RAG-FUSION: A NEW TAKE ON RETRIEVALAUGMENTED GENERATION

Infineon has identified a need for engineers, account managers, and customers to rapidly obtain productinformation. This problem is traditionally addressed with retrieval-augmented generation (RAG) chatbots,but in this study, I evaluated the use of the newly popularized RAG-Fusion method. RAG-Fusion combinesRAG and reciprocal rank fusion (RRF) by generating multiple queries, reranking them with reciprocalscores and fusing the documents and scores. Through manually evaluating answers on accuracy,relevance, and comprehensiveness, I found that RAG-Fusion was able to provide accurate andcomprehensive answers due to the generated queries contextualizing the original query from variousperspectives. However, some answers strayed off topic when the generated queries' relevance to theoriginal query is insufficient. This research marks significant progress in artificial intelligence (AI) andnatural language processing (NLP) applications and demonstrates transformations in a global and multiindustry context.