Merge pull request #332 from marklogic/feature/docs-tweak

Doc tweaks

Author: rjrudin

docs/copy.md

@@ -84,7 +84,7 @@ of `--collections`.
 
 ## Building a RAG data pipeline
 
-[Retrieval-augmented generation](https://en.wikipedia.org/wiki/Retrieval-augmented_generation), or RAG, with MarkLogic depends on preparing data so that the most relevant
+[Retrieval-augmented generation](https://www.progress.com/marklogic/solutions/generative-ai), or RAG, with MarkLogic depends on preparing data so that the most relevant
 chunks of text for a user's question can be sent to a Large Language Model, or LLM. Starting with release 1.2.0, Flux
 supports the construction of a data pipeline by splitting the text in a document into chunks and adding a vector
 embedding to each chunk while copying data. Please see [the guide on splitting text](import/splitting.md) and

docs/import/common-import-features.md

@@ -109,7 +109,7 @@ The following shows an example of each option:
 
 ## Building a RAG data pipeline
 
-[Retrieval-augmented generation](https://en.wikipedia.org/wiki/Retrieval-augmented_generation), or RAG, with MarkLogic depends on preparing data so that the most relevant 
+[Retrieval-augmented generation](https://www.progress.com/marklogic/solutions/generative-ai), or RAG, with MarkLogic depends on preparing data so that the most relevant 
 chunks of text for a user's question can be sent to a Large Language Model, or LLM. Starting with release 1.2.0, Flux 
 supports the construction of a data pipeline by splitting the text in a document into chunks and adding a vector 
 embedding to each chunk while importing data. Please see [the guide on splitting text](splitting.md) and 

docs/import/embedder/embedder.md

@@ -11,7 +11,7 @@ associated with a "chunk" of text that is usually, but not necessarily, produced
 [support for splitting text](../splitting.md). Flux can add embeddings during 
 any import operation and also when [copying documents](../../copy.md). Adding embeddings to documents is a critical 
 part of creating a data pipeline in support of 
-[retrieval-augmented generation, or RAG](https://en.wikipedia.org/wiki/Retrieval-augmented_generation), 
+[retrieval-augmented generation, or RAG](https://www.progress.com/marklogic/solutions/generative-ai), 
 use cases that utilize MarkLogic's support for 
 [vector queries](https://docs.marklogic.com/12.0/guide/release-notes/en/new-features-in-marklogic-12-0-ea1/native-vector-support.html). 
 

docs/import/splitting.md

@@ -8,7 +8,7 @@ nav_order: 6
 Flux supports splitting the text in documents into chunks of configurable size, either written to the source document
 or to separate "sidecar" documents containing one or more chunks. Flux can split text during any import operation and also 
 when [copying documents](../copy.md). Splitting text is often a critical part of creating a data pipeline in support
-of [retrieval-augmented generation, or RAG](https://en.wikipedia.org/wiki/Retrieval-augmented_generation), use cases with MarkLogic.
+of [retrieval-augmented generation, or RAG](https://www.progress.com/marklogic/solutions/generative-ai), use cases with MarkLogic.
 
 ## Table of contents
 {: .no_toc .text-delta }
@@ -321,7 +321,7 @@ via the `--transform` option for your import command or `--output-transform` opt
 By default, Flux will create each XML sidecar document using the following structure:
 
 ```
-<root>
+<root xmlns="http://marklogic.com/appservices/model">
   <source-uri>The URI of the source document</source-uri>
   <chunks>
     <chunk><text>The first chunk</text></chunk>

docs/index.md

@@ -12,6 +12,7 @@ With Flux, you can automate common data movement use cases including:
 
 - Importing rows from an RDBMS.
 - Importing JSON, XML, CSV, Parquet and other file types from a local filesystem or S3.
+- Implementing a data pipeline for a [RAG solution with MarkLogic](https://www.progress.com/marklogic/solutions/generative-ai).
 - Copying data from one MarkLogic database to another database.
 - Reprocessing data in MarkLogic via custom code.
 - Exporting data to an RDBMS, a local filesystem, or S3.
@@ -25,7 +26,7 @@ Flux has the following system requirements:
 Java 21 should work but has not been thoroughly tested yet. Java 23 will not yet work. 
 
 Earlier versions of MarkLogic 9 and 10 will support any features not involving Optic queries.
-Additionally, the latest version of MarkLogic 11 is recommended if possible.
+Additionally, the latest version of MarkLogic 11 or 12 is recommended if possible.
 
 Flux is built on top of [Apache Spark](https://spark.apache.org/), but you do not need to know anything about Spark
 to use Flux. If you are already making use of Spark for other use cases, see the