AI Agents

Build an Intelligent Movie Recommendation System with Qdrant

27 nodes 327 175 Automatic trigger
Download

Workflow Description

An automation that constructs a retrieval-augmented generation (RAG) system for movie recommendations, integrating Qdrant vector storage with an intelligent agent that extracts data from GitHub, processes it, and generates personalized suggestions via OpenAI.

How it works

  1. 1.Extract movie data from GitHub files and split content into manageable text chunks for processing
  2. 2.Convert text into numerical vectors using OpenAI embeddings and store them in Qdrant vector database
  3. 3.Receive user queries through chat interface and execute semantic search across the vector repository
  4. 4.Generate personalized movie recommendations based on retrieved results and conversation context
  5. 5.Publish recommendations to social media or deliver them to the user

Use cases

  • Build an intelligent movie recommendation engine that understands user preferences and suggests relevant content
  • Create a natural language movie query system that handles complex and loosely-defined questions about films

Requirements

  • Valid OpenAI API key for embeddings generation and AI-powered recommendations
  • Active Qdrant vector store instance with sufficient storage capacity for movie data embeddings
  • Structured movie dataset files hosted in a GitHub repository

Service Value

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

Apps Used

GitHub OpenAI Document Default Data Loader Text Splitter Vector Store Chat Trigger Tool Memory Twitter/X AI Agent

Details

Trigger Automatic trigger
Nodes 27
Apps 10
Views 327
Downloads 175

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 (27)

/

When clicking ‘Test workflow’

Manual Trigger

#1

GitHub

Github

#2

Extract from File

Extract From File

#3

Embeddings OpenAI

OpenAI

#4

Default Data Loader

Document Default Data Loader

#5

Token Splitter

Text Splitter Token Splitter

#6

Qdrant Vector Store

Vector Store Qdrant

#7

When chat message received

Chat Trigger

#8

OpenAI Chat Model

OpenAI

#9

Call n8n Workflow Tool

Tool Workflow

#10

Window Buffer Memory

Memory Buffer Window

#11

Execute Workflow Trigger

Execute Workflow Trigger

#12

Merge

Merge

#13

Split Out

Split Out

#14

Split Out1

Split Out

#15

Merge1

Merge

#16

Aggregate

Aggregate

#17

AI Agent

Agent

#18

Embedding Recommendation Request with Open AI

HTTP Request

#19

Embedding Anti-Recommendation Request with Open AI

HTTP Request

#20

Extracting Embedding

Set

#21

Extracting Embedding1

Set

#22

Calling Qdrant Recommendation API

HTTP Request

#23

Retrieving Recommended Movies Meta Data

HTTP Request

#24

Selecting Fields Relevant for Agent

Set

#25

Sticky Note

Sticky Note

#26

Sticky Note1

Sticky Note

#27