Couple docs edits

docs/embedding.md

@@ -4,14 +4,6 @@ title: Embedding Examples
 nav_order: 5
 ---
 
-## Table of contents
-{: .no_toc .text-delta }
-
-- TOC
-{:toc}
-
-## Adding embeddings with langchain4j
-
 The vector queries shown in the [langchain](../rag-langchain-python/README.md),
 [langchain4j](../rag-langchain-java), and [langchain.js](../rag-langchain-js/README.md) RAG examples
 depend on embeddings - vector representations of text - being added to documents in MarkLogic. Vector queries can
@@ -21,6 +13,12 @@ This project demonstrates the use of a
 the [MarkLogic Data Movement SDK](https://docs.marklogic.com/guide/java/data-movement) for adding embeddings to
 documents in MarkLogic.
 
+## Table of contents
+{: .no_toc .text-delta }
+
+- TOC
+{:toc}
+
 ## Setup
 
 This example depends both on the [main setup for all examples](../setup/README.md) and also on having run the
@@ -29,7 +27,7 @@ This example depends both on the [main setup for all examples](../setup/README.m
 the text in Enron email documents and write each chunk of text to a separate document. This example will then use
 langchain4j to generate an embedding for the chunk of text and add it to each chunk document.
 
-## Add embeddings example
+## Adding embedding to documents
 
 To try the embedding example, run the following Gradle task:
 

docs/splitting.md

@@ -4,21 +4,21 @@ title: Splitting Examples
 nav_order: 4
 ---
 
-## Table of contents
-{: .no_toc .text-delta }
-
-- TOC
-{:toc}
-
-## Splitting documents with langchain4j
-
 A RAG approach typically benefits from sending multiple smaller segments or "chunks" of text to an LLM. While MarkLogic
 can efficiently ingest and index large documents, sending all the text in even a single document may either exceed
 the number of tokens allowed by your LLM or may result in slower and more expensive responses from the LLM. Thus,
 when importing or reprocessing documents in MarkLogic, your RAG approach may benefit from splitting the searchable
 text in a document into smaller segments or "chunks" that allow for much smaller and more relevent segments of text
 to be sent to the LLM.
 
+## Table of contents
+{: .no_toc .text-delta }
+
+- TOC
+{:toc}
+
+## Overview
+
 This project demonstrates two different approaches to splitting documents:
 
 1. Splitting the text in a document and storing each chunk in a new separate document.