LegalEze
A Spring Boot–based Retrieval-Augmented Generation (RAG) legal assistant that delivers accurate, context-aware answers by grounding AI responses in verified legal documents using vector similarity search.
LegalEze is a Retrieval-Augmented Generation (RAG) based legal assistant built with Spring Boot that provides accurate and context-aware legal responses by grounding AI outputs in verified legal documents. The system processes and chunks legal texts, converts them into vector embeddings using the Gemini Embeddings API, and stores them in PostgreSQL with the pgvector extension for efficient similarity search. When a user submits a query, the application retrieves the most relevant document fragments through vector similarity matching and supplies them as context to a language model to generate reliable answers. This architecture reduces hallucinations, improves factual accuracy, and ensures that responses are supported by real legal sources.