Built an intelligent semantic search system that allows users to find relevant results based on meaning rather than exact keywords. The system uses embedding models to convert text into vectors and performs similarity search to return the most relevant results. Implemented features such as: Natural language queries (e.g., “cars that are not black”) Vector similarity search using cosine similarity Handling partial negation and improving ranking relevance API integration for real-time search results This project demonstrates understanding of NLP, embeddings, and modern AI search techniques.