Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200369,
        author = {Pandalaneni Mani Prakash and Dr. K. Baalaji and Paloju Venu Gopal Sai and Parkepalli Aditya Sai Ram and Paramkusham Varun},
        title = {Multi-Lingual Legal Document Assistant},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {1259-1264},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200369},
        abstract = {Legal documents are difficult for many readers because contractual language, statutory references, exception-heavy clauses, and procedural terminology demand careful interpretation. This work presents a multilingual legal document assistant that transforms uploaded files into a document-grounded question-answering workspace. The system follows a retrieval-augmented generation pipeline in which legal files are parsed, normalized, segmented into semantically coherent chunks, embedded, and indexed in a vector database for evidence retrieval. At query time, the assistant retrieves the most relevant clauses, assembles a bounded context, and generates an explanation that stays tied to the uploaded material through citation-aware answer construction. The architecture also supports bilingual interaction and voice-first access through speech playback and phone-call integration, making the platform usable for readers who prefer Tamil or spoken responses over conventional text-heavy interfaces. The design combines a web dashboard, authentication layer, document service, RAG orchestrator, chat API, language adapter, and audio service with external components such as Pinecone, file storage, Gemini 2.5 Flash, ElevenLabs, and Twilio. The resulting framework improves clause discoverability, traceability, and accessibility while preserving a modular cloud deployment model suitable for future extension.},
        keywords = {retrieval-augmented generation, legal document analysis, multilingual question answering, vector database, citation grounding, voice interface, telephony integration, cloud deployment},
        month = {May},
        }