Hoche, JosephCharlon, ThomasCai, Tianxi2025-09-052025-03-08Thomas Charlon, Joseph Hoche, and Tianxi Cai. 2025. "R / Python Pipelines for Biomedical LLM Semantic Search Apps." Talk presented at SoCal Linux Expo 22x.https://dash.harvard.edu/handle/1/42719073Leveraging Pytorch's GPU indexing and R's data management, evaluation and visualization capabilities At the CELEHS laboratory we are particularly interested by LLM-based embeddings as BGE and BERT. As the number of models increases, we need methods to compare their clinical usefulness. While some R packages exist to leverage GPU capabilities, Pytorch is by far more used for GPU computation. In contrast, R is efficient for data management and visualization. How should one build robust and reproducible pipelines incorporating them both ? My answer is well-designed pipelines with Docker, Makefile, and Elasticsearch. In this talk I will showcase my design approaches to such challenges.EnglishR / Python Pipelines for Biomedical LLM Semantic Search AppsConference Proceedings