Building RAG for movie recommendations using Qdrant and AI
Workflow Description
An advanced template for building a Retrieval-Augmented Generation (RAG) system for movie recommendations, integrating Qdrant vector database with OpenAI models. The AI agent analyzes content and retrieves relevant recommendations based on user queries with contextual understanding and persistent memory.
How it works
- 1.Trigger workflow manually or via GitHub integration
- 2.Load and split movie data using text tokenization splitter
- 3.Generate vector embeddings via OpenAI and store in Qdrant
- 4.Process user queries through the AI agent with buffer window memory
- 5.Retrieve relevant movie recommendations from the vector store
- 6.Share results via Twitter/X or other configured channels
Use cases
- Content-aware movie recommendation engines for streaming platforms
- Automated search and ranking across large film databases
- Conversational AI agents specialized in entertainment content suggestions
Requirements
- OpenAI API keys for embeddings and language model access
- Qdrant server instance configured for vector storage and retrieval
- GitHub repository or data source containing movie metadata and descriptions
Service Value
Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (27)
When clicking ‘Test workflow’
Manual Trigger
GitHub
Github
Extract from File
Extract From File
Embeddings OpenAI
OpenAI
Default Data Loader
Document Default Data Loader
Token Splitter
Text Splitter Token Splitter
Qdrant Vector Store
Vector Store Qdrant
When chat message received
Chat Trigger
OpenAI Chat Model
OpenAI
Call n8n Workflow Tool
Tool Workflow
Window Buffer Memory
Memory Buffer Window
Execute Workflow Trigger
Execute Workflow Trigger
Merge
Merge
Split Out
Split Out
Split Out1
Split Out
Merge1
Merge
Aggregate
Aggregate
AI Agent
Agent
Embedding Recommendation Request with Open AI
HTTP Request
Embedding Anti-Recommendation Request with Open AI
HTTP Request
Extracting Embedding
Set
Extracting Embedding1
Set
Calling Qdrant Recommendation API
HTTP Request
Retrieving Recommended Movies Meta Data
HTTP Request
Selecting Fields Relevant for Agent
Set
Sticky Note
Sticky Note
Sticky Note1
Sticky Note