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{201754,
        author = {Shivanand R Koppalkar},
        title = {Designing a Healthcare Knowledge Assistant Using Retrieval-Augmented Generation and Tool Agents},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {4789-4799},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201754},
        abstract = {This paper presents the design and prototype of a healthcare knowledge assistant that combines Retrieval-Augmented Generation with a tool-using agent. The system addresses two well-known weaknesses of large language models in clinical settings. First, language models can produce confident but incorrect medical statements when they rely on parametric memory alone (Ji et al., 2023). Second, language models cannot reach private patient records that sit behind hospital systems. The proposed solution pairs a vector-store knowledge base for clinical concepts with two structured tools, namely a SQL query tool that reads a patient electronic health record and a custom range-validation tool that compares values against published clinical thresholds. A LangChain ReAct agent orchestrates the three tools and decides which to call based on the user query. The paper describes the system architecture, tool configurations, prompt design, sample input and output, and an evaluation plan that maps back to the assignment rubric. The work shows how grounded retrieval, structured data access, and rule-based validation can work together to lower hallucination risk and produce useful answers for clinicians.},
        keywords = {Retrieval-Augmented Generation, Tool-using Agents, Healthcare Informatics, Vector Search, Clinical Decision Support, Large Language Models},
        month = {May},
        }