AskYourDocs: A Retrieval-Augmented Generation (RAG) Powered Document Assistant for Intelligent Information Retrieval
DOI:
https://doi.org/10.5281/zenodo.2167259Keywords:
Retrieval-Augmented Generation, Semantic Search, Vector Database, FAISS, Sentence Transformers, Large Language Model, Natural Language Processing, Document Assistant, Google Gemini, Streamlit.Abstract
The rapid growth of electronic documents in academic, research, legal and enterprise environments has made effective information retrieval progressively more difficult. Conventional keyword-based search approaches are unable to understand the semantic meaning and the contextual intent of the user query, leading to incomplete or irrelevant results. In this paper, we introduce AskYourDocs, a RAG-based intelligent document assistant that enables users to query documents in natural language. The system accepts multiple document formats such as PDF, DOCX, and TXT. It processes the documents by cleaning the text and splitting it into smaller chunks. These chunks are transformed into semantic embeddings using Sentence-Transformer models and stored in a vector database, FAISS. When a user query comes in, the system performs a vector similarity search to retrieve the most relevant document segments and uses them as grounding context for the Google Gemini Large Language Model (LLM) to generate accurate, document-grounded responses. Voice input and text-to-speech output are also integrated into the system for better accessibility. The system is implemented through an interactive interface built with Streamlit. AskYourDocs combines semantic retrieval and generative AI to reduce hallucinated responses and improve the reliability of document-based question answering, providing a practical solution for education, research, legal, healthcare and enterprise use cases.
References
Gijre, S., Agrawal, R., Laddha, P., & Keswani, G. (2024). Enhancing question answering with knowledge graph retrieval and generation using LLMs. In Proceedings of the 2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA) (pp. 1–6). IEEE. https://doi.org/10.1109/ICAIQSA64000.2024.10882212
Heydari, M. H., Hemmat, A., Naman, E., & Fatemi, A. (2024). Context awareness gate for retrieval-augmented generation. In Proceedings of the 2024 15th International Conference on Information and Knowledge Technology (IKT) (pp. 260–264). IEEE. https://doi.org/10.1109/IKT65497.2024.10892659
Johnson, J., Douze, M., & Jégou, H. (2021). Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 7(3), 535–547. https://doi.org/10.1109/TBDATA.2019.2921572
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (pp. 9459–9474). Curran Associates.
Mengmeng, S., Zhibin, L., Qingwei, W., Man, H., & Feiyang, X. (2024). An effective retrieval method to improve RAG performance. In Proceedings of the 2024 7th International Conference on Data Science and Information Technology (DSIT) (pp. 1–5). IEEE. https://doi.org/10.1109/DSIT61374.2024.10881380
Putri, M. R., [+ additional authors]. (2024). Simplification of embedding process in RAG for optimizing QA chatbot.
Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (pp. 3982–3992). Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1410
Shan, R. (2024). OpenRAG: Open-source retrieval-augmented generation architecture for personalized learning. In Proceedings of the 2024 4th International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC) (pp. 212–216). IEEE. https://doi.org/10.1109/ICAIRC64177.2024.10900069
Singh, A., Gupta, R., & Kumar, P. (2025). Agentic retrieval-augmented generation: Enabling autonomous reasoning in RAG systems. arXiv. https://doi.org/10.48550/arXiv.2501.09136
Tural, B., [+ additional authors]. (2024). Retrieval-augmented generation (RAG) and LLM integration.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 V. Neelima, Panuganti Varshini, Shaik Zohaib Ur Rahman, Purella Sravya, Mohammed Ansaar Ahmed
This work is licensed under a Creative Commons Attribution 4.0 International License.