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{180709,
        author = {Abdul Hai and Dr. Gousiya Begum and Dr. K. Rajitha and R. Mohan Krishna Ayyapa},
        title = {A Hybrid Retrieval-Augmented Conversational AI System using LangChain and FAISS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {2698-2702},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180709},
        abstract = {This paper presents a conversational AI system capable of retrieving and synthesizing information from PDFs and web URLs using a hybrid retrieval-augmented generation (RAG) framework. The system integrates FastAPI for backend processing and Streamlit for a lightweight, user-friendly interface. By combining BM25 for keyword search with FAISS-based semantic analysis, the platform offers high retrieval accuracy and contextual relevance. Features such as document summarization, persistent conversation history (via SQLite), and modular architecture make the system well-suited for academic, research, and professional use.},
        keywords = {BM25, FAISS, LangChain, RAG},
        month = {June},
        }