Pragya: An AI-Based Semantic Recommendation System for Sanskrit Subhasitas

TL;DR

Pragya is an innovative AI system that combines retrieval and generation techniques to semantically recommend, translate, and explain Sanskrit Subhasitas, making this cultural heritage more accessible in the digital age.

Contribution

This work introduces the first integrated retrieval-augmented generation framework for Sanskrit Subhasitas, enhancing semantic relevance and accessibility.

Findings

Semantic retrieval outperforms keyword matching in relevance.

Generated summaries improve user accessibility.

System effectively produces transliterations and translations.

Abstract

Sanskrit Subhasitas encapsulate centuries of cultural and philosophical wisdom, yet remain underutilized in the digital age due to linguistic and contextual barriers. In this work, we present Pragya, a retrieval-augmented generation (RAG) framework for semantic recommendation of Subhasitas. We curate a dataset of 200 verses annotated with thematic tags such as motivation, friendship, and compassion. Using sentence embeddings (IndicBERT), the system retrieves top-k verses relevant to user queries. The retrieved results are then passed to a generative model (Mistral LLM) to produce transliterations, translations, and contextual explanations. Experimental evaluation demonstrates that semantic retrieval significantly outperforms keyword matching in precision and relevance, while user studies highlight improved accessibility through generated summaries. To our knowledge, this is the first attempt at integrating retrieval and generation for Sanskrit Subhasitas, bridging cultural heritage with modern applied AI.