Google Gemini",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"position": [
1612,
210
],
"parameters": {
"modelName": "models/text-embedding-004"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "e6443541-de71-4d26-ad58-d7c72868a190",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1760,
220
],
"parameters": {
"options": {},
"jsonData": "={{ $('Information Extractor with Data Formatter').item.json.output.search_result }}",
"jsonMode": "expressionData"
},
"typeVersion": 1
},
{
"id": "09ffc8cd-096f-47fe-937d-f8ab4fb41266",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1820,
410
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "90cc9aa4-0931-4c52-8734-e4e0de820205",
"name": "Google Gemini Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1240,
160
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "1090a4af-7e5d-446b-a537-3afe48cd4909",
"name": "Google Gemini Chat Model2",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
948,
-340
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "324c530c-0a03-411e-acb0-d82e9dc635cf",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
948,
160
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "3226a2d6-ade1-4d6a-95c5-0be4d787a947",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1400,
160
],
"parameters": {
"jsonSchemaExample": "[{\n\t\"id\": \"<string>\",\n\t\"title\": \"<string>\",\n \"summary\": \"<string>\",\n \"keywords\": [\"\"],\n \"topics\": [\"\"]\n}]"
},
"typeVersion": 1.2
},
{
"id": "a739a314-900a-4ef7-9cc2-1b65374e2e05",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
40,
-360
],
"parameters": {
"width": 480,
"height": 220,
"content": "## Note\nPlease make sure to set the URL for web crawling. \n\nWeb-Unlocker Product is being utilized for performing the web scrapping. \n\nThis workflow is utilizing the Basic LLM Chain, Information Extraction with the AI Agents for formatting, extracting and persisting the response in PineCone Vector Database"
},
"typeVersion": 1
},
{
"id": "3dca6d46-c423-4fb5-a6e4-c2aa2852d51c",
"name": "Set Fields - URL and Webhook URL",
"type": "n8n-nodes-base.set",
"notes": "Set the URL which you are interested to scrap the data",
"position": [
420,
-710
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "1c132dd6-31e4-453b-a8cf-cad9845fe55b",
"name": "url",
"type": "string",
"value": "https://news.ycombinator.com?product=unlocker&method=api"
},
{
"id": "90f3272b-d13d-44e2-8b4c-0943648cfce9",
"name": "webhook_url",
"type": "string",
"value": "https://webhook.site/bc804ce5-4a45-4177-a68a-99c80e5c86e6"
}
]
}
},
"notesInFlow": true,
"typeVersion": 3.4
},
{
"id": "216a3261-a398-484c-9bf4-ca5966b829b6",
"name": "Make a web request",
"type": "n8n-nodes-base.httpRequest",
"position": [
640,
-260
],
"parameters": {
"url": "https://api.brightdata.com/request",
"method": "POST",
"options": {},
"sendBody": true,
"sendHeaders": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "zone",
"value": "web_unlocker1"
},
{
"name": "url",
"value": "={{ $json.url }}"
},
{
"name": "format",
"value": "raw"
}
]
},
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{}
]
}
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "0c74e21c-3007-4297-b6ab-8ee17f4c6436",
"name": "Structured JSON Data Formatter",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
860,
-560
],
"parameters": {
"text": "=Format the below response and produce a textual data. Output the response as per the below JSON schema.\n\nHere's the input: {{ $json.data }}\nHere's the JSON schema: \n\n[{\n \"rank\": { \"type\": \"integer\" },\n \"title\": { \"type\": \"string\" },\n \"site\": { \"type\": \"string\" },\n \"points\": { \"type\": \"integer\" },\n \"user\": { \"type\": \"string\" },\n \"age\": { \"type\": \"string\" },\n \"comments\": { \"type\": \"string\" }\n}]",
"messages": {
"messageValues": [
{
"message": "You are an expert data formatter"
}
]
},
"promptType": "define"
},
"typeVersion": 1.6
},
{
"id": "012d4bb0-2b58-47cd-9cea-b4e0dced9082",
"name": "Webhook for structured data",
"type": "n8n-nodes-base.httpRequest",
"position": [
1314,
-860
],
"parameters": {
"url": "={{ $json.webhook_url }}",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "response",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "93b35e5e-6f52-4aeb-8f1b-39cc495beefe",
"name": "Webhook for structured AI agent response",
"type": "n8n-nodes-base.httpRequest",
"position": [
1750,
-660
],
"parameters": {
"url": "={{ $json.webhook_url }}",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "response",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "251b4251-255c-48c6-999b-02227fa2de9b",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
800,
-620
],
"parameters": {
"width": 360,
"height": 420,
"content": "## AI Data Formatter\n"
},
"typeVersion": 1
},
{
"id": "f62463cd-6be3-4942-a636-de980a3154b4",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1560,
-160
],
"parameters": {
"color": 4,
"width": 520,
"height": 720,
"content": "## Vector Database Persistence\n"
},
"typeVersion": 1
},
{
"id": "ad20cc91-766a-4a57-be54-6f0d09a784eb",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1260,
-920
],
"parameters": {
"color": 3,
"width": 680,
"height": 440,
"content": "## Webhook Notification Handler\n"
},
"typeVersion": 1
},
{
"id": "37ab5c0f-d36e-4131-844d-20a22d3f2861",
"name": "Information Extractor with Data Formatter",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
860,
-60
],
"parameters": {
"text": "={{ $json.data }}",
"options": {
"systemPromptTemplate": "You are an expert HTML extractor. Your job is to analyze the search result and extract the content as a collection on items"
},
"attributes": {
"attributes": [
{
"name": "search_result",
"description": "Search Response"
}
]
}
},
"typeVersion": 1
},
{
"id": "e04e189a-8ba9-4ef4-9a49-fc13daf00828",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
800,
-160
],
"parameters": {
"color": 5,
"width": 720,
"height": 720,
"content": "## Data Extraction/Formatting with the AI Agent\n"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "799fb406-600d-45a5-b926-24b8844f33a5",
"connections": {
"AI Agent": {
"main": [
[
{
"node": "Pinecone Vector Store",
"type": "main",
"index": 0
},
{
"node": "Webhook for structured AI agent response",
"type": "main",
"index": 0
}
]
]
},
"Make a web request": {
"main": [
[
{
"node": "Structured JSON Data Formatter",
"type": "main",
"index": 0
},
{
"node": "Information Extractor with Data Formatter",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Pinecone Vector Store": {
"ai_tool": [
[]
]
},
"Embeddings Google Gemini": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Information Extractor with Data Formatter",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "AI Agent",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Google Gemini Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model2": {
"ai_languageModel": [
[
{
"node": "Structured JSON Data Formatter",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured JSON Data Formatter": {
"main": [
[
{
"node": "Webhook for structured data",
"type": "main",
"index": 0
}
]
]
},
"Set Fields - URL and Webhook URL": {
"main": [
[
{
"node": "Make a web request",
"type": "main",
"index": 0
},
{
"node": "Webhook for structured data",
"type": "main",
"index": 0
},
{
"node": "Webhook for structured AI agent response",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "Set Fields - URL and Webhook URL",
"type": "main",
"index": 0
}
]
]
},
"Information Extractor with Data Formatter": {
"main": [
[
{
"node": "AI Agent",
"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.
googlePalmApihttpHeaderAuthpineconeApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
Transform raw web data into structured vector datasets ready for fine-tuning large language models, saving hours of manual preparation and enabling faster AI model development. This workflow suits data scientists and AI developers building custom LLMs who need high-quality embeddings from diverse sources. It leverages Bright Data to scrape and collect content, then uses Google Gemini to generate embeddings stored in Pinecone, with the key step being the recursive text splitting that ensures optimal chunking for accurate vectorisation.
Use this workflow when preparing datasets from web-scraped articles or documents for LLM training, especially in research or product prototyping phases. Avoid it for real-time inference or non-text data like images, where specialised tools are better. Common variations include swapping Bright Data for RSS feeds or integrating additional cleaning nodes for noisy sources like social media.
About this workflow
Create AI-Ready Vector Datasets for LLMs with Bright Data, Gemini & Pinecone. Uses manualTrigger, agent, vectorStorePinecone, embeddingsGoogleGemini. Event-driven trigger; 21 nodes.
Source: https://github.com/Zie619/n8n-workflows — 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.
Api Schema Extractor. Uses manualTrigger, httpRequest, splitOut, textSplitterRecursiveCharacterTextSplitter. Event-driven trigger; 88 nodes.
HTTP Request, Text Splitter Recursive Character Text Splitter, Document Default Data Loader +9
Wait Splitout. Uses manualTrigger, httpRequest, splitOut, textSplitterRecursiveCharacterTextSplitter. Event-driven trigger; 88 nodes.
HTTP Request, Text Splitter Recursive Character Text Splitter, Document Default Data Loader +9
This workflow automates the process of discovering and extracting APIs from various services, followed by generating custom schemas. It works in three distinct stages: research, extraction, and schema
HTTP Request, Text Splitter Recursive Character Text Splitter, Document Default Data Loader +9
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
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