Use Semantic Search vs keyword search

[christinach]

Introduction

Semantic search enables search experiences that can interpret the meaning of words and phrases. It returns content matching the meaning of a query and not just a keyword search.

Problem Statement

Provide search results interpreting the intent of the user's query. This could improve search experience by 1. Delivering highly relevant results to the users with less effort, 2. Returning fast search results, even on large and varied data, 3. Enabling new classes of search for text, image, and audio.

Acceptance criteria

• If there is no research directory, create one. https://github.com/christinach/semantic-search-research/

• Update an existing markdown document or add a new one in the research directory.

• It has introduction: Explains the goals and purpose of this research work.

• It lists methods: Describe what you did to research the question.

• It has a conclusion: Includes a summary of what was discovered in the research process.

• It has a step by step list of potential next steps that build upon the research.

• It includes references: References any related resources that have assisted in the research process (links to other tickets, online articles etc.).

• It includes any artifacts (charts, notes, code samples etc.) that were produced during the work.

References

• why technology leaders need vector search
• overview-image-similarity-search-in-elastic
• Apache Solr Dense Vector Search Solr9
• text_embedding_api_semantic_search_with_scann- uses Billable components