Firecrawl This workflow corresponds to n8n.io template #13964 — 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": "pvB5795JWJtf6D0H",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Scrape and ingest web content into Pinecone with Firecrawl",
"tags": [],
"nodes": [
{
"id": "979bb858-9afc-4fbf-a2ed-c158f3b0a440",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1136,
-384
],
"parameters": {
"width": 432,
"height": 496,
"content": "> ## How it works\n> 1. A webhook receives a URL via POST request\n> 2. The URL is validated and normalized, returning a 422 error if invalid\n> 3. Firecrawl scrapes the page and converts it to clean markdown\n> 4. OpenAI generates 1536-dimensional vector embeddings from the content\n> 5. The content and embeddings are stored in Pinecone\n> 6. A built-in RAG chat agent lets you query the knowledge base using natural language, with Cohere reranking for better retrieval\n>\n> ## Setup steps\n> 1. Create a Pinecone index with the settings from the \"Pinecone setup\" sticky\n> 2. Add your Firecrawl API key\n> 3. Add your OpenAI API key (for embeddings)\n> 4. Add your OpenRouter API key (for the chat agent)\n> 5. Add your Cohere API key (for reranking)\n> 6. Activate the workflow and send a POST request with `{\"url\": \"https://example.com\"}` to the webhook\n"
},
"typeVersion": 1
},
{
"id": "c1cbef33-52b3-44dd-aa62-58f3fdecfc30",
"name": "Receive URL",
"type": "n8n-nodes-base.webhook",
"position": [
-1056,
144
],
"parameters": {
"path": "dedaa64a-3dc9-43ea-82ac-7fac034af0b2",
"options": {},
"httpMethod": "POST",
"responseMode": "responseNode"
},
"typeVersion": 2.1
},
{
"id": "79cfc235-c533-4595-999f-09f3b7fb48a2",
"name": "Validate and normalize URL",
"type": "n8n-nodes-base.code",
"onError": "continueErrorOutput",
"position": [
-832,
144
],
"parameters": {
"jsCode": "const body = $input.first().json.body;\nconst raw = body?.url?.trim();\n\nif (!raw) {\n return [{\n json: {\n status: 422,\n message: \"Missing 'url' field in request body.\"\n }\n }];\n}\n\n// Strip protocol and path to get clean domain\nconst domain = raw.replace(/^https?:\\/\\//i, \"\").replace(/\\/.*$/, \"\");\n\n// Validate domain format\nconst isValid = /^[a-zA-Z0-9]([a-zA-Z0-9\\-]{0,61}[a-zA-Z0-9])?(\\.[a-zA-Z]{2,})+$/.test(domain);\n\nif (!isValid) {\n throw new Error(`Invalid URL: \"${raw}\" is not a valid domain or URL.`);\n}\nreturn [{\n json: {\n status: 200,\n domain: domain,\n url: `https://${domain}`\n }\n}];"
},
"typeVersion": 2
},
{
"id": "fe4f2f6c-d6e6-4d68-9133-8cd90fed5a39",
"name": "Scrape page with Firecrawl",
"type": "@mendable/n8n-nodes-firecrawl.firecrawl",
"position": [
-464,
-32
],
"parameters": {
"url": "={{ $('Validate and normalize URL').item.json.url }}",
"operation": "scrape",
"scrapeOptions": {
"options": {
"formats": {
"format": [
{}
]
},
"headers": {}
}
},
"requestOptions": {}
},
"credentials": {
"firecrawlApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "4f1cbecc-a01a-4c22-abcd-8263cc633c97",
"name": "Return URL validation error",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
-608,
240
],
"parameters": {
"options": {
"responseKey": "={{ $json.error }}",
"responseCode": 422
}
},
"typeVersion": 1.5
},
{
"id": "1e0853a9-651e-4fa0-a60d-65d22cf8df9d",
"name": "Store embeddings in Pinecone",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
-256,
-32
],
"parameters": {
"mode": "insert",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "firecrawl",
"cachedResultName": "firecrawl"
}
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "d9e2f16a-ef0d-4879-adce-2ef72b758f7d",
"name": "Return ingestion result",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
112,
-32
],
"parameters": {
"options": {
"responseCode": 200
},
"respondWith": "json",
"responseBody": "={\n \"message\": \"Added {{$input.all().length}} items to Supabase\"\n}"
},
"executeOnce": true,
"typeVersion": 1.5
},
{
"id": "0bc6e04f-062a-4fde-9787-5d98ee68a67c",
"name": "Generate OpenAI embeddings",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-288,
160
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "f5ba03be-4e36-4868-a119-5f15a8180ede",
"name": "Load scraped content",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
-112,
160
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "url",
"value": "={{ $('Validate and normalize URL').item.json.url }}"
}
]
}
}
},
"typeVersion": 1.1
},
{
"id": "4beb288d-8c95-4fe2-8462-40d138c1771e",
"name": "Receive chat message",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-1056,
512
],
"parameters": {
"options": {}
},
"typeVersion": 1.4
},
{
"id": "af6c4d23-10ff-4911-98fb-6f1c3d4defe3",
"name": "Answer query from knowledge base",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-832,
512
],
"parameters": {
"options": {}
},
"typeVersion": 3.1
},
{
"id": "b29b726a-c5f6-4b4b-b9b3-800915ab0a86",
"name": "OpenRouter LLM",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
-928,
704
],
"parameters": {
"model": "anthropic/claude-sonnet-4.6",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "aeb8b2cf-d054-45f6-8416-c7ce3cd13564",
"name": "Chat memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-768,
704
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "23ca0f36-bf16-44d6-b7a3-b1d0ec5b984c",
"name": "Retrieve documents from Pinecone",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
-576,
688
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"useReranker": true,
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "firecrawl",
"cachedResultName": "firecrawl"
},
"toolDescription": "Retrieve data for the AI Agent."
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "f8a8894d-0c58-4702-b57b-633e9803974c",
"name": "Generate OpenAI embeddings1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-608,
864
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "5c098782-83ad-4fd4-bbbb-d1d85b3df6e7",
"name": "Rerank results with Cohere",
"type": "@n8n/n8n-nodes-langchain.rerankerCohere",
"position": [
-448,
880
],
"parameters": {},
"credentials": {
"cohereApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "8acd099c-3f48-454b-bcf3-e75a239178a9",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-688,
-384
],
"parameters": {
"color": 7,
"width": 272,
"height": 336,
"content": "> ## Pinecone setup\n> Your Pinecone index must use 1536 dimensions to match the `text-embedding-3-small` OpenAI model.\n>\n> 1. Go to your Pinecone console and open your index settings\n> 2. Select text-embedding-3-small as the embedding model\n> 3. Confirm these settings:\n>\n> | Setting | Value |\n> |---|---|\n> | Modality | Text |\n> | Vector type | Dense |\n> | Dimension | 1536 |\n> | Metric | cosine |"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"binaryMode": "separate",
"availableInMCP": false,
"executionOrder": "v1"
},
"versionId": "e7c154c2-1552-4ffb-91d2-a35ab1e7d1ee",
"connections": {
"Chat memory": {
"ai_memory": [
[
{
"node": "Answer query from knowledge base",
"type": "ai_memory",
"index": 0
}
]
]
},
"Receive URL": {
"main": [
[
{
"node": "Validate and normalize URL",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter LLM": {
"ai_languageModel": [
[
{
"node": "Answer query from knowledge base",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Load scraped content": {
"ai_document": [
[
{
"node": "Store embeddings in Pinecone",
"type": "ai_document",
"index": 0
}
]
]
},
"Receive chat message": {
"main": [
[
{
"node": "Answer query from knowledge base",
"type": "main",
"index": 0
}
]
]
},
"Generate OpenAI embeddings": {
"ai_embedding": [
[
{
"node": "Store embeddings in Pinecone",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Rerank results with Cohere": {
"ai_reranker": [
[
{
"node": "Retrieve documents from Pinecone",
"type": "ai_reranker",
"index": 0
}
]
]
},
"Scrape page with Firecrawl": {
"main": [
[
{
"node": "Store embeddings in Pinecone",
"type": "main",
"index": 0
}
]
]
},
"Validate and normalize URL": {
"main": [
[
{
"node": "Scrape page with Firecrawl",
"type": "main",
"index": 0
}
],
[
{
"node": "Return URL validation error",
"type": "main",
"index": 0
}
]
]
},
"Generate OpenAI embeddings1": {
"ai_embedding": [
[
{
"node": "Retrieve documents from Pinecone",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Store embeddings in Pinecone": {
"main": [
[
{
"node": "Return ingestion result",
"type": "main",
"index": 0
}
]
]
},
"Retrieve documents from Pinecone": {
"ai_tool": [
[
{
"node": "Answer query from knowledge base",
"type": "ai_tool",
"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.
cohereApifirecrawlApiopenAiApiopenRouterApipineconeApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
What this does
Source: https://n8n.io/workflows/13964/ — 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.
What this does
Supabase, @Mendable/N8N Nodes Firecrawl, Document Default Data Loader +7
WooriFisa. Uses agent, httpRequest, documentDefaultDataLoader, vectorStorePinecone. Scheduled trigger; 86 nodes.
Agent, HTTP Request, Document Default Data Loader +14
This intelligent chatbot leverages cutting-edge financial APIs and AI-driven analysis to deliver comprehensive stock research reports. Get instant access to professional-grade investment analysis that
Tool Think, Supabase Vector Store, OpenAI Embeddings +15
WooriFisa 최종. Uses memoryMongoDbChat, agent, httpRequest, documentDefaultDataLoader. Scheduled trigger; 68 nodes.
Memory Mongo Db Chat, Agent, HTTP Request +14
YouTube Agent. Uses supabase, agent, lmChatAnthropic, outputParserStructured. Webhook trigger; 56 nodes.
Supabase, Agent, Anthropic Chat +10