Thomas Janssen This workflow corresponds to n8n.io template #5148 — 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 →
{
"id": "L9nteAq0NLYqIGxH",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "RAG Pipeline",
"tags": [],
"nodes": [
{
"id": "a00e5b5b-1cc1-4272-9790-8ffde3c92efb",
"name": "On form submission",
"type": "n8n-nodes-base.formTrigger",
"position": [
0,
0
],
"parameters": {
"options": {},
"formTitle": "Add your file here",
"formFields": {
"values": [
{
"fieldType": "file",
"fieldLabel": "File",
"requiredField": true,
"acceptFileTypes": ".pdf"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "1218186e-a93e-4e05-b47e-a395f28cf5f9",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
220,
0
],
"parameters": {
"mode": "insert",
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "rag_collection"
}
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "9c7fb858-b571-4626-b976-d3e1995c464b",
"name": "Embeddings Ollama",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"position": [
60,
220
],
"parameters": {
"model": "mxbai-embed-large:latest"
},
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "af14443b-ae01-48dc-8552-5ded7a27fce2",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
360,
220
],
"parameters": {
"options": {},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "660380c5-63da-4404-98e6-f9c0ee9aaa90",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
460,
440
],
"parameters": {
"options": {},
"chunkSize": 200,
"chunkOverlap": 50
},
"typeVersion": 1
},
{
"id": "49dbe387-751f-4a2e-8803-290bc2c06ec5",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-140,
-100
],
"parameters": {
"color": 3,
"width": 840,
"height": 700,
"content": "## Data Ingestion\n**Add data to the semantic database"
},
"typeVersion": 1
},
{
"id": "45683271-af59-41d0-9e69-af721d566661",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
940,
-20
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "af562588-2e8c-4c0b-b041-d6fc8c0affd0",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1220,
-20
],
"parameters": {
"options": {
"systemMessage": "You are a helpful assistant. You have access to a tool to retrieve data from a semantic database to answer questions. Always provide arguments when you execute the tool"
}
},
"typeVersion": 2
},
{
"id": "4d924b4a-fe07-4606-8385-613d6ea14991",
"name": "Ollama Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"position": [
1060,
220
],
"parameters": {
"options": {}
},
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "de87b7bb-6fec-4d8f-a77a-25bc3a30a038",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
1260,
220
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "16261539-5218-4df1-8b14-915dd3377167",
"name": "Qdrant Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
1540,
240
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "retriever",
"toolDescription": "Retrieve data from a semantic database to answer questions",
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "rag_collection"
}
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "57d3be1d-73cd-4464-a3f3-7dd4a3157cdf",
"name": "Embeddings Ollama1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"position": [
1460,
440
],
"parameters": {
"model": "mxbai-embed-large:latest"
},
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "5919cc58-05f4-42c8-aada-3782a16574d9",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
740,
-100
],
"parameters": {
"color": 4,
"width": 1200,
"height": 700,
"content": "## RAG Chatbot\n**Chat with your data"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "895c0261-fbf5-4bb6-9581-4cea3c4d20bd",
"connections": {
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Ollama Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings Ollama1": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"On form submission": {
"main": [
[
{
"node": "Qdrant Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Qdrant Vector Store1": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"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.
ollamaApiqdrantApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Click here to view the YouTube Tutorial
Source: https://n8n.io/workflows/5148/ — 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 workflow implements a complete Retrieval-Augmented Generation (RAG) knowledge assistant with built-in document ingestion, conversational AI, and automated analytics using n8n, OpenAI, and Pinecon
Indexation. Uses formTrigger, embeddingsOllama, textSplitterRecursiveCharacterTextSplitter, modelSelector. Event-driven trigger; 25 nodes.
Local RAG AI Agent. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Event-driven trigger; 24 nodes.
V1 ocal RAG AI Agent. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Event-driven trigger; 24 nodes.
This template is designed for podcasters, researchers, educators, product teams, and support teams who work with audio content and want to turn it into searchable knowledge. It is especially useful fo