This workflow follows the Chainllm → OpenAI Embeddings 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 →
{
"name": "N8N Expert",
"nodes": [
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "ee2bcd57-3b4c-43f9-b4b7-3a25687b9a68",
"name": "query",
"value": "={{ $json.body.query }}",
"type": "string"
},
{
"id": "63f23e51-af2b-47c4-a288-5abaf9b6c357",
"name": "user_id",
"value": "={{ $json.body.user_id }}",
"type": "string"
},
{
"id": "b97a3670-8a87-481b-8695-db44624be7d8",
"name": "request_id",
"value": "={{ $json.body.request_id }}",
"type": "string"
},
{
"id": "7d3fa06d-08f7-4517-b9c5-3c46ff476f55",
"name": "session_id",
"value": "={{ $json.body.session_id }}",
"type": "string"
}
]
},
"options": {}
},
"id": "f4a396a1-0e77-4ca8-9150-d27c4af2ee77",
"name": "Edit Fields",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
640,
640
]
},
{
"parameters": {
"model": "text-embedding-3-small",
"options": {}
},
"id": "3f7da8d5-e9d3-4c0b-9648-f23cdfb0dbfa",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1,
"position": [
1160,
820
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"fieldsToAggregate": {
"fieldToAggregate": [
{
"fieldToAggregate": "text",
"renameField": true,
"outputFieldName": "workflow_ids"
}
]
},
"options": {}
},
"id": "aad41c91-c6d6-48c3-9e43-346a5069c667",
"name": "Aggregate",
"type": "n8n-nodes-base.aggregate",
"typeVersion": 1,
"position": [
1720,
640
]
},
{
"parameters": {
"model": "gpt-4o",
"options": {}
},
"id": "cf371ddb-1521-4e9c-813c-5e5c7fdbce44",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
1480,
560
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "getAll",
"tableId": "workflows",
"limit": 5,
"filterType": "string",
"filterString": "=workflow_id=in.{{ $json.query_string }}"
},
"id": "16abcadb-db84-4be0-821d-725cd53ac196",
"name": "Supabase",
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
2340,
400
],
"alwaysOutputData": true,
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"fieldsToSummarize": {
"values": [
{
"aggregation": "concatenate",
"field": "workflow_ids"
}
]
},
"options": {}
},
"id": "1e00bcc2-ea78-4b35-8c81-2ee625c7d5a2",
"name": "Summarize",
"type": "n8n-nodes-base.summarize",
"typeVersion": 1,
"position": [
1940,
400
]
},
{
"parameters": {
"jsCode": "// Loop over input items and add a new field called 'myNewField' to the JSON of each one\nfor (const item of $input.all()) {\n item.json.query_string = $('Summarize').first().json.concatenated_workflow_ids.replaceAll(\"\\\"\", \"\").replaceAll(\"[\", \"(\").replaceAll(\"]\", \")\");\n}\n\nreturn $input.all();"
},
"id": "64627fc4-d2e5-42d4-a0b5-3bcd931d24ab",
"name": "Code",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2140,
640
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "b5eaa2a2-a6bc-40ab-af5e-baa8a5dda1a7",
"name": "output",
"value": "={{ $('Aggregate1').item.json.data.length ? \"Here are the recommended workflows to use as an example for you:\" : \"No related workflows found at this time. Please try a different prompt.\" }}",
"type": "string"
}
]
},
"includeOtherFields": true,
"options": {}
},
"id": "4a14b34b-ecb6-4d43-836c-ceec97f626cd",
"name": "Edit Fields1",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
2720,
420
]
},
{
"parameters": {
"tableId": "messages",
"fieldsUi": {
"fieldValues": [
{
"fieldId": "session_id",
"fieldValue": "={{ $('Edit Fields').first().json.session_id }}"
},
{
"fieldId": "message",
"fieldValue": "={{ {\n\"type\": \"ai\",\n\"content\": $json.output,\n\"data\": $json.data,\n\"additional_kwargs\": {},\n\"response_metadata\": {}\n} }}"
}
]
}
},
"id": "b9f99ec8-96df-45ff-9d41-c78328889a1e",
"name": "Supabase1",
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
2920,
640
],
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"aggregate": "aggregateAllItemData",
"options": {}
},
"id": "df095f3f-9691-419e-aca6-c43eabe14de8",
"name": "Aggregate1",
"type": "n8n-nodes-base.aggregate",
"typeVersion": 1,
"position": [
2520,
640
]
},
{
"parameters": {
"respondWith": "allIncomingItems",
"options": {
"responseHeaders": {
"entries": [
{
"name": "X-n8n-Signature",
"value": "EvtIS^EBVISeie6svB@6ev"
}
]
}
}
},
"id": "59550b57-845f-49ef-80c8-b14eae1d2d5a",
"name": "Respond to Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
3320,
660
]
},
{
"parameters": {
"promptType": "define",
"text": "=Here is a n8n workflow descriptions:\n\n{{ $json.document.pageContent }}\n\nYour job is to identify if the workflow is relevant to the user query which is:\n\n{{ $('Edit Fields').first().json.query }}\n\nOutput the workflow ID if the workflow relates to the user query. Otherwise, output -1. ONLY ever output a number, nothing else. You will always output the workflow ID or -1.\n\nThe workflow ID is: {{ $json.document.metadata.workflow_id }}\n\nThe workflow ID or -1 if the workflow doesn't relate to the user query:"
},
"id": "4c49b44d-b707-41ef-8577-4939df2bc2db",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.4,
"position": [
1360,
400
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "b5eaa2a2-a6bc-40ab-af5e-baa8a5dda1a7",
"name": "output",
"value": "={{ $('Edit Fields1').item.json.output }}",
"type": "string"
},
{
"id": "392160a6-53a6-4b7e-9c43-75571172c590",
"name": "data",
"value": "={{ $('Edit Fields1').item.json.data}}",
"type": "string"
}
]
},
"options": {}
},
"id": "416ee827-a9a5-4461-8b77-798b7ecaea50",
"name": "Edit Fields2",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
3120,
420
]
},
{
"parameters": {
"tableId": "messages",
"fieldsUi": {
"fieldValues": [
{
"fieldId": "session_id",
"fieldValue": "={{ $json.session_id }}"
},
{
"fieldId": "message",
"fieldValue": "={{ {\n\"type\": \"human\",\n\"content\": $json.query,\n\"additional_kwargs\": {},\n\"response_metadata\": {}\n} }}"
}
]
}
},
"id": "79873137-cbdb-4c90-9dc6-adbcb516f6de",
"name": "Supabase2",
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
840,
420
],
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "load",
"tableName": {
"__rl": true,
"value": "workflows",
"mode": "list",
"cachedResultName": "workflows"
},
"prompt": "={{ $('Edit Fields').item.json.query }}",
"topK": 5,
"options": {
"queryName": "match_summaries"
}
},
"id": "ee10e7a4-da98-4775-b641-310ce79110a4",
"name": "Supabase Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"typeVersion": 1,
"position": [
1020,
640
],
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "## The n8n Expert Agent helps you find and understand n8n automation workflows. Simply describe what you're trying to automate, and the agent will recommend relevant workflows to help you get started.\n\nAuthor: [Cole Medin](https://www.youtube.com/@ColeMedin)\n\n## For example:\n\n### User: \"I need to automatically post tweets when new blog posts are published\"\n### Agent: Here are some recommended workflows to help you get started:\n- WordPress to Twitter Auto-Poster\n- Blog RSS Feed to Social Media\n- Content Distribution Workflow\nThe agent analyzes your request and provides matching workflows from its knowledge base, along with explanations of how to implement and customize them for your needs.",
"height": 502.790697674419,
"width": 651.0139534883727,
"color": 6
},
"id": "1ac32a2f-f121-4b7c-bfb6-b90056c9d6bd",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-260,
360
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "invoke-n8n-expert",
"authentication": "headerAuth",
"responseMode": "responseNode",
"options": {}
},
"id": "90236e22-385a-49ba-8d5c-263a60a82f33",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
460,
460
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "#### This agent is in beta, especially as its knowledgebase grows! Workflows won't always be super related to your query and sometimes it won't have any. This agent will also involve into a conversational agent eventually to help you build n8n workflows!",
"height": 111.41953488372111,
"width": 648.3795348837208
},
"id": "934e70b5-3825-4bb7-91e3-0fa786bf88e8",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-260,
900
]
}
],
"connections": {
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Edit Fields": {
"main": [
[
{
"node": "Supabase2",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Supabase": {
"main": [
[
{
"node": "Aggregate1",
"type": "main",
"index": 0
}
]
]
},
"Aggregate": {
"main": [
[
{
"node": "Summarize",
"type": "main",
"index": 0
}
]
]
},
"Summarize": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Code": {
"main": [
[
{
"node": "Supabase",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields1": {
"main": [
[
{
"node": "Supabase1",
"type": "main",
"index": 0
}
]
]
},
"Supabase1": {
"main": [
[
{
"node": "Edit Fields2",
"type": "main",
"index": 0
}
]
]
},
"Aggregate1": {
"main": [
[
{
"node": "Edit Fields1",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields2": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"Supabase2": {
"main": [
[
{
"node": "Supabase Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Supabase Vector Store": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "9cb778c5-1d8e-4af0-a6fd-8107eb8069ef",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "e1rZ3MNMH9g4i1Yw",
"tags": [
{
"createdAt": "2024-12-09T14:35:20.507Z",
"updatedAt": "2024-12-09T14:35:20.507Z",
"id": "wBUwbX8AS8QmBHOC",
"name": "studio-prod"
}
]
}
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.
httpHeaderAuthopenAiApisupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
N8N Expert. Uses embeddingsOpenAi, lmChatOpenAi, supabase, chainLlm. Webhook trigger; 18 nodes.
Source: https://github.com/DPabloFlores/ottomator-agents/blob/main/n8n-expert/N8N_Expert_Agent.json — 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.
Hi! I’m Amanda, a creator of intelligent automations using n8n and Make. I’ve been building AI-powered workflows for over 2 years, always focused on usability and innovation. This one here is very spe
OpenAI Chat, Redis, OpenAI +11
• Create a Google Drive folder to watch. • Connect your Google Drive account in n8n and authorize access. • Point the Google Drive Trigger node to this folder (new/modified files trigger the flow).
Agent, Chat Trigger, Memory Buffer Window +14
HeyDinastia. Uses executeCommand, httpRequest, youTube, postgres. Webhook trigger; 66 nodes.
Execute Command, HTTP Request, YouTube +15
This workflow automates customer support across multiple channels (Email, Live Chat, WhatsApp, Slack, Discord) using AI-powered responses enhanced with Retrieval Augmented Generation (RAG) and your pr
Email Read Imap, WhatsApp Trigger, Slack Trigger +12
Indoor Farming Agent. Uses lmChatOpenAi, documentDefaultDataLoader, embeddingsOpenAi, toolVectorStore. Webhook trigger; 36 nodes.
OpenAI Chat, Document Default Data Loader, OpenAI Embeddings +16