This workflow follows the Documentdefaultdataloader → OpenAI Embeddings 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": "Update Bella Vista KB",
"nodes": [
{
"parameters": {
"formTitle": "Upload documents",
"formDescription": "Upload documents to the knowledge base. ",
"formFields": {
"values": [
{
"fieldLabel": "File",
"fieldType": "file",
"multipleFiles": false,
"requiredField": true
}
]
},
"options": {}
},
"type": "n8n-nodes-base.formTrigger",
"typeVersion": 2.2,
"position": [
0,
0
],
"id": "e2d1d389-8b1e-4d72-8d39-e4cb7a9efa90",
"name": "On form submission"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
80,
224
],
"id": "c51c96da-0c89-4641-a6f5-9a3c931988d9",
"name": "Embeddings OpenAI",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"dataType": "binary",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1.1,
"position": [
352,
208
],
"id": "1a9b9bfe-6a4e-4651-9485-afed019126f1",
"name": "Default Data Loader"
},
{
"parameters": {
"mode": "insert",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"typeVersion": 1.3,
"position": [
208,
0
],
"id": "4ce1be89-4a4d-459d-a69b-02fdf73599f9",
"name": "Postgres PGVector Store",
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
}
],
"connections": {
"On form submission": {
"main": [
[
{
"node": "Postgres PGVector Store",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Postgres PGVector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Postgres PGVector Store",
"type": "ai_document",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "8b19b909-c61a-4e60-95ba-9af7026827ad",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "OUeSSBG1nqrTlle0",
"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.
openAiApipostgres
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Update Bella Vista KB. Uses formTrigger, embeddingsOpenAi, documentDefaultDataLoader, vectorStorePGVector. Event-driven trigger; 4 nodes.
Source: https://github.com/Khuzaima-AI-2112/n8n-automation-templates/blob/master/01_Bussiness-&-Support/05_Customer-support-&-Booking-ai-agent-(Restaurant)/Update+Bella+Vista+KB.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 template shows how to use the Question and Answer tool to save costs in RAG use cases.
This workflow is ideal for: Professionals Project managers Sales and support teams Anyone managing high volumes of Gmail messages
Demo: RAG in n8n. Uses formTrigger, documentDefaultDataLoader, vectorStoreInMemory, agent. Event-driven trigger; 13 nodes.
Rag Ejemplo. Uses formTrigger, embeddingsOpenAi, documentDefaultDataLoader, vectorStoreInMemory. Event-driven trigger; 12 nodes.
[Lab] n8n RAG in memory vector. Uses formTrigger, embeddingsOpenAi, documentDefaultDataLoader, vectorStoreInMemory. Event-driven trigger; 12 nodes.