Navigating the complexities of data within the legal framework presents a formidable challenge, as the corpora are often dense, verbose, and syntactically intricate. These characteristics necessitate sophisticated tools capable of not only accessing and interpreting the content but also effectively organizing it for practical use, particularly in applications such as chatbots or Retrieval Augmented Generation (RAG) systems. The existing legal databases, vital for the computationally intensive applications mentioned earlier, typically lack the systematic structure and indexing required for straightforward application, further complicating their integration into advanced conversational systems. The proposed work underscores the pivotal role of Generative AI, emerging as a dual-purpose tool by facilitating the structuring of vast, complex datasets and leveraging the optimized knowledge base. This dual functionality has been proven to significantly enhance the quality and interpretability of the outputs, fostering human validation, thereby mitigating the computational load and reducing the occurrence of inaccuracies commonly associated with Language Models (LMs).