This project utilizes a large language model (LLM) to bridge the gap between human intent and book metadata. The recommendations are powered by enriched metadata generated through heavy computational tasks using Google Colab’s T4 GPU runtime. The dataset consists of 7,000 books, including metadata like titles, authors, descriptions, and thumbnails (from Kaggle).
Project case study
AI Book Reccommendation
A semantic book recommendation system designed to find books based on natural language queries, categories, and emotional tones. Unlike traditional keyword search, this system understands the semantic meaning of your query.
Key outcomes
- Semantic Search: Finds books based on the content of their descriptions rather than just title matches.
- Emotion Analysis: Filters books by emotional tone (Happy, Surprising, Angry, Suspenseful, Sad).
- Category Filtering: Refine results by genre or category.
- Interactive Dashboard: Built with Gradio for a user-friendly web interface.