This workflow outlines the creation of an intelligent movie recommendation chatbot leveraging n8n, OpenAI, and Qdrant vector database. The workflow begins with manual initiation for testing purposes, fetching a dataset of top movies from GitHub, and extracting relevant movie data. It then generates text embeddings for movie descriptions using OpenAI, which are stored in Qdrant for efficient similarity search. When a user sends a chat message with preferences, the AI model processes the request, and the system fetches top movie recommendations based on vector similarity. The workflow retrieves movie metadata, filters relevant information, and presents personalized suggestions. This setup is ideal for building dynamic, AI-powered movie recommendation services that improve with user interactions.
Building a Movie Recommendation Chatbot with n8n, OpenAI, and Qdrant
| Node Count | >20 Nodes |
|---|---|
| Nodes Used | @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.chatTrigger, @n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsOpenAi, @n8n/n8n-nodes-langchain.lmChatOpenAi, @n8n/n8n-nodes-langchain.memoryBufferWindow, @n8n/n8n-nodes-langchain.textSplitterTokenSplitter, @n8n/n8n-nodes-langchain.toolWorkflow, @n8n/n8n-nodes-langchain.vectorStoreQdrant, aggregate, executeWorkflowTrigger, extractFromFile, github, httpRequest, manualTrigger, merge, set, splitOut, stickyNote |
Be the first to review “Building a Movie Recommendation Chatbot with n8n, OpenAI, and Qdrant”
Reviews
There are no reviews yet.