Upload My findings about Parent Document R.txt

My findings about Parent Document R.txt

@@ -0,0 +1,27 @@
+My findings about "Parent Document Retriever"
+
+1) brief about the method/technique
+
+if there is one specific splited document that is quite big then that means the embedding itself will be less specific. however, if it is small then the embedding itself will be more specific.
+with split parent docs and the splited child docs, the embeddings themselves become more specific
+
+The ParentDocumentRetriever strikes that balance by splitting and storing small chunks of data. During retrieval, it first fetches the small chunks but then looks up the parent IDs for those chunks and returns those larger documents
+
+********************************
+
+2) why do we need to use this technique
+
+so basically what parent document retrieval does is look into the documents to find the most relevant answer to a query, and how it is being done is very simple that would be by dividing the large amount of data that we have ( which by the way could be complex too) and then have different parent documents and within the parent documents we do have child documents.
+that being said the embeddings will become more specific
+
+********************************
+
+3) what would make this technique the best choice
+
+so this technique really shines when we are dealing with large amounts of data and complex relationships between documents, and it is beneficial when information is scattered over many different sources or when the data isn't easily searchable.
+
+********************************
+
+4) what type of data would be there if we want to use that technique
+
+it would be text-based documents which could be news articles, research papers, user reviews, or any other form of written document.