[DOCS] Change order on 'tune knn' page (elastic#104036) (elastic#104042)

Author: abdonpijpelink

docs/reference/how-to/knn-search.asciidoc

@@ -11,36 +11,14 @@ the indexing algorithm runs searches under the hood to create the vector index
 structures. So these same recommendations also help with indexing speed.
 
 [discrete]
-=== Ensure data nodes have enough memory
-
-{es} uses the https://arxiv.org/abs/1603.09320[HNSW] algorithm for approximate
-kNN search. HNSW is a graph-based algorithm which only works efficiently when
-most vector data is held in memory. You should ensure that data nodes have at
-least enough RAM to hold the vector data and index structures. To check the
-size of the vector data, you can use the <<indices-disk-usage>> API. As a
-loose rule of thumb, and assuming the default HNSW options, the bytes used will
-be `num_vectors * 4 * (num_dimensions + 12)`. When using the `byte` <<dense-vector-element-type,`element_type`>>
-the space required will be closer to  `num_vectors * (num_dimensions + 12)`. Note that
-the required RAM is for the filesystem cache, which is separate from the Java
-heap.
-
-The data nodes should also leave a buffer for other ways that RAM is needed.
-For example your index might also include text fields and numerics, which also
-benefit from using filesystem cache. It's recommended to run benchmarks with
-your specific dataset to ensure there's a sufficient amount of memory to give
-good search performance.
-You can find https://elasticsearch-benchmarks.elastic.co/#tracks/so_vector[here]
-and https://elasticsearch-benchmarks.elastic.co/#tracks/dense_vector[here] some examples
-of datasets and configurations that we use for our nightly benchmarks.
-
-[discrete]
-include::search-speed.asciidoc[tag=warm-fs-cache]
-
-The following file extensions are used for the approximate kNN search:
+=== Reduce vector memory foot-print
 
-* `vec` and `veq` for vector values
-* `vex` for HNSW graph
-* `vem`, `vemf`, and `vemq` for metadata
+The default <<dense-vector-element-type,`element_type`>> is `float`. But this
+can be automatically quantized during index time through
+<<dense-vector-quantization,`quantization`>>. Quantization will reduce the
+required memory by 4x, but it will also reduce the precision of the vectors. For
+`float` vectors with `dim` greater than or equal to `384`, using a
+<<dense-vector-quantization,`quantized`>> index is highly recommended.
 
 [discrete]
 === Reduce vector dimensionality
@@ -54,14 +32,6 @@ reduction techniques like PCA. When experimenting with different approaches,
 it's important to measure the impact on relevance to ensure the search
 quality is still acceptable.
 
-[discrete]
-=== Reduce vector memory foot-print
-
-The default <<dense-vector-element-type,`element_type`>> is `float`. But this can be
-automatically quantized during index time through <<dense-vector-quantization,`quantization`>>. Quantization will
-reduce the required memory by 4x, but it will also reduce the precision of the vectors. For `float` vectors with
-`dim` greater than or equal to `384`, using a <<dense-vector-quantization,`quantized`>> index is highly recommended.
-
 [discrete]
 === Exclude vector fields from `_source`
 
@@ -82,6 +52,37 @@ downsides of omitting fields from `_source`.
 Another option is to use  <<synthetic-source,synthetic `_source`>> if all
 your index fields support it.
 
+[discrete]
+=== Ensure data nodes have enough memory
+
+{es} uses the https://arxiv.org/abs/1603.09320[HNSW] algorithm for approximate
+kNN search. HNSW is a graph-based algorithm which only works efficiently when
+most vector data is held in memory. You should ensure that data nodes have at
+least enough RAM to hold the vector data and index structures. To check the
+size of the vector data, you can use the <<indices-disk-usage>> API. As a
+loose rule of thumb, and assuming the default HNSW options, the bytes used will
+be `num_vectors * 4 * (num_dimensions + 12)`. When using the `byte` <<dense-vector-element-type,`element_type`>>
+the space required will be closer to  `num_vectors * (num_dimensions + 12)`. Note that
+the required RAM is for the filesystem cache, which is separate from the Java
+heap.
+
+The data nodes should also leave a buffer for other ways that RAM is needed.
+For example your index might also include text fields and numerics, which also
+benefit from using filesystem cache. It's recommended to run benchmarks with
+your specific dataset to ensure there's a sufficient amount of memory to give
+good search performance.
+You can find https://elasticsearch-benchmarks.elastic.co/#tracks/so_vector[here]
+and https://elasticsearch-benchmarks.elastic.co/#tracks/dense_vector[here] some examples
+of datasets and configurations that we use for our nightly benchmarks.
+
+[discrete]
+include::search-speed.asciidoc[tag=warm-fs-cache]
+
+The following file extensions are used for the approximate kNN search:
+
+* `vec` and `veq` for vector values
+* `vex` for HNSW graph
+* `vem`, `vemf`, and `vemq` for metadata
 
 [discrete]
 === Reduce the number of index segments