Delivering an exceptional search experience is vital in digital marketplaces. This post discusses how to enhance search functionality using Amazon OpenSearch and Amazon Bedrock, focusing on overcoming synonym deficiencies with large language models (LLMs). Practical steps and approaches, including naive synonym expansion, semantic search with embeddings, query-time synonym expansion, and neural sparse retrieval, are shared, providing insight into their effectiveness in improving search accuracy and user experience.
Table of contents
IntroductionThe Challenge: Synonym Deficiency and Semantic GapOur Approach: Leveraging LLMs and Amazon BedrockChoosing the right LLM for the jobConclusionSort: