The post describes an issue where a search query returns unexpected results, with documents and paragraphs that do not match the user's request. The community members discuss the difference between textual and semantic search, and suggest that using a list or tree index, as well as different indexes for different use cases (such as summarizing and searching), could be a better approach. They also mention the possibility of using "exclude" and "required" keywords as a partial solution, and recommend reading a page on different use cases for the GPT Index library.
YEs makes sense for me as well. But what if an user asks for a summary? EG: "can you summarize the doc xyz? Specifically the paragraph 123."
In this way the AI would summarize the doc xyw or it would respond that it can't find the document requested. I mean, it's so disappointing. A partial solution would be to include the "exclude" and "required" keywords...
But my point is: is it normal such a behaviour? Are you experiencing the same kind of results? If yes, I don't know what i did in these 2 months, but at least I will use the partial solution...
