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 →
{
"name": "Open WebUI Agent Template",
"nodes": [
{
"parameters": {
"options": {}
},
"id": "405066b4-56f0-4a51-939c-a94c8067f8ef",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
-640,
560
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $json.body.sessionId }}"
},
"id": "573a013f-9f44-4356-82c1-02034a48d42f",
"name": "Postgres Chat Memory",
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"typeVersion": 1,
"position": [
-460,
560
],
"notesInFlow": false,
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "## AI Agent with Webhook for Open WebUI",
"height": 525,
"width": 1596,
"color": 6
},
"id": "f63e9ae3-6a93-44de-a202-90fd9349d84b",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-1560,
220
]
},
{
"parameters": {
"options": {}
},
"id": "4136a9a8-d005-4d87-9c0a-25d1ec0a9ffb",
"name": "Respond to Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
-200,
300
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "invoke-n8n-agent",
"authentication": "headerAuth",
"responseMode": "responseNode",
"options": {}
},
"id": "e78b6ddb-4734-4911-b291-5ddedaf05016",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
-1500,
380
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "web_search",
"description": "Call this tool to do an advanced web search based on a query you define.",
"workflowId": {
"__rl": true,
"value": "={{ $workflow.id }}",
"mode": "id"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {
"query": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('query', ``, 'string') }}"
},
"matchingColumns": [],
"schema": [
{
"id": "tool_type",
"displayName": "tool_type",
"required": false,
"defaultMatch": false,
"display": true,
"canBeUsedToMatch": true,
"type": "string",
"removed": true
},
{
"id": "query",
"displayName": "query",
"required": false,
"defaultMatch": false,
"display": true,
"canBeUsedToMatch": true,
"type": "string"
},
{
"id": "image_url",
"displayName": "image_url",
"required": false,
"defaultMatch": false,
"display": true,
"canBeUsedToMatch": true,
"type": "string",
"removed": true
}
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 2,
"position": [
-300,
560
],
"id": "41a56129-7449-4efb-9695-930e52f7b640",
"name": "Web Search Tool"
},
{
"parameters": {
"content": "## Example Agent Tool",
"height": 340,
"width": 680,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-640,
760
],
"id": "441ac286-7313-4c1f-b222-fc2fed3ec8a0",
"name": "Sticky Note7"
},
{
"parameters": {
"url": "=https://api.search.brave.com/res/v1/web/search?q={{ $('Tool Start').item.json.query }} }}&summary=1",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Accept",
"value": "application/json"
},
{
"name": "Accept-Encoding",
"value": "gzip"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-360,
860
],
"id": "e423a192-c546-42cd-9565-5f7982c7aa00",
"name": "Brave Web Search",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"workflowInputs": {
"values": [
{
"name": "query"
}
]
}
},
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1.1,
"position": [
-580,
860
],
"id": "4c89122b-b406-4141-bc3c-7e63dafd0968",
"name": "Tool Start"
},
{
"parameters": {
"url": "=https://api.search.brave.com/res/v1/summarizer/search?key={{ $json.summarizer.key }}&entity_info=1",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Accept",
"value": "application/json"
},
{
"name": "Accept-Encoding",
"value": "gzip"
}
]
},
"options": {}
},
"id": "067241db-a694-4709-a1f7-2d0a7e11223b",
"name": "Summarize Web Research",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-160,
860
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "f5ebbd4f-6549-4a31-b3f8-eee7634dc439",
"leftValue": "={{ $json.body.sessionId }}",
"rightValue": "None",
"operator": {
"type": "string",
"operation": "notEquals"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
-1300,
380
],
"id": "d20be913-7202-4155-8c48-a24384ff4d4c",
"name": "If"
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
-1000,
620
],
"id": "fec49db7-7093-4f76-93a5-639412970ae5",
"name": "OpenAI Chat Model1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "d264444f-c01a-4fa0-86a4-c0bf0e4c8537",
"name": "output",
"value": "={{ $json.output || $json.text }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-420,
300
],
"id": "de256928-39d5-4bff-9c89-2b35310b8e75",
"name": "Edit Fields (Set Output Field)"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.body.chatInput }}",
"options": {
"systemMessage": "You are a personal assistant who helps answer questions from a corpus of documents. The documents are either text based (Txt, docs, extracted PDFs, etc.) or tabular data (CSVs or Excel documents).\n\nYou are given tools to perform RAG in the 'documents' table, look up the documents available in your knowledge base in the 'document_metadata' table, extract all the text from a given document, and query the tabular files with SQL in the 'document_rows' table.\n\nAlways start by performing RAG unless the question requires a SQL query for tabular data (fetching a sum, finding a max, something a RAG lookup would be unreliable for). If RAG doesn't help, then look at the documents that are available to you, find a few that you think would contain the answer, and then analyze those.\n\nAlways tell the user if you didn't find the answer. Don't make something up just to please them."
}
},
"id": "307aa3e6-8e90-4f61-89cc-c736a5651c8f",
"name": "Primary AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.6,
"position": [
-900,
300
]
},
{
"parameters": {
"promptType": "define",
"text": "={{ $('Webhook').item.json.body.chatInput }}"
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.5,
"position": [
-1100,
480
],
"id": "77de21fb-fe2e-4796-97f3-26ce2cdfdefb",
"name": "Open WebUI Metadata LLM"
}
],
"connections": {
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Primary AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Postgres Chat Memory": {
"ai_memory": [
[
{
"node": "Primary AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"Respond to Webhook": {
"main": [
[]
]
},
"Web Search Tool": {
"ai_tool": [
[
{
"node": "Primary AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Tool Start": {
"main": [
[
{
"node": "Brave Web Search",
"type": "main",
"index": 0
}
]
]
},
"Brave Web Search": {
"main": [
[
{
"node": "Summarize Web Research",
"type": "main",
"index": 0
}
]
]
},
"If": {
"main": [
[
{
"node": "Primary AI Agent",
"type": "main",
"index": 0
}
],
[
{
"node": "Open WebUI Metadata LLM",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "Open WebUI Metadata LLM",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Edit Fields (Set Output Field)": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"Primary AI Agent": {
"main": [
[
{
"node": "Edit Fields (Set Output Field)",
"type": "main",
"index": 0
}
]
]
},
"Open WebUI Metadata LLM": {
"main": [
[
{
"node": "Edit Fields (Set Output Field)",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "6d5ce905-6d74-4f88-869f-b554894f7c81",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "D30OKjXg1D8MlT4p",
"tags": []
}
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.
httpHeaderAuthopenAiApipostgres
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Open WebUI Agent Template. Uses lmChatOpenAi, memoryPostgresChat, toolWorkflow, httpRequest. Webhook trigger; 15 nodes.
Source: https://github.com/DPabloFlores/ottomator-agents/blob/main/n8n-openwebui-agent/Open_WebUI_Agent_Template.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.
🔍🛠️Perplexity Researcher to HTML Web Page. Uses stickyNote, lmChatOpenAi, outputParserStructured, respondToWebhook. Webhook trigger; 47 nodes.
OpenAI Chat, Output Parser Structured, Telegram +5
Transform simple queries into comprehensive, well-structured content with this n8n workflow that leverages Perplexity AI for research and GPT-4 for content transformation. Create professional blog pos
OpenAI Chat, Output Parser Structured, Telegram +5
AI Agent to chat with you Search Console Data, using OpenAI and Postgres. Uses memoryPostgresChat, lmChatOpenAi, stickyNote, respondToWebhook. Webhook trigger; 30 nodes.
Memory Postgres Chat, OpenAI Chat, Tool Workflow +3
AI Agent to chat with you Search Console Data, using OpenAI and Postgres. Uses memoryPostgresChat, lmChatOpenAi, stickyNote, respondToWebhook. Webhook trigger; 30 nodes.
Memory Postgres Chat, OpenAI Chat, Tool Workflow +3
Edit 19/11/2024: As explained on the workflow, the AI Agent with the original system prompt was not effective when using .
Memory Postgres Chat, OpenAI Chat, Tool Workflow +3