Related Experiment Video
Updated: Sep 13, 2025
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
ChemReactSeek: an artificial intelligence-guided chemical reaction protocol design using retrieval-augmented large
Ziyang Gong1, Chengwei Zhang2, Danyang Song2
1Key Laboratory of Pharmaceutical Engineering of Zhejiang Province, National Engineering Research Center for Process Development of Active Pharmaceutical Ingredients, Collaborative Innovation Center of Yangtze River Delta Region Green Pharmaceuticals, Zhejiang University of Technology, Hangzhou, 310014, P. R. China.
Abstract:
We introduce ChemReactSeek, an advanced artificial intelligence platform that integrates retrieval-augmented generation using large language models (LLMs) to automate the design of chemical reaction protocols. The system employs DeepSeek-v3 to extract and structure data from scientific literature, enabling the construction of a specialized knowledge base focused on hydrogenation reactions. By combining FAISS-based semantic search with LLM-driven reasoning, ChemReactSeek generates executable reaction conditions, which we further validate through experiments on heterogeneous hydrogenation.
