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 with Web Search",
"nodes": [
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $json.sessionId }}"
},
"id": "93b4e520-196c-4d47-ae29-5166cac6656e",
"name": "Postgres Chat Memory",
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"typeVersion": 1,
"position": [
-1020,
-260
],
"notesInFlow": false,
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "9a9a245e-f1a1-4282-bb02-a81ffe629f0f",
"name": "chatInput",
"value": "={{ $json?.chatInput || $('Webhook1').item.json.body.chatInput }}",
"type": "string"
},
{
"id": "b80831d8-c653-4203-8706-adedfdb98f77",
"name": "sessionId",
"value": "={{ $json?.sessionId || $('Webhook1').item.json.body.sessionId }}",
"type": "string"
}
]
},
"options": {}
},
"id": "f413ed88-5706-4c59-8db0-740d346d955a",
"name": "Edit Fields",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-1200,
-480
]
},
{
"parameters": {
"public": true,
"options": {}
},
"id": "32b4e5d3-baa3-49a1-8778-394e6527f9e8",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
-1660,
-360
]
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.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 users asks you to check a document or 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": "15da50c9-38a5-4a75-be30-a81ceb151d7e",
"name": "RAG AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.6,
"position": [
-980,
-480
]
},
{
"parameters": {
"content": "## Web Search Tool",
"height": 400,
"width": 1680,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-1740,
220
],
"id": "1964c10e-edfb-4f61-86c0-448a21aac8eb",
"name": "Sticky Note7"
},
{
"parameters": {
"workflowInputs": {
"values": [
{
"name": "query"
}
]
}
},
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1.1,
"position": [
-1680,
360
],
"id": "6f2c2692-84b0-457c-9cd8-7a475a8995b0",
"name": "Tool Start"
},
{
"parameters": {
"name": "web_search",
"description": "Call this tool to do an advanced web search based on a query you define.\n\nThis tool will return the contents of the 3 most relevant web pages from the search.",
"workflowId": {
"__rl": true,
"value": "={{ $workflow.id }}",
"mode": "id"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {
"query": "={{ $fromAI('query') }}"
},
"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",
"removed": false
},
{
"id": "image_path",
"displayName": "image_path",
"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": [
-860,
-260
],
"id": "9d26b1bf-0dc2-40e8-b0da-b88f1e2f6609",
"name": "Web Search Tool"
},
{
"parameters": {
"url": "=http://searxng:8080/search?q={{ $json.query }}&format=json",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-1480,
360
],
"id": "461520d4-370e-481c-8f78-6edd6ea87423",
"name": "SearXNG"
},
{
"parameters": {
"fieldToSplitOut": "results",
"options": {}
},
"type": "n8n-nodes-base.splitOut",
"typeVersion": 1,
"position": [
-1280,
360
],
"id": "b6c1be02-9bc0-45cd-b78d-09dc8b541687",
"name": "Split Out"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "169ce734-0077-4c34-b7f1-40a35184fad6",
"name": "url",
"value": "={{ $json.url }}",
"type": "string"
},
{
"id": "310e45f1-904e-4350-971f-a8519a49ab91",
"name": "title",
"value": "={{ $json.title }}",
"type": "string"
},
{
"id": "f6ac5cd2-4504-4f37-a766-33bc6ef09d47",
"name": "content",
"value": "={{ $json.content }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-1080,
360
],
"id": "1c490ba8-87b7-4edb-90d6-c27c9ba92cdb",
"name": "Edit Fields2"
},
{
"parameters": {
"maxItems": 3
},
"type": "n8n-nodes-base.limit",
"typeVersion": 1,
"position": [
-880,
360
],
"id": "1e1fabe5-a258-4f08-8394-9f8fba5eb24f",
"name": "Limit"
},
{
"parameters": {
"aggregate": "aggregateAllItemData",
"destinationFieldName": "search_results",
"options": {}
},
"type": "n8n-nodes-base.aggregate",
"typeVersion": 1,
"position": [
-280,
360
],
"id": "36ab3b3e-1e4b-40bb-aa31-425f546c2fe3",
"name": "Aggregate1"
},
{
"parameters": {
"url": "={{ $json.url }}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-680,
360
],
"id": "38d2389b-1368-4c0a-9964-3f4eac930f00",
"name": "HTTP Request",
"alwaysOutputData": true,
"onError": "continueRegularOutput"
},
{
"parameters": {
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "site_html",
"cssSelector": "body"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.html",
"typeVersion": 1.2,
"position": [
-480,
360
],
"id": "4b0f50d2-1c62-42b3-8877-a306b6aad3f1",
"name": "HTML",
"alwaysOutputData": true,
"onError": "continueRegularOutput"
},
{
"parameters": {
"model": "qwen2.5:14b-instruct-q4_K_M",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
-1180,
-260
],
"id": "4a88e757-3746-4d86-8473-80656434ac97",
"name": "Ollama Chat Model",
"credentials": {
"ollamaApi": {
"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": [
-540,
-260
],
"id": "68b1c7ad-2ff9-4cc4-877d-6aa30e87fcfd",
"name": "Edit Fields (Set Output Field)"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $('Webhook1').item.json.body.chatInput }}"
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.5,
"position": [
-1100,
-100
],
"id": "4bc2c2b0-ace5-4290-be29-4c73f9d0ed12",
"name": "Open WebUI Metadata LLM"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "f5ebbd4f-6549-4a31-b3f8-eee7634dc439",
"leftValue": "={{ $json.body.chatInput }}",
"rightValue": "### Task",
"operator": {
"type": "string",
"operation": "notStartsWith"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
-1420,
-140
],
"id": "3306140e-db0f-4efa-ae4b-87ab4389f0b6",
"name": "Chat message or metadata request?"
},
{
"parameters": {
"options": {}
},
"id": "cc8aae54-563e-4786-99c4-eafdd29122a5",
"name": "Respond to Webhook1",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
-300,
-260
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "invoke-n8n-agent",
"authentication": "headerAuth",
"responseMode": "responseNode",
"options": {}
},
"id": "768234d5-081d-4058-b57f-c59017a10441",
"name": "Webhook1",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
-1660,
-140
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "qwen2.5:14b-instruct-q4_K_M",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
-1020,
60
],
"id": "4f98290b-644b-4f26-8979-8b1ddd3006f9",
"name": "Ollama Chat Model1",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "## Open WebUI Compatible n8n Agent with Web Search (100% Local)",
"height": 760,
"width": 1680,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-1740,
-560
],
"id": "4498ec28-9135-4707-b701-033e80902328",
"name": "Sticky Note"
}
],
"connections": {
"Postgres Chat Memory": {
"ai_memory": [
[
{
"node": "RAG AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Edit Fields": {
"main": [
[
{
"node": "RAG AI Agent",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"RAG AI Agent": {
"main": [
[
{
"node": "Edit Fields (Set Output Field)",
"type": "main",
"index": 0
}
]
]
},
"Tool Start": {
"main": [
[
{
"node": "SearXNG",
"type": "main",
"index": 0
}
]
]
},
"Web Search Tool": {
"ai_tool": [
[
{
"node": "RAG AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"SearXNG": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "Edit Fields2",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields2": {
"main": [
[
{
"node": "Limit",
"type": "main",
"index": 0
}
]
]
},
"Limit": {
"main": [
[
{
"node": "HTTP Request",
"type": "main",
"index": 0
}
]
]
},
"HTTP Request": {
"main": [
[
{
"node": "HTML",
"type": "main",
"index": 0
}
]
]
},
"HTML": {
"main": [
[
{
"node": "Aggregate1",
"type": "main",
"index": 0
}
]
]
},
"Ollama Chat Model": {
"ai_languageModel": [
[
{
"node": "RAG AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Edit Fields (Set Output Field)": {
"main": [
[
{
"node": "Respond to Webhook1",
"type": "main",
"index": 0
}
]
]
},
"Open WebUI Metadata LLM": {
"main": [
[
{
"node": "Edit Fields (Set Output Field)",
"type": "main",
"index": 0
}
]
]
},
"Chat message or metadata request?": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
],
[
{
"node": "Open WebUI Metadata LLM",
"type": "main",
"index": 0
}
]
]
},
"Webhook1": {
"main": [
[
{
"node": "Chat message or metadata request?",
"type": "main",
"index": 0
}
]
]
},
"Ollama Chat Model1": {
"ai_languageModel": [
[
{
"node": "Open WebUI Metadata LLM",
"type": "ai_languageModel",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "0183f370-583c-41e0-add0-633c0dd2d272",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "8NGtjxzT5j3cWdbP",
"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.
httpHeaderAuthollamaApipostgres
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Open WebUI Agent with Web Search. Uses memoryPostgresChat, chatTrigger, agent, executeWorkflowTrigger. Chat trigger; 22 nodes.
Source: https://github.com/DPabloFlores/ottomator-agents/blob/main/python-local-ai-agent/n8n_local_ai_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.
✨📊Multi-AI Agent Chatbot for Postgres/Supabase DB and QuickCharts + Tool Router. Uses chatTrigger, postgresTool, executeWorkflowTrigger, toolWorkflow. Chat trigger; 40 nodes.
Chat Trigger, Postgres Tool, Execute Workflow Trigger +6
This workflow is ideal for data analysts, developers, and business intelligence teams who need an AI-powered chatbot to query Postgres/Supabase databases and generate dynamic charts for data visualiza
Chat Trigger, Postgres Tool, Execute Workflow Trigger +6
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Google Gemini Chat, HTTP Request Tool, Chat Trigger +8
This Chatbot automates the process of discovering job openings and generating tailored job application emails.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
Extract Insights & Analyse Youtube Comments Via Ai Agent Chat. Uses stickyNote, lmChatOpenAi, toolWorkflow, memoryPostgresChat. Chat trigger; 29 nodes.
OpenAI Chat, Tool Workflow, Memory Postgres Chat +5