Eric ZhùinTowards Data SciencePlease Use Streaming Workload to Benchmark Vector DatabasesWhy static workload is insufficient and what I learned by comparing HNSWLIB and DiskANN using streaming workload9 min read·Dec 1, 2023--1--1
Eric ZhùinTowards Data ScienceFinding Needles in a Haystack — Search Indexes for Jaccard SimilarityFrom basic concepts to exact and approximate indexes15 min read·Aug 18, 2023--1--1
Eric ZhùGPT-4’s Maze Navigation: A Deep Dive into ReAct Agent and LLM’s ThoughtsIn this post I dissect a GPT-4 ReAct Agent capable of navigating a maze, and reveal GPT-4’s thoughts and built-in skills.10 min read·May 10, 2023--3--3
Eric ZhùHuman-Aligned Text-to-SQL EvaluationIn my last post about Text-to-SQL using GPT-3.5, I pointed out the issue with existing benchmark’s evaluation metric: it rejects perfectly…5 min read·Mar 18, 2023--1--1
Eric ZhùWhat is Coming Next for Text-to-SQLText-to-SQL is a natural language processing (NLP) task that involves converting natural language questions into SQL queries that can be…10 min read·Mar 7, 2023----