AI chat with any data source (using the n8n workflow tool)
Workflow JSON
{"meta": {"instanceId": "cb484ba7b742928a2048bf8829668bed5b5ad9787579adea888f05980292a4a7"}, "nodes": [{"id": "4c52efcf-039b-4550-8a63-3d3d4dde488b", "name": "On new manual Chat Message", "type": "@n8n/n8n-nodes-langchain.manualChatTrigger", "position": [740, 300], "parameters": {}, "typeVersion": 1.1}, {"id": "adb528f1-b87b-4bb2-99e1-776fd839522e", "name": "Execute Workflow Trigger", "type": "n8n-nodes-base.executeWorkflowTrigger", "position": [680, 940], "parameters": {}, "typeVersion": 1}, {"id": "092cf737-5b53-4fc8-82f5-c775b77ea0bd", "name": "Hacker News", "type": "n8n-nodes-base.hackerNews", "position": [900, 940], "parameters": {"limit": 50, "resource": "all", "additionalFields": {}}, "typeVersion": 1}, {"id": "a0805137-630c-4065-826e-88afa000660f", "name": "Clean up data", "type": "n8n-nodes-base.set", "position": [1120, 940], "parameters": {"fields": {"values": [{"name": "title", "stringValue": "={{ $json._highlightResult.title.value }}"}, {"name": "points", "type": "numberValue", "numberValue": "={{ $json.points }}"}, {"name": "url", "stringValue": "={{ $json.url }}"}, {"name": "created_at", "stringValue": "={{ $json.created_at }}"}, {"name": "author", "stringValue": "={{ $json.author }}"}]}, "include": "none", "options": {}}, "typeVersion": 3.2}, {"id": "e1b255f4-e970-42d6-9870-4e302bf2da83", "name": "AI Agent", "type": "@n8n/n8n-nodes-langchain.agent", "position": [960, 300], "parameters": {"options": {"maxIterations": 10}}, "typeVersion": 1.1}, {"id": "91e3391e-909e-4d63-9649-ff62781dbba9", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [960, 520], "parameters": {"options": {}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "cd1f0028-635e-48eb-ac38-4c6fb25ed63e", "name": "Stringify", "type": "n8n-nodes-base.code", "position": [1340, 940], "parameters": {"jsCode": "return {\n 'response': JSON.stringify($input.all().map(x => x.json))\n}"}, "typeVersion": 2}, {"id": "7df241eb-67d3-4724-8b32-4b53561ed55f", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [880, 820], "parameters": {"color": 7, "width": 150, "height": 293, "content": "### Replace me\nwith any other service, e.g. fetching your own data"}, "typeVersion": 1}, {"id": "270845df-7c2d-4035-9ac0-e41d418b3026", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [600, 738.125], "parameters": {"color": 7, "width": 927.5, "height": 406.875, "content": "### Sub-workflow: Custom tool\nThis can be called by the agent above. This example fetches the top 50 posts ever on Hacker News"}, "typeVersion": 1}, {"id": "1d796a86-45d1-4fc4-8245-893525505d1f", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [600, 200], "parameters": {"color": 7, "width": 927.5, "height": 486.5625, "content": "### Main workflow: AI agent using custom tool\nTry it out by clicking 'Chat' and entering 'What is the 5th most popular post ever on Hacker News?'"}, "typeVersion": 1}, {"id": "38ff64b5-6f47-4d2d-9051-caab418bb0e8", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [440, 300], "parameters": {"width": 185.9375, "height": 218, "content": "## Try me out\n\nClick the 'Chat' button and enter:\n\n_What is the 5th most popular post ever on Hacker News?_"}, "typeVersion": 1}, {"id": "3532e461-bd74-48f7-93e1-96d608c88688", "name": "Custom tool to call the wf below", "type": "@n8n/n8n-nodes-langchain.toolWorkflow", "position": [1120, 520], "parameters": {"name": "hn_tool", "workflowId": "={{ $workflow.id }}", "description": "Returns a list of the most popular posts ever on Hacker News, in json format"}, "typeVersion": 1}], "pinData": {}, "connections": {"Hacker News": {"main": [[{"node": "Clean up data", "type": "main", "index": 0}]]}, "Clean up data": {"main": [[{"node": "Stringify", "type": "main", "index": 0}]]}, "OpenAI Chat Model": {"ai_languageModel": [[{"node": "AI Agent", "type": "ai_languageModel", "index": 0}]]}, "Execute Workflow Trigger": {"main": [[{"node": "Hacker News", "type": "main", "index": 0}]]}, "On new manual Chat Message": {"main": [[{"node": "AI Agent", "type": "main", "index": 0}]]}, "Custom tool to call the wf below": {"ai_tool": [[{"node": "AI Agent", "type": "ai_tool", "index": 0}]]}}}How to Import This Workflow
- 1Copy the workflow JSON above using the Copy Workflow JSON button.
- 2Open your n8n instance and go to Workflows.
- 3Click Import from JSON and paste the copied workflow.
Don't have an n8n instance? Start your free trial at n8nautomation.cloud
Related Templates
Text to Speech (OpenAI)
Converts text into natural-sounding speech using OpenAI's Text-to-Speech API. It sends your input text to OpenAI and receives an audio file in return. This is useful for creating audio versions of articles, generating voiceovers for videos, or providing accessibility features for web content. Quickly transform written content into engaging audio.
Automate Customer Support Issue Resolution using AI Text Classifier
Automate the resolution of customer support issues by classifying their state and applying AI-driven actions. This workflow connects Jira for issue management, OpenAI for AI classification and response generation, and Slack for notifications. Support teams can use this to automatically close resolved tickets, remind customers about open issues, or escalate complex cases.
AI-Powered Candidate Shortlisting Automation for ERPNext
Automate AI-powered candidate shortlisting for ERPNext job applications. This workflow connects ERPNext, Google Gemini, WhatsApp, and Outlook to process resumes, evaluate candidates, and communicate outcomes. Recruiters and HR departments can use this to efficiently screen applicants, automatically reject unqualified candidates, and send acceptance notifications. It significantly reduces manual review time and streamlines the hiring process.