AI Agents

Process and Store Documents in Vector Database

13 nodes 296 146 Automatic trigger
Download

Workflow Description

An automated workflow that loads documents from FTP, splits them into text chunks, generates semantic embeddings via OpenAI, and stores them in Qdrant vector database for intelligent retrieval and search.

How it works

  1. 1.Trigger workflow manually or on file arrival event
  2. 2.Load documents from FTP server
  3. 3.Split text into sized chunks
  4. 4.Generate embeddings using OpenAI API
  5. 5.Store embeddings and metadata in Qdrant database

Use cases

  • Build semantic search engine for document repositories
  • Automate indexing of files from FTP sources
  • Set up retrieval layer for RAG-based AI applications

Requirements

  • Valid FTP credentials and read access permissions
  • OpenAI API key with embedding model access
  • Running Qdrant instance with network connectivity
  • Support for multiple document formats

Service Value

Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.

Apps Used

Vector Store OpenAI Document Default Data Loader Text Splitter Ftp Split In Batches

Details

Trigger Automatic trigger
Nodes 13
Apps 6
Views 296
Downloads 146

How to Use

  1. 1.Click "Download Template"
  2. 2.Open your n8n dashboard
  3. 3.Go to Workflows > Import from File
  4. 4.Select downloaded file and configure credentials

Nodes Used (13)

/

Qdrant Vector Store

Vector Store Qdrant

#1

When clicking ‘Test workflow’

Manual Trigger

#2

Embeddings OpenAI

OpenAI

#3

Default Data Loader

Document Default Data Loader

#4

Character Text Splitter

Text Splitter Character Text Splitter

#5

Sticky Note

Sticky Note

#6

Sticky Note1

Sticky Note

#7

Sticky Note2

Sticky Note

#8

Sticky Note3

Sticky Note

#9

List all the files

Ftp

#10

Loop over one item

Split In Batches

#11

Downloading item

Ftp

#12

Sticky Note4

Sticky Note

#13