Chat with OpenAI Assistant (by adding a memory)
Engage in a continuous conversation with an OpenAI Assistant, maintaining context across multiple turns. This workflow connects a Chat Trigger to an OpenAI Assistant, with Chat Memory Managers storing and retrieving the conversation history. Use this for building interactive chatbots, customer support agents, or personalized learning experiences that remember past interactions.
Workflow JSON
{"meta": {"instanceId": "cb484ba7b742928a2048bf8829668bed5b5ad9787579adea888f05980292a4a7"}, "nodes": [{"id": "087ae6e2-b333-4a30-9010-c78050203961", "name": "OpenAI Assistant", "type": "@n8n/n8n-nodes-langchain.openAiAssistant", "position": [1340, 460], "parameters": {"text": "=## Our Previous Conversation:\n{{ $json[\"messages\"].map(m => `\nHuman: ${m.human}\nAI Assistant: ${m.ai}\n`) }}\n## Current message:\n{{ $('Chat Trigger').item.json.chatInput }}", "options": {}, "assistantId": "asst_HDSAnzsp4WqY4UC1iI9auH5z"}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "3793b10a-ebb7-42ec-8b9b-7fa3a353d9a3", "name": "Calculator", "type": "@n8n/n8n-nodes-langchain.toolCalculator", "position": [1500, 640], "parameters": {}, "typeVersion": 1}, {"id": "7bee2882-bb9e-402e-ba42-9b1ed0e1264b", "name": "Chat Memory Manager", "type": "@n8n/n8n-nodes-langchain.memoryManager", "position": [760, 460], "parameters": {}, "typeVersion": 1, "alwaysOutputData": true}, {"id": "5c66e482-819e-47e7-90be-779e92364e2a", "name": "Chat Memory Manager1", "type": "@n8n/n8n-nodes-langchain.memoryManager", "position": [1720, 460], "parameters": {"mode": "insert", "messages": {"messageValues": [{"type": "user", "message": "={{ $('Chat Trigger').item.json.chatInput }}"}, {"type": "ai", "message": "={{ $json.output }}"}]}}, "typeVersion": 1, "alwaysOutputData": true}, {"id": "b96bf629-bd21-4528-8988-e63c5af89fd7", "name": "Aggregate", "type": "n8n-nodes-base.aggregate", "position": [1140, 460], "parameters": {"options": {}, "aggregate": "aggregateAllItemData", "destinationFieldName": "messages"}, "typeVersion": 1, "alwaysOutputData": true}, {"id": "95001be1-f046-47e3-a58c-25bff170ba06", "name": "Edit Fields", "type": "n8n-nodes-base.set", "position": [2320, 460], "parameters": {"fields": {"values": [{"name": "output", "stringValue": "={{ $('OpenAI Assistant').item.json.output }}"}]}, "options": {}}, "typeVersion": 3.2}, {"id": "4ea04793-c7fb-4b81-abf7-49590aa76ca7", "name": "Limit", "type": "n8n-nodes-base.limit", "position": [2100, 460], "parameters": {}, "typeVersion": 1}, {"id": "16921f74-d420-445a-9e09-19a6116a3267", "name": "Chat Trigger", "type": "@n8n/n8n-nodes-langchain.chatTrigger", "position": [460, 460], "webhookId": "1f83e8ac-d465-454a-8327-cef7f0149cb1", "parameters": {"public": true, "options": {"loadPreviousSession": "memory"}}, "typeVersion": 1}, {"id": "c0826494-779a-4c2d-93c9-746150ac9482", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [740, 400], "parameters": {"color": 7, "width": 514.8706020514577, "height": 196.64941360686112, "content": "Read contents of the chat from memory"}, "typeVersion": 1}, {"id": "4ce4594d-070a-4985-9c5d-fcd4ebc4a627", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [1320, 400], "parameters": {"color": 7, "width": 298.02823821086326, "height": 196.64941360686112, "content": "Call the assistant, passing in the previous chat messages"}, "typeVersion": 1}, {"id": "49885b3b-de77-4c02-a35e-d188fee38831", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [1700, 400], "parameters": {"color": 7, "width": 298.02823821086326, "height": 196.64941360686112, "content": "Add the latest chat messages to the memory"}, "typeVersion": 1}, {"id": "f45e8589-d61b-440a-ae89-31ded2738ef7", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [2080, 400], "parameters": {"color": 7, "width": 356.0564764217267, "height": 196.64941360686112, "content": "Return the model output"}, "typeVersion": 1}, {"id": "3b72a676-aaa2-472a-b055-1fed03f52101", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [360, 640], "parameters": {"height": 300.48941882630095, "content": "## Try me out\n1. In the OpenAI Assistant node, make sure your OpenAI credentials are set and choose an assistant to use (you'll need to create one if you don't have one already)\n2. Click the 'Chat' button below\n\n - In the first message, tell the AI what your name is\n - In a second message, ask the AI what your name is"}, "typeVersion": 1}, {"id": "a2250328-e4ce-4ac6-b4fe-658ab173bc28", "name": "Window Buffer Memory", "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow", "position": [1280, 880], "parameters": {"sessionKey": "={{ $('Chat Trigger').item.json.sessionId }}123", "contextWindowLength": 20}, "typeVersion": 1.1}], "pinData": {}, "connections": {"Limit": {"main": [[{"node": "Edit Fields", "type": "main", "index": 0}]]}, "Aggregate": {"main": [[{"node": "OpenAI Assistant", "type": "main", "index": 0}]]}, "Calculator": {"ai_tool": [[{"node": "OpenAI Assistant", "type": "ai_tool", "index": 0}]]}, "Chat Trigger": {"main": [[{"node": "Chat Memory Manager", "type": "main", "index": 0}]]}, "OpenAI Assistant": {"main": [[{"node": "Chat Memory Manager1", "type": "main", "index": 0}]]}, "Chat Memory Manager": {"main": [[{"node": "Aggregate", "type": "main", "index": 0}]]}, "Chat Memory Manager1": {"main": [[{"node": "Limit", "type": "main", "index": 0}]]}, "Window Buffer Memory": {"ai_memory": [[{"node": "Chat Trigger", "type": "ai_memory", "index": 0}, {"node": "Chat Memory Manager", "type": "ai_memory", "index": 0}, {"node": "Chat Memory Manager1", "type": "ai_memory", "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.
LangChain - Example - Code Node Example
Explore a basic LangChain agent that answers questions using a custom tool. This workflow connects n8n's AI nodes and custom code nodes to OpenAI for language model interactions. It's useful for developers building custom AI assistants or researchers experimenting with agentic workflows. This saves development time by providing a ready-to-use example of a LangChain agent.
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.