Allan Vaccarizi This workflow corresponds to n8n.io template #7381 — we link there as the canonical source.
This workflow follows the Agent → Chat Trigger 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "2df4ecf6-a027-4a7e-8368-f712023168ee",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-160,
-32
],
"parameters": {
"width": 480,
"height": 832,
"content": "## Chatbot w/ RAG\n\n### How it works\n\n1. A chat trigger receives incoming user messages and passes them to the AI Agent.\n2. The AI Agent uses Anthropic's Claude model to generate responses, retrieves relevant context from a Supabase Vector Store (using OpenAI embeddings), and maintains conversation history via Postgres Chat Memory.\n\n### Setup steps\n\n- - [ ] Configure the **Chat Trigger** node with your desired authentication settings.\n- - [ ] Add your **Anthropic API key** credential to the Anthropic Chat Model sub-node.\n- - [ ] Add your **OpenAI API key** credential to the Embeddings OpenAI node for vector search.\n- - [ ] Set up a **Supabase** project and configure the Supabase Vector Store with your project URL and API key.\n- - [ ] Configure the **Postgres Chat Memory** node with credentials pointing to your PostgreSQL database for session memory storage.\n\n### Customization\n\nYou can swap the Anthropic Chat Model for a different LLM (e.g., OpenAI GPT-4), replace Supabase Vector Store with another vector store (e.g., Pinecone), or adjust the Postgres memory session key to support multi-user conversations."
},
"typeVersion": 1
},
{
"id": "44d4cd6d-eb12-4f00-a714-c4ddec06ba1d",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
400,
96
],
"parameters": {
"color": 7,
"height": 384,
"content": "## Chat trigger entry point\n\nListens for incoming chat messages and forwards them to the AI Agent to begin processing."
},
"typeVersion": 1
},
{
"id": "3c7a4bfb-2f1a-477a-bdc0-07086182834e",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
672,
96
],
"parameters": {
"color": 7,
"width": 672,
"height": 688,
"content": "## AI agent with memory and retrieval\n\nCore AI processing cluster: the AI Agent orchestrates responses using Anthropic Claude as the LLM, Postgres Chat Memory for conversation history, and a Supabase Vector Store for knowledge retrieval. The OpenAI Embeddings node is spatially attached to this cluster and provides the embedding model for the vector store lookups."
},
"typeVersion": 1
},
{
"id": "5e145545-374c-4829-87f0-2b9edf80d0ff",
"name": "Chat Assistant Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
896,
304
],
"parameters": {
"options": {
"systemMessage": "You are a helpful assistant"
}
},
"typeVersion": 2.2
},
{
"id": "a1d0c158-4fef-45a7-8536-0575b4a567c6",
"name": "Store Chat History in Postgres",
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"position": [
976,
496
],
"parameters": {},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "84166510-806b-464c-a647-99cc2564b37b",
"name": "Retrieve from Supabase Vectors",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"position": [
1072,
480
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"tableName": {
"__rl": true,
"mode": "id",
"value": "=Your_database"
},
"toolDescription": "Data base"
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "45508c40-cfe6-4993-8a2f-3316ddbe69ed",
"name": "Generate OpenAI Embeddings",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1120,
640
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "1f9c83fa-7345-4ad8-a8ee-733725ddf8cd",
"name": "When Chat Message Received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
448,
304
],
"parameters": {
"public": true,
"options": {
"title": "Chatbot Growth AI \ud83e\udd16",
"subtitle": "Toujours l\u00e0 pour vous aider",
"customCss": ":root {\n /* \u2500\u2500\u2500 Growth AI Brand Colors \u2500\u2500\u2500 */\n --chat--color-primary: #00C48C;\n --chat--color-primary-shade-50: #00B07D;\n --chat--color-primary-shade-100: #009B6E;\n --chat--color-secondary: #0A0F1E;\n --chat--color-secondary-shade-50: #111827;\n --chat--color-white: #ffffff;\n --chat--color-light: #F0F4F8;\n --chat--color-light-shade-50: #DDE3EC;\n --chat--color-light-shade-100: #B8C3D4;\n --chat--color-medium: #8896AB;\n --chat--color-dark: #0A0F1E;\n --chat--color-disabled: #C8D2DF;\n --chat--color-typing: #404040;\n\n /* \u2500\u2500\u2500 Base Layout \u2500\u2500\u2500 */\n --chat--spacing: 1rem;\n --chat--border-radius: 0.25rem;\n --chat--transition-duration: 0.15s;\n\n /* \u2500\u2500\u2500 Police syst\u00e8me native (d'origine) \u2500\u2500\u2500 */\n --chat--font-family: (\n -apple-system,\n BlinkMacSystemFont,\n 'Segoe UI',\n Roboto,\n Oxygen-Sans,\n Ubuntu,\n Cantarell,\n 'Helvetica Neue',\n sans-serif\n );\n\n /* \u2500\u2500\u2500 Window Dimensions \u2500\u2500\u2500 */\n --chat--window--width: 400px;\n --chat--window--height: 600px;\n --chat--window--bottom: var(--chat--spacing);\n --chat--window--right: var(--chat--spacing);\n --chat--window--z-index: 9999;\n --chat--window--border: 1px solid rgba(0, 196, 140, 0.2);\n --chat--window--border-radius: var(--chat--border-radius);\n --chat--window--margin-bottom: var(--chat--spacing);\n\n /* \u2500\u2500\u2500 Header \u2500\u2500\u2500 */\n --chat--header-height: auto;\n --chat--header--padding: var(--chat--spacing);\n --chat--header--background: #0A0F1E;\n --chat--header--color: var(--chat--color-light);\n --chat--header--border-top: none;\n --chat--header--border-bottom: 1px solid rgba(0, 196, 140, 0.25);\n --chat--header--border-left: none;\n --chat--header--border-right: none;\n --chat--heading--font-size: 2em;\n --chat--subtitle--font-size: inherit;\n --chat--subtitle--line-height: 1.8;\n\n /* \u2500\u2500\u2500 Messages \u2500\u2500\u2500 */\n --chat--message--font-size: 1rem;\n --chat--message--padding: var(--chat--spacing);\n --chat--message--border-radius: var(--chat--border-radius);\n --chat--message-line-height: 1.5;\n --chat--message--margin-bottom: calc(var(--chat--spacing) * 1);\n\n --chat--message--bot--background: var(--chat--color-white);\n --chat--message--bot--color: var(--chat--color-dark);\n --chat--message--bot--border: none;\n\n --chat--message--user--background: #00C48C;\n --chat--message--user--color: var(--chat--color-white);\n --chat--message--user--border: none;\n\n --chat--message--pre--background: rgba(0, 0, 0, 0.05);\n --chat--messages-list--padding: var(--chat--spacing);\n\n /* \u2500\u2500\u2500 Toggle Button \u2500\u2500\u2500 */\n --chat--toggle--size: 64px;\n --chat--toggle--width: var(--chat--toggle--size);\n --chat--toggle--height: var(--chat--toggle--size);\n --chat--toggle--border-radius: 50%;\n --chat--toggle--background: #00C48C;\n --chat--toggle--hover--background: #00B07D;\n --chat--toggle--active--background: #009B6E;\n --chat--toggle--color: var(--chat--color-white);\n\n /* \u2500\u2500\u2500 Input Area \u2500\u2500\u2500 */\n --chat--textarea--height: 50px;\n --chat--textarea--max-height: 30rem;\n --chat--input--font-size: inherit;\n --chat--input--border: 0;\n --chat--input--border-radius: 0;\n --chat--input--padding: 0.8rem;\n --chat--input--background: var(--chat--color-white);\n --chat--input--text-color: initial;\n --chat--input--line-height: 1.5;\n --chat--input--placeholder--font-size: var(--chat--input--font-size);\n --chat--input--border-active: 0;\n --chat--input--left--panel--width: 2rem;\n\n /* \u2500\u2500\u2500 Buttons \u2500\u2500\u2500 */\n --chat--button--color: var(--chat--color-light);\n --chat--button--background: #00C48C;\n --chat--button--padding: calc(var(--chat--spacing) * 1 / 2) var(--chat--spacing);\n --chat--button--border-radius: var(--chat--border-radius);\n --chat--button--hover--color: var(--chat--color-light);\n --chat--button--hover--background: #00B07D;\n --chat--close--button--color-hover: #00C48C;\n\n /* \u2500\u2500\u2500 Send & File Buttons \u2500\u2500\u2500 */\n --chat--input--send--button--background: var(--chat--color-white);\n --chat--input--send--button--color: #00C48C;\n --chat--input--send--button--background-hover: #00B07D;\n --chat--input--send--button--color-hover: #009B6E;\n --chat--input--file--button--background: var(--chat--color-white);\n --chat--input--file--button--color: #00C48C;\n --chat--input--file--button--background-hover: var(--chat--input--file--button--background);\n --chat--input--file--button--color-hover: #009B6E;\n --chat--files-spacing: 0.25rem;\n\n /* \u2500\u2500\u2500 Body & Footer \u2500\u2500\u2500 */\n --chat--body--background: var(--chat--color-light);\n --chat--footer--background: var(--chat--color-light);\n --chat--footer--color: var(--chat--color-dark);\n}\n\n\n/* \u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\n OVERRIDES \u2014 Personnalisation Growth AI\n\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550 */\n\n/* \u2500\u2500 Largeur des bulles (identique \u00e0 l'original) \u2500\u2500 */\n.chat-message {\n max-width: 50%;\n}\n\n/* \u2500\u2500 Fen\u00eatre : ombre \u00e9l\u00e9gante \u2500\u2500 */\n.chat-window {\n box-shadow:\n 0 20px 60px rgba(10, 15, 30, 0.2),\n 0 0 0 1px rgba(0, 196, 140, 0.12) !important;\n overflow: hidden;\n}\n\n/* \u2500\u2500 Header : d\u00e9grad\u00e9 noir \u2192 dor\u00e9 Growth AI \u2500\u2500 */\n.chat-header {\n background: linear-gradient(135deg, #0A0F1E 0%, #1A1408 40%, #B8860B 80%, #D4A017 100%) !important;\n border-bottom: 1px solid rgba(212, 160, 23, 0.4) !important;\n position: relative;\n}\n\n/* Trait dor\u00e9 en bas du header */\n.chat-header::after {\n content: '';\n position: absolute;\n bottom: 0;\n left: 0;\n width: 56px;\n height: 2px;\n background: linear-gradient(90deg, #D4A017, #F5C842);\n border-radius: 0 2px 2px 0;\n}\n\n/* \u2500\u2500 Sous-titre header plus discret \u2500\u2500 */\n.chat-header p,\n.chat-header .chat-subtitle {\n color: rgba(255, 255, 255, 0.5) !important;\n}\n\n/* \u2500\u2500 Zone messages \u2500\u2500 */\n.chat-messages-list {\n background: linear-gradient(180deg, #F0F4F8 0%, #EDF1F7 100%) !important;\n}\n\n/* \u2500\u2500 Bulle bot : bordure verte subtile \u2500\u2500 */\n.chat-message.chat-message-from-bot .chat-message-bubble {\n border: 1px solid rgba(0, 196, 140, 0.18) !important;\n box-shadow: 0 1px 6px rgba(10, 15, 30, 0.07);\n}\n\n/* \u2500\u2500 Bulle user : d\u00e9grad\u00e9 vert \u2500\u2500 */\n.chat-message.chat-message-from-user .chat-message-bubble {\n background: linear-gradient(135deg, #00C48C 0%, #00A87A 100%) !important;\n box-shadow: 0 2px 12px rgba(0, 196, 140, 0.35);\n}\n\n/* \u2500\u2500 Zone de saisie \u2500\u2500 */\n.chat-input-area,\n.chat-inputs-container {\n border-top: 1.5px solid var(--chat--color-light-shade-50) !important;\n background: #ffffff !important;\n}\n\n/* \u2500\u2500 Placeholder discret \u2500\u2500 */\n.chat-input::placeholder {\n color: var(--chat--color-light-shade-100) !important;\n}\n\n/* \u2500\u2500 Bouton send : micro-animation au hover \u2500\u2500 */\n.chat-input-send-button {\n transition: transform 0.15s ease, color 0.15s ease !important;\n}\n\n.chat-input-send-button:hover {\n transform: scale(1.15) rotate(-8deg) !important;\n}\n\n/* \u2500\u2500 Bouton toggle flottant : halo vert \u2500\u2500 */\n.chat-window-toggle {\n box-shadow:\n 0 4px 20px rgba(0, 196, 140, 0.5),\n 0 0 0 3px rgba(0, 196, 140, 0.1) !important;\n transition: box-shadow 0.2s ease, transform 0.2s ease !important;\n}\n\n.chat-window-toggle:hover {\n box-shadow:\n 0 8px 32px rgba(0, 196, 140, 0.65),\n 0 0 0 5px rgba(0, 196, 140, 0.15) !important;\n transform: scale(1.07) !important;\n}\n\n/* \u2500\u2500 Footer \u2500\u2500 */\n.chat-footer {\n border-top: 1px solid var(--chat--color-light-shade-50) !important;\n}\n\n/* \u2500\u2500 Scrollbar custom (Webkit) \u2500\u2500 */\n.chat-messages-list::-webkit-scrollbar {\n width: 4px;\n}\n\n.chat-messages-list::-webkit-scrollbar-track {\n background: transparent;\n}\n\n.chat-messages-list::-webkit-scrollbar-thumb {\n background: rgba(0, 196, 140, 0.3);\n border-radius: 4px;\n}\n\n.chat-messages-list::-webkit-scrollbar-thumb:hover {\n background: rgba(0, 196, 140, 0.55);\n}",
"responseMode": "responseNodes",
"inputPlaceholder": "Votre message..."
},
"initialMessages": "Bienvenue sur le chatbot Growth AI"
},
"typeVersion": 1.3
},
{
"id": "60ef6545-be26-481d-b351-8fd2d4e9dd52",
"name": "Claude Sonnet 4.6 Model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
816,
496
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-sonnet-4-6",
"cachedResultName": "Claude Sonnet 4.6"
},
"options": {}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "63b4a198-8048-4c28-8811-86cef9f1d43b",
"name": "Sticky Note13",
"type": "n8n-nodes-base.stickyNote",
"position": [
1408,
400
],
"parameters": {
"width": 1024,
"height": 400,
"content": "## Need more advanced automation solutions? Contact us for custom enterprise workflows!\n\n# Growth-AI.fr\n\n## https://www.linkedin.com/in/allanvaccarizi/\n## https://www.linkedin.com/in/hugo-marinier-%F0%9F%A7%B2-6537b633/"
},
"typeVersion": 1
},
{
"id": "5c081302-f173-4939-b00e-99d90ea73f67",
"name": "Sticky Note16",
"type": "n8n-nodes-base.stickyNote",
"position": [
1408,
-16
],
"parameters": {
"width": 1024,
"height": 400,
"content": ""
},
"typeVersion": 1
}
],
"connections": {
"Claude Sonnet 4.6 Model": {
"ai_languageModel": [
[
{
"node": "Chat Assistant Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Generate OpenAI Embeddings": {
"ai_embedding": [
[
{
"node": "Retrieve from Supabase Vectors",
"type": "ai_embedding",
"index": 0
}
]
]
},
"When Chat Message Received": {
"main": [
[
{
"node": "Chat Assistant Agent",
"type": "main",
"index": 0
}
]
]
},
"Retrieve from Supabase Vectors": {
"ai_tool": [
[
{
"node": "Chat Assistant Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Store Chat History in Postgres": {
"ai_memory": [
[
{
"node": "Chat Assistant Agent",
"type": "ai_memory",
"index": 0
}
]
]
}
}
}
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.
anthropicApiopenAiApipostgressupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
📺 Full walkthrough video: https://youtu.be/Z_l_T22px3U
Source: https://n8n.io/workflows/7381/ — 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.
The workflow operates through a three-step process that handles incoming chat messages with intelligent tool orchestration: Message Trigger: The node triggers whenever a user message arrives and passe
Chat Trigger, Memory Postgres Chat, OpenAI Embeddings +16
Build an All-Source Knowledge Assistant with Claude, RAG, Perplexity, and Drive. Uses chatTrigger, memoryPostgresChat, embeddingsOpenAi, rerankerCohere. Chat trigger; 40 nodes.
Chat Trigger, Memory Postgres Chat, OpenAI Embeddings +16
This workflow provides comprehensive AI-driven stock analysis, generating detailed deep reports by leveraging advanced vector-based data retrieval and API integrations for precise financial analytics
Tool Think, Supabase Vector Store, OpenAI Embeddings +9
RAG Agent supabase. Uses chatTrigger, lmChatOpenAi, embeddingsOpenAi, formTrigger. Chat trigger; 23 nodes.
Chat Trigger, OpenAI Chat, OpenAI Embeddings +7
This guide is designed for developers, data scientists, and AI enthusiasts who want to create intelligent chatbots capable of understanding and using custom data. Whether you are building a research a
Chat Trigger, OpenAI Chat, OpenAI Embeddings +6