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 →
{
"id": "YoUP55V241b9F2ze",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Qdrant Vector Database Embedding Pipeline",
"tags": [],
"nodes": [
{
"id": "934ffad4-c93e-40c1-b4fd-1c09b518a9c3",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
460,
-460
],
"parameters": {
"mode": "insert",
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "list",
"value": "sv_lang_data",
"cachedResultName": "sv_lang_data"
},
"embeddingBatchSize": 100
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "4127d85d-45c9-4536-a15d-08af9dfdcfa8",
"name": "When clicking \u2018Test workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-960,
-460
],
"parameters": {},
"typeVersion": 1
},
{
"id": "abb61b81-72e0-468e-855b-72402db828fc",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
400,
-240
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "e9ae24be-6da9-4c04-b891-7e450f505e02",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
780,
-180
],
"parameters": {
"options": {},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "9aff896d-4edb-494c-b84f-ede4e47db1e3",
"name": "Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter",
"position": [
800,
20
],
"parameters": {
"separator": "\"chunk_id\""
},
"typeVersion": 1
},
{
"id": "a083a47e-a835-4323-86a8-a2eaed226aaa",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-760,
-680
],
"parameters": {
"color": 4,
"width": 260,
"height": 200,
"content": "### Fetch JSON File List\n**Node:** FTP (all files)\n**Operation:** List\n**Path:** <file path>\n\nRecursively lists all .json files prepared for embedding."
},
"typeVersion": 1
},
{
"id": "072ae9dc-c1cd-4ceb-954a-6b6b1b984e29",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-460,
-660
],
"parameters": {
"color": 5,
"height": 180,
"content": "### Iterate Over Files\n**Node:** Loop Over Items\n\nBatches each file path individually for processing."
},
"typeVersion": 1
},
{
"id": "08d852f2-f1de-42ce-b882-1dc1343ed967",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-160,
-700
],
"parameters": {
"color": 4,
"width": 420,
"height": 220,
"content": "### Download Each File\n**Node:** FTP (1 file download)\n\nDownloads the current file in binary form using:\n```\nPath = file_path/{{ $json.name }}\n```"
},
"typeVersion": 1
},
{
"id": "905c3d74-2817-4aa3-865d-51e972cbbb5a",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
920,
-80
],
"parameters": {
"color": 3,
"width": 320,
"height": 400,
"content": "### Parse JSON Document (Default Data Loader)\n**Node:** Default Data Loader\n**Loader Type**: binary\n- Converts JSON structure into a document format compatible with embedding.\n\n\n### Split into Smaller Chunks\n**Node:** Character Text Splitter\n**Split by:** \"chunk_id\" or custom logic based on chunk formatting\n\nOptional node if chunk size normalization is required before embedding."
},
"typeVersion": 1
},
{
"id": "9fb8e5be-3ee1-42b4-a858-40bc6afcf457",
"name": "List all the files",
"type": "n8n-nodes-base.ftp",
"position": [
-700,
-460
],
"parameters": {
"path": "Oracle/AI/embedding/svenska",
"operation": "list"
},
"credentials": {
"ftp": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "6f8d0390-5851-44ca-9712-0ae51f9a22ef",
"name": "Loop over one item",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-400,
-460
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "1c89a4a9-ec68-4c48-b7bc-74f5b30d8ac2",
"name": "Downloading item",
"type": "n8n-nodes-base.ftp",
"position": [
-40,
-440
],
"parameters": {
"path": "=Oracle/AI/embedding/svenska/{{ $json.name }}",
"binaryPropertyName": "binary.data"
},
"credentials": {
"ftp": {
"name": "<your credential>"
}
},
"typeVersion": 1,
"alwaysOutputData": true
},
{
"id": "01ca4ee3-5f1c-4977-a7f9-88e46db580ad",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
360,
-960
],
"parameters": {
"width": 480,
"height": 460,
"content": "### Store in Vector DB\n**Node:** Qdrant Vector Store\n**Batch Size:** 100\n\n**Collection:** <collection_name>\nSends cleaned text chunks to OpenAI to get embeddings (1536 dim for text-embedding-ada-002)\n\n#### collection settings in Qdrant cluster\n```\nPUT /collections/{collection_name}\n{\n \"vectors\": {\n \"size\": 1536,\n \"distance\": \"Cosine\"\n }\n}\n```\nEmbed Chunks\n**Node:** Embeddings OpenAI\nPushes the embedded chunks (with metadata) into Qdrant for semantic retrieval."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "c71fca63-26e9-4795-9a00-942dab6d07ce",
"connections": {
"Downloading item": {
"main": [
[
{
"node": "Qdrant Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"List all the files": {
"main": [
[
{
"node": "Loop over one item",
"type": "main",
"index": 0
}
]
]
},
"Loop over one item": {
"main": [
[],
[
{
"node": "Downloading item",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Qdrant Vector Store": {
"main": [
[
{
"node": "List all the files",
"type": "main",
"index": 0
}
]
]
},
"Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "List all the files",
"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.
ftpopenAiApiqdrantApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This pipeline transforms your unstructured text data into searchable vector embeddings stored in Qdrant, enabling efficient similarity searches and AI-powered retrieval for applications like recommendation systems or knowledge bases. It's ideal for developers and data teams handling large document collections who need to integrate semantic search without building everything from scratch. The key step involves using OpenAI's embeddings model to convert split text chunks into vectors, which are then upserted into Qdrant for quick querying.
Use this workflow when onboarding new datasets for RAG-based chatbots or when automating content indexing in event-driven setups, such as after FTP uploads. Avoid it for real-time processing of tiny files, where simpler tools suffice, or if you require custom embedding models beyond OpenAI. Common variations include swapping the text splitter for recursive chunking on codebases or adding a vector store retriever node for immediate search testing.
About this workflow
Qdrant Vector Database Embedding Pipeline. Uses vectorStoreQdrant, manualTrigger, embeddingsOpenAi, documentDefaultDataLoader. Event-driven trigger; 13 nodes.
Source: https://github.com/Zie619/n8n-workflows — 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 is designed for one purpose only, to bulk-upload structured JSON articles from an FTP server into a Qdrant vector database for use in LLM-powered semantic search, RAG systems, or AI as
Alfred (funcional). Uses gmailTool, googleCalendarTool, gmail, embeddingsOpenAi. Event-driven trigger; 83 nodes.
🤖📈 This workflow is my personal solution for the Agentic Arena Community Contest, where the goal is to build a Retrieval-Augmented Generation (RAG) AI agent capable of answering questions based on a p
n8n-4-1: Qdrant. Uses vectorStoreQdrant, embeddingsOpenAi, textClassifier, chainSummarization. Event-driven trigger; 27 nodes.
> Summary: > This workflow listens for new Gmail messages, extracts and cleans email content, generates embeddings via OpenAI, stores them in a Qdrant vector database, and then enables a Retriev