This study introduces an AI-driven chatbot designed to help researchers navigate academic literature efficiently. Leveraging frameworks such as Langchain, Pinecone, and OpenAI’s large language models, the chatbot streamlines research processes by summarizing papers, answering queries, and recommending related literature. This study addresses the limitations of expensive proprietary models and the lack of accessible research tools; it proposes a model-agnostic and highly scalable solution that enables the chatbot to cost-effectively ingest numerous research papers. A collection of papers from six domains such as Artificial Intelligence was collected, pre-processed, and fed into the system for evaluation. The chatbot’s effectiveness was evaluated using the RAGAS evaluation method and user usability testing. Results demonstrated high accuracy in retrieving factual information and generating relevant answers. A set of sixteen respondents, through convenience sampling, carried out the usability testing. Results show that the respondents expressed strong intent to adopt and recommend the system as it significantly improves the research experience.