This repository facilitates the integration of a comprehensive movie dataset from Kaggle into a PostgreSQL database, setting the foundation for a sophisticated movie recommendation system.
The dataset, structured in JSON format, contains detailed plot descriptions and can be directly accessed here: Movie Plots Dataset.
This initiative is part of a larger project to develop a robust movie recommendation engine. The system is designed to suggest films to users based on plot similarities and other relevant factors. By populating the PostgreSQL database with Kaggle's dataset, we enable the use of advanced vector search techniques powered by TensorFlow, PGVector, and Next.js.
- Yiwei Zhang
- Shizhe Zhang
- Weiran Zhao
- DevPost: For a detailed narrative on the project's evolution and insights, visit the DevPost project page.
- Kaggle: The source of the dataset is available on Kaggle, providing a rich repository of movie plots.
- Vector Search Web App: The project's web application, ZZZ - MovieSearch Client, demonstrates the application of vector search to recommend movies, tying together the populated database with a user-friendly interface.
Our goal is to enhance the movie-watching experience by offering tailored recommendations through a user-centric, data-and-semantic-driven search approach.