fastbmRAG: A Fast Graph-Based RAG Framework for Efficient Processing of Large-Scale Biomedical Literature

TL;DR

fastbmRAG tackles the scalability bottleneck of graph-based RAG in biomedical literature by a two-stage graph construction: drafting from abstracts to capture core entities and relations, then refining with main-text evidence through vector-based linking. The approach leverages an LLM-driven extraction pipeline, standardized biomedical nomenclature, and a vector database to enable efficient, large-scale semantic querying and answer generation. Empirical results show over an order-of-magnitude speedup (≈10x) compared with LightRAG while improving coverage and accuracy on disease-focused corpora. This provides a practical, scalable solution for rapid understanding, summarization, and question answering over vast biomedical literature collections, with open-source availability for adoption and extension.

Abstract

Large language models (LLMs) are rapidly transforming various domains, including biomedicine and healthcare, and demonstrate remarkable potential from scientific research to new drug discovery. Graph-based retrieval-augmented generation (RAG) systems, as a useful application of LLMs, can improve contextual reasoning through structured entity and relationship identification from long-context knowledge, e.g. biomedical literature. Even though many advantages over naive RAGs, most of graph-based RAGs are computationally intensive, which limits their application to large-scale dataset. To address this issue, we introduce fastbmRAG, an fast graph-based RAG optimized for biomedical literature. Utilizing well organized structure of biomedical papers, fastbmRAG divides the construction of knowledge graph into two stages, first drafting graphs using abstracts; and second, refining them using main texts guided by vector-based entity linking, which minimizes redundancy and computational load. Our evaluations demonstrate that fastbmRAG is over 10x faster than existing graph-RAG tools and achieve superior coverage and accuracy to input knowledge. FastbmRAG provides a fast solution for quickly understanding, summarizing, and answering questions about biomedical literature on a large scale. FastbmRAG is public available in https://github.com/menggf/fastbmRAG.

Figures (2)

• Figure 1: The flowchart of fastbmRAG to build knowledge graph
• Figure 2: Outputs of fastbmRAG, LightRAG and Phi4 model