AI Recommendation Engine

This project implements a sophisticated, two-stage recommendation pipeline designed to provide highly relevant suggestions from a large catalog of items. Unlike simple search engines that rely on keyword matching, this system understands the semantic meaning of item content, enabling it to find conceptually similar items and then apply a layer of learned business logic to intelligently rank the results. The architecture is built using a modern microservices pattern, ensuring that each component is decoupled, independently scalable, and maintains a single responsibility. This makes the system robust, maintainable, and ready for production deployment.

Key Features

• Microservice Architecture: Independent services for vectorization, re-ranking, and matching communicate over a network.
• Semantic Vector Search: Deep learning model (sentence-transformers) converts text-based content into rich numerical vectors for meaning-based matching.
• Two-Stage Recommendation Pipeline:
  • Candidate Generation: Efficient first pass uses ChromaDB to retrieve a broad set of relevant candidates.
  • Intelligent Re-ranking: Second stage uses a trained XGBoost model to re-rank candidates based on learned business logic.
• Decoupled & Reusable Feature Engineering: Centralized feature generation logic eliminates training-serving skew and ensures consistency.