This workflow follows the Agent → Documentdefaultdataloader 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": "2Chat Chatbot",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "2chatbot",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
0,
0
],
"id": "6ad656e4-8553-41d3-87c7-5205e1da8fd8",
"name": "Webhook",
"notesInFlow": false
},
{
"parameters": {
"agent": "conversationalAgent",
"promptType": "define",
"text": "={{ $json.body.message }}",
"options": {
"systemMessage": "As a customer service agent, your primary goal is to assist customers effectively and efficiently. Here's how you should approach each interaction:\n\n<language_detection>Begin by detecting the language of the customer's query. Respond in the same language to ensure clear and effective communication.</language_detection>\n\n<understanding_query>Carefully read and understand the customer's question or issue. If the query is unclear, politely ask for more details to better assist them.</understanding_query>\n\n<providing_solutions>Offer accurate and helpful solutions based on the information available. If you don't know the answer, acknowledge it and offer to find out more or direct them to someone who can help.</providing_solutions>\n\n<empathy_professionalism>Maintain a friendly and professional tone throughout the interaction. Show empathy and understanding towards the customer's concerns.</empathy_professionalism>\n\n<follow_up>Ensure the customer is satisfied with the resolution. Ask if there's anything else you can assist with before concluding the interaction.</follow_up>\n\n<feedback>Encourage customers to provide feedback on the service to help improve future interactions.</feedback>\n\nBy following these guidelines, you will provide excellent customer service and build strong relationships with our customers."
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.7,
"position": [
360,
0
],
"id": "d34b94f7-bbff-4bb8-960f-b9e27300ce7b",
"name": "AI Agent"
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Webhook').item.json.body.phonenumber }}"
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
460,
280
],
"id": "e617782c-f270-4531-bb6d-efa8911e9aab",
"name": "Window Buffer Memory"
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={\n \"answer\": \"{{ $json.output }}\"\n} ",
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
800,
0
],
"id": "169041e7-a64f-4b27-a281-3f5c1bd5dee8",
"name": "Respond to Webhook"
},
{
"parameters": {
"formTitle": "Knowledge",
"formFields": {
"values": [
{
"fieldLabel": "Knowledge",
"fieldType": "textarea"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.formTrigger",
"typeVersion": 2.2,
"position": [
-20,
-480
],
"id": "ea0b407a-92f0-4949-adf0-6fd80351a3f5",
"name": "On form submission",
"disabled": true
},
{
"parameters": {
"mode": "insert",
"memoryKey": "knowledge"
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreInMemory",
"typeVersion": 1,
"position": [
220,
-480
],
"id": "902e8ea3-b20b-4a1f-a8a3-267d60b548c3",
"name": "In-Memory Vector Store"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.1,
"position": [
220,
-260
],
"id": "4f36895d-bf6f-4dc3-8ebf-388f9d47fb11",
"name": "Embeddings OpenAI",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsonMode": "expressionData",
"jsonData": "={{ $json.Knowledge }}",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1,
"position": [
360,
-320
],
"id": "a975209c-7158-4767-8fd7-d55e86e7e496",
"name": "Default Data Loader"
},
{
"parameters": {
"chunkOverlap": 100,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"typeVersion": 1,
"position": [
700,
-260
],
"id": "cb78b053-b63e-40e4-bfd8-deda18a6d18d",
"name": "Recursive Character Text Splitter"
},
{
"parameters": {
"name": "KnowledgeBase",
"topK": 10
},
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"typeVersion": 1,
"position": [
660,
260
],
"id": "496100bf-c95a-489a-ad1e-d453b71770f8",
"name": "Vector Store Tool"
},
{
"parameters": {
"memoryKey": "knowledge"
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreInMemory",
"typeVersion": 1,
"position": [
620,
460
],
"id": "a11012c0-992d-4d5e-8955-c10f3cc19f3a",
"name": "In-Memory Vector Store1"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
1140,
440
],
"id": "9ce0e480-de77-4a3f-9e9a-e93365109992",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.1,
"position": [
720,
640
],
"id": "47f20703-e71a-425c-8186-1a936c3dbe9f",
"name": "Embeddings OpenAI1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
320,
280
],
"id": "690b9684-fce3-4391-ae07-2b9484d15862",
"name": "OpenAI Chat Model1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "## Add texts to Knowledgebase\n\nEnable the form submission and deactivate the webhook to enter the knowledge the chatbot will use in the in Memory Vector Store",
"height": 460,
"width": 1300
},
"type": "n8n-nodes-base.stickyNote",
"position": [
-180,
-580
],
"typeVersion": 1,
"id": "305ef8be-e3c4-4247-bed8-9700bd413c02",
"name": "Sticky Note"
},
{
"parameters": {
"content": "## AI Chatbot agent\nEnable the webhook to load data into ",
"height": 880,
"width": 1460,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"position": [
-180,
-80
],
"typeVersion": 1,
"id": "c3082ca2-5fcb-49f5-8f35-6700e2a6b490",
"name": "Sticky Note1"
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"Window Buffer Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"On form submission": {
"main": [
[
{
"node": "In-Memory Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "In-Memory Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "In-Memory Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Vector Store Tool": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"In-Memory Vector Store1": {
"ai_vectorStore": [
[
{
"node": "Vector Store Tool",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Vector Store Tool",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "In-Memory Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "e84c587a-da6b-4c5f-b7bb-5f8fbff21d3b",
"id": "p7hTq5J3PodLFm02",
"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.
openAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
2Chat Chatbot. Uses agent, memoryBufferWindow, formTrigger, vectorStoreInMemory. Webhook trigger; 16 nodes.
Source: https://github.com/2ChatCo/Tutorials/blob/main/n8n/2Chat_Chatbot.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
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
AI Multi-Document Analyzer with Smart Recommendations & Reporting
Crypto, Agent, OpenAI Chat +8
This workflow implements a complete Voice AI Chatbot system for Wordress that integrates speech recognition, guardrails for safety, retrieval-augmented generation (RAG), Qdrant vector search, and audi
OpenAI Chat, Memory Buffer Window, Tool Calculator +10
This workflow implements a complete Retrieval-Augmented Generation (RAG) system for document ingestion and intelligent querying.
Text Splitter Recursive Character Text Splitter, Document Default Data Loader, OpenAI Embeddings +5