resource · 2024
Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine
arXiv
Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine is a resource in the TCM LLM catalog (Awesome-TCM-LLM), dated 2024. It is maintained alongside the GitHub list of Traditional Chinese Medicine large language models.
Prompt-RAG, which does not use vector embeddings, outperformed ChatGPT and vector-embedding retrieval-augmented generation on relevance and informativeness in a Korean-medicine question-answering chatbot.