Can you provide an example of how LSI can improve search for 'apple'?

If a user searches for 'apple', a traditional keyword search might only return results related to the fruit. However, LSI, recognizing the context, could also retrieve documents about 'Apple Inc.', 'iPhone', 'macOS', or 'Steve Jobs'. It would understand the semantic relationship between these terms and 'apple', offering a more comprehensive and contextually relevant set of search results based on the document collection.