Akash Narayan This workflow corresponds to n8n.io template #17764 — we link there as the canonical source.
This workflow follows the Documentdefaultdataloader → Textsplitterrecursivecharactertextsplitter 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": "9Kv1TmgV5VxVUUH0",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Local RAG Indexer (n8n + Qdrant + Ollama)",
"tags": [],
"nodes": [
{
"id": "002111ae-d102-4a0d-b508-c5004d3134a0",
"name": "When clicking \u2018Execute workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
176,
-48
],
"parameters": {},
"typeVersion": 1
},
{
"id": "ecf92f10-ccbb-464b-81a1-1061e29e488a",
"name": "Read/Write Files from Disk",
"type": "n8n-nodes-base.readWriteFile",
"position": [
384,
-48
],
"parameters": {
"options": {},
"fileSelector": "example: /path/to/your/document.txt"
},
"executeOnce": true,
"notesInFlow": false,
"retryOnFail": true,
"typeVersion": 1.1,
"alwaysOutputData": true
},
{
"id": "6b78dc27-05d8-426f-9660-f4577821065f",
"name": "Extract from File",
"type": "n8n-nodes-base.extractFromFile",
"position": [
592,
-48
],
"parameters": {
"options": {},
"operation": "text"
},
"typeVersion": 1.1
},
{
"id": "15e1c2bd-1ee2-48fe-ac00-779724188901",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
800,
-48
],
"parameters": {
"mode": "insert",
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "handbook"
}
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "ece5b976-a62e-40c3-860b-fb0e970da37b",
"name": "Embeddings Ollama",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"position": [
880,
160
],
"parameters": {
"model": "nomic-embed-text:latest"
},
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "636439be-a4a7-4410-a5f4-29e64575092b",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1008,
128
],
"parameters": {
"options": {},
"textSplittingMode": "custom"
},
"typeVersion": 1.1
},
{
"id": "4cab5b92-f331-4e41-af01-0eafc0c5a3ac",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1104,
336
],
"parameters": {
"options": {},
"chunkOverlap": 200
},
"typeVersion": 1
},
{
"id": "9246ca7a-7c77-4e21-86cb-aee755d2445c",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
48,
-320
],
"parameters": {
"color": "#5B0617",
"width": 288,
"height": 80,
"content": "AIR-GAPPED DOCUMENT INGESTION & VECTOR MAPPING"
},
"typeVersion": 1
},
{
"id": "936e6b49-ba5f-41d3-a078-7c032145def4",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-288,
-208
],
"parameters": {
"color": "#000000",
"width": 1008,
"height": 80,
"content": "Pipeline: Local File Ingestion \u2192 Recursive Character Splitting (1,000-char / 200 overlap) \u2192 Local Embeddings (nomic-embed-text)\nSecurity: 100% On-Premise Indexing | Zero Data Leakage | 1 Document Mapped to 13 Semantic Vector Chunks in Qdrant"
},
"typeVersion": 1
},
{
"id": "659eb643-5d81-469b-86b4-33a69adabdf2",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
144,
144
],
"parameters": {
"color": 4,
"width": 368,
"height": 320,
"content": "SETUP STEP 1: Point this node at your own file.\n\nDouble click the \"Read/Write Files from Disk\" node above.\n\nReplace the file path with the path to your own document.\n\nThis example uses a plain .txt file for PDFs, swap the \"Extract from File\" node's operation to PDF.\n"
},
"typeVersion": 1
},
{
"id": "a89c6dad-715a-4189-b57d-ac3d77e2dc9f",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
576,
144
],
"parameters": {
"color": 4,
"width": 256,
"content": "SETUP STEP 2: Requires Ollama running on your computer, with the nomic-embed-text model installed.\n\nInstall Ollama, then in your terminal run:\nollama pull nomic-embed-text"
},
"typeVersion": 1
},
{
"id": "e482b63d-268e-4448-b5c7-1724b01253a4",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
800,
-240
],
"parameters": {
"color": 4,
"width": 512,
"content": "SETUP STEP 3: Create a Qdrant credential in n8n\n(your Qdrant URL + API key) and set a Collection Name\non this node. \n\nWrite that collection name down you must\ntype the EXACT SAME name into the \"Ask\" workflow's\nQdrant node, or that workflow will find nothing.\n"
},
"typeVersion": 1
},
{
"id": "f16ce64c-8d7e-4e90-b37f-9477dadc9efa",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
304,
528
],
"parameters": {
"width": 416,
"height": 176,
"content": "HOW TO RUN: Click the orange \"Execute workflow\" button\nto index a document. \n\nRun this once per new document,\nbefore using the \"Ask\" workflow to query it.\n"
},
"typeVersion": 1
},
{
"id": "0dbaec2c-4344-4f2e-ac89-3df974070eba",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-416,
-64
],
"parameters": {
"width": 512,
"height": 224,
"content": " IMPORTANT: This node only sees files inside your Docker\ncontainer's mounted volume, not your whole computer.\n\nCopy your document into the folder your docker-compose.yml\nmounts (commonly \"./shared\") and reference the CONTAINER\npath here (e.g. /data/shared/yourfile.pdf), not the Mac path.\n\nThis workflow will not work on n8n Cloud only self-hosted.\n"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"binaryMode": "separate",
"availableInMCP": false,
"executionOrder": "v1"
},
"versionId": "4e11216a-4ff4-478a-8b0a-4e21b842129d",
"nodeGroups": [],
"connections": {
"Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Qdrant Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Read/Write Files from Disk": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Read/Write Files from Disk",
"type": "main",
"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
This workflow ingests a local document file, splits it into chunks, generates embeddings with Ollama (nomic-embed-text), and stores the vectors in a Qdrant collection for on-prem RAG indexing. Runs manually when you click Execute workflow in n8n. Reads a document from disk from…
Source: https://n8n.io/workflows/17764/ — 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.
An on-premises, domain-specific AI assistant for Kaggle (tested on binary disaster-tweet classification), combining LLM, an n8n workflow engine, and Qdrant-backed Retrieval-Augmented Generation (RAG).
This workflow ingests a local PDF into Qdrant with Ollama embeddings, then supports hybrid retrieval by querying Qdrant with both dense vectors and BM25 sparse vectors from an n8n chat trigger. Starts
Breakdown Documents Into Study Notes Using Templating Mistralai And Qdrant. Uses localFileTrigger, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsMistralCloud. Event-
Localfile Wait. Uses localFileTrigger, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsMistralCloud. Event-driven trigger; 42 nodes.
Workflow 2339. Uses localFileTrigger, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsMistralCloud. Event-driven trigger; 42 nodes.