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{203688,
        author = {Anurag Shakya and Shubham kumar},
        title = {Intent Aware RAG assistant for technical documentation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2596-2602},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203688},
        abstract = {Big pdf and research papers are some of the technical documents that are too long and not easily comprehensible. The traditional methods of searching by using keywords fail to comprehend the context, the Large Language Models (LLMs) can produce misinformation when the solution to the question is not provided in the document So, there is Intent-Aware Retrieval-Augmented Generation (RAG) Assistant that helps the user to engage with the technical documents in the PDF format using natural language. The first step in the system is to determine the query type, i.e., whether it is general or specific, then you choose the appropriate retrieval technique i.e., full document context in the case of general query and semantic search using ChromadDB Database in the case of specific query. In this case, Google Gemini does embed and answer generation, whereas LangChain deals with document chunking and retrieval. The hash-based caching minimizes regular processing and enhances the response time. It enables better accuracy of the experiment, less false perceptions, and faster performance than old-fashioned RAG systems.},
        keywords = {RAG, Intent Classification, Google Gemini, ChromaDB, LangChain, Technical Documentation},
        month = {June},
        }