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 →
{
"active": false,
"connections": {
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Get row(s) in sheet",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Weaviate Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Get row(s) in sheet": {
"main": [
[
{
"node": "Weaviate Vector Store",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"HTTP Request": {
"main": [
[]
]
},
"Edit Fields": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Weaviate Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Preparar B\u00fasqueda": {
"main": [
[
{
"node": "Buscar en Weaviate",
"type": "main",
"index": 0
}
]
]
},
"Buscar en Weaviate": {
"main": [
[]
]
},
"Weaviate Vector Store1": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
],
"main": [
[]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "Weaviate Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
}
},
"createdAt": "2025-07-18T03:15:35.272Z",
"id": "yH7IrF2LzIVp4ZDu",
"isArchived": false,
"meta": {
"templateCredsSetupCompleted": true
},
"name": "weavite",
"nodes": [
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-288,
752
],
"id": "f0ade45f-70fd-4c20-8424-c2acd4d298ca",
"name": "When clicking \u2018Execute workflow\u2019"
},
{
"parameters": {
"mode": "insert",
"weaviateCollection": {
"__rl": true,
"value": "=ProductosNuevos",
"mode": "id"
},
"options": {
"clearStore": true
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreWeaviate",
"typeVersion": 1.3,
"position": [
128,
736
],
"id": "0be13c8a-af1e-4339-b549-42c314778f7f",
"name": "Weaviate Vector Store",
"credentials": {
"weaviateApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "text-embedding-ada-002",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
-48,
960
],
"id": "d588d898-9daa-46a9-8a31-f859fce5df45",
"name": "Embeddings OpenAI",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"documentId": {
"__rl": true,
"value": "1L_JcEQ9bno1dhNMZmjdgrrHsY71RG5gvmlvZBTSP_mc",
"mode": "list",
"cachedResultName": "weavite_BBDD",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1L_JcEQ9bno1dhNMZmjdgrrHsY71RG5gvmlvZBTSP_mc/edit?usp=drivesdk"
},
"sheetName": {
"__rl": true,
"value": 771354105,
"mode": "list",
"cachedResultName": "datos",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1L_JcEQ9bno1dhNMZmjdgrrHsY71RG5gvmlvZBTSP_mc/edit#gid=771354105"
},
"options": {}
},
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.6,
"position": [
-96,
752
],
"id": "33d5dd00-1da3-4879-9051-d56407ead8cf",
"name": "Get row(s) in sheet",
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"public": true,
"initialMessages": "",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
912,
416
],
"id": "978d4935-ea72-4b31-9f9d-77a57994d02e",
"name": "When chat message received"
},
{
"parameters": {
"method": "POST",
"url": "https://weavite.qeva.xyz/v1/graphql",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "query",
"value": "={ \n Get { \n ProductosNuevos(nearText: {concepts: [\"{{ $json.busqueda.toLowerCase().trim() }}\"]\n}) \n { \n nombre \n descripcion \n categoria\n marca\n } \n } \n}\n"
}
]
},
"options": {
"allowUnauthorizedCerts": true
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
80,
-256
],
"id": "4f272ca5-a5b5-4b7e-9a18-d2e132e31c8d",
"name": "HTTP Request"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "3dd2f672-e4ec-4a16-9b72-f147cd728ee8",
"name": "busqueda",
"value": "={{ $json.chatInput }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1136,
416
],
"id": "60f7c614-97f6-4981-8940-413de9da5339",
"name": "Edit Fields"
},
{
"parameters": {
"method": "DELETE",
"url": "https://weavite.qeva.xyz/v1/schema/Products",
"options": {
"allowUnauthorizedCerts": true
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
80,
-32
],
"id": "414d07a3-db3e-46cf-95c8-1cdb8f3a002a",
"name": "DELETE BBDD"
},
{
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "nombre",
"value": "={{ $json.nombre }}"
},
{
"name": "descripcion",
"value": "={{ $json.descripcion }}"
},
{
"name": "categoria",
"value": "={{ $json.categoria }}"
},
{
"name": "marca",
"value": "={{ $json.marca }}"
},
{
"name": "precio_final",
"value": "={{ $json.precio_final }}"
},
{
"name": "ingredientes_principales",
"value": "={{ $json.ingredientes_principales }}"
}
]
}
}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1.1,
"position": [
336,
976
],
"id": "e92e4b7b-8988-4f9f-9ae6-1b3f0514d036",
"name": "Default Data Loader"
},
{
"parameters": {
"content": "## Weavite \n**usar misma api que en portainer para embeddings**",
"height": 128,
"width": 288,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"position": [
1360,
-352
],
"typeVersion": 1,
"id": "b1c39ac0-e447-458f-983e-54aa82fc60c8",
"name": "Sticky Note"
},
{
"parameters": {
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.2,
"position": [
-752,
608
],
"name": "Preparar B\u00fasqueda",
"id": "e9b9a69b-474c-449d-9619-a77847859002"
},
{
"parameters": {
"url": "https://weavite.qeva.xyz/v1/graphql",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"bodyParameters": {
"parameters": [
{}
]
},
"options": {
"allowUnauthorizedCerts": true
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
-528,
608
],
"name": "Buscar en Weaviate",
"id": "1736caa1-09e9-457c-9b8f-220db457824a"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.busqueda }}",
"options": {
"systemMessage": "=vendes perfume y productos naturales, cremas, ademas debes dar precios de todo lo que te pregunte"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2.1,
"position": [
1488,
416
],
"id": "d305622b-a713-4170-a8ed-a430a7c12264",
"name": "AI Agent"
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolDescription": "={{ $json.busqueda }}",
"weaviateCollection": {
"__rl": true,
"value": "ProductosNuevos",
"mode": "list",
"cachedResultName": "ProductosNuevos"
},
"topK": 10,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreWeaviate",
"typeVersion": 1.3,
"position": [
1824,
640
],
"id": "fd7b9a5d-2b69-41a3-bad1-833d6487ee6b",
"name": "Weaviate Vector Store1",
"credentials": {
"weaviateApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "text-embedding-ada-002",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
1792,
848
],
"id": "fea36bbd-f8c6-4a89-857d-edba6c36b50d",
"name": "Embeddings OpenAI1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "google/gemini-2.5-flash",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"typeVersion": 1,
"position": [
1280,
704
],
"id": "d7ad82ab-50b7-485e-b290-cab8a53ef5ad",
"name": "OpenRouter Chat Model",
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('When chat message received').item.json.sessionId }}"
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
1600,
672
],
"id": "dee6c31f-2405-4dcd-91b4-1defc400ac4f",
"name": "Simple Memory"
}
],
"settings": {
"executionOrder": "v1",
"callerPolicy": "workflowsFromSameOwner",
"errorWorkflow": "EBMwLGTBawYqkZM1"
},
"staticData": null,
"tags": [],
"triggerCount": 1,
"updatedAt": "2025-07-27T22:13:37.108Z",
"versionId": "eb1a1607-e46c-42e5-906d-fc62deb49f2f"
}
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.
googleSheetsOAuth2ApiopenAiApiopenRouterApiweaviateApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow empowers content creators and researchers to effortlessly query and retrieve relevant information from a Weaviate vector database integrated with Google Sheets, delivering precise results via an interactive chat interface. It transforms static data into dynamic, searchable knowledge by generating OpenAI embeddings for efficient similarity matching, saving hours of manual searching and enabling quick insights from large datasets. The key step involves processing chat queries through the Weaviate vector store to fetch and rank the most pertinent Google Sheets entries, ensuring responses are both accurate and contextually rich.
Use this workflow when building AI-powered chatbots for knowledge bases stored in Google Sheets, particularly for event-driven interactions like customer support or internal Q&A systems. Avoid it for non-textual data or when real-time updates exceed Weaviate's capabilities, opting instead for simpler database queries. Common variations include swapping OpenAI embeddings for alternative models or adding HTTP requests to pull external data for enriched responses.
About this workflow
weavite. Uses vectorStoreWeaviate, embeddingsOpenAi, googleSheets, chatTrigger. Event-driven trigger; 17 nodes.
Source: https://github.com/fer336/workback/blob/328a48f11b1e3d69b6c7a911b4269e5d6497480b/workflows/yH7IrF2LzIVp4ZDu.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.
This intelligent chatbot leverages cutting-edge financial APIs and AI-driven analysis to deliver comprehensive stock research reports. Get instant access to professional-grade investment analysis that
This n8n template automatically classifies incoming emails (Sales, Support, Internal, Finance, Promotions) and routes them to a dedicated OpenAI LLM Agent for processing. Depending on the category, th
Chat with docs - 5minAI New version. Uses httpRequest, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Event-driven trigger; 62 nodes.
I prepared a detailed guide that illustrates the entire process of building an AI agent using Supabase and Google Drive within N8N workflows.
Code Extractfromfile. Uses manualTrigger, sort, httpRequest, compression. Event-driven trigger; 50 nodes.