RAG Chatbot for Movie Recommendations with Qdrant & OpenAI

This workflow creates a sophisticated recommendation system powered by Retrieval-Augmented Generation (RAG) to deliver accurate, hallucination-free movie suggestions. It leverages the IMDB top-1000 dataset, embedding movie descriptions with OpenAI models into a Qdrant vector database. Users interact via a chat interface with an AI agent that interprets wishes and 'big no's' (e.g., 'A movie about wizards but not Harry Potter'), triggering a workflow to fetch top-3 recommendations using Qdrant's Recommendation API.

Key components include data ingestion from GitHub (where the IMDB dataset is uploaded), vectorization and storage in Qdrant, and an intelligent agent workflow for query processing. Benefits include precise personalization, avoidance of AI fabrications common in pure generative models, scalability for similar domains like books or products, and ease of deployment with free-tier Qdrant Cloud.

Use cases span entertainment apps, content discovery platforms, or custom recommendation engines. Adapt it for e-commerce product recs, job matching, or any semantic search scenario. Setup requires Qdrant/OpenAI/GitHub credentials and dataset upload, making it accessible yet powerful for developers building production-grade AI tools.