Juan YinDesensitizing of Private Information in Enterprise DataThe descriptive data of task application provides rich training and fine-tuning data for internal AI assistant. However, internal…Sep 18Sep 18
Juan YinSome Methods of Data Ingestion in RAG-based ChatbotsRAG-based chatbots are very popular. Cloud service platforms such as Google cloud, Microsoft Azure, and AWS have provided good and user…Jun 5Jun 5
Juan YinGenerating Test Data for RAG-based ChatbotRAG-based chatbots are very popular and easy to implement, but after implementation, evaluating their performance is a problem. The…Jun 4Jun 4
Juan YinTelling Stories with Data Part 1:Data Visualization via NLIn the process of data-driven decision-making, the perfect process is the DIKW(Data, Information, Knowledge, Wisdom) model. Data is a…Apr 9Apr 9
Juan YinSome Popular Approximate Nearest Neighbor Graph-based Search AlgorithmsThe popular vector search algorithmsAug 31, 2023Aug 31, 2023