Apply suggestions from code review

Co-authored-by: Greg Richardson <[email protected]>

apps/docs/pages/guides/ai/choosing-compute-addon.mdx

@@ -23,7 +23,7 @@ The number of dimensions in your embeddings is the most important factor in choo
 
 ### 384 Dimensions
 
-This benchmark uses the dbpedia-entities-openai-1M dataset, which contains 1,000,000 embeddings of text. Each embedding is 384 dimensions created with the [gte-small](https://huggingface.co/Supabase/gte-small).
+This benchmark uses the dbpedia-entities-openai-1M dataset containing 1,000,000 embeddings of text, regenerated for 384 dimension embeddings. Each embedding is generated using [gte-small](https://huggingface.co/Supabase/gte-small).
 
 <Tabs
   scrollable
@@ -106,7 +106,7 @@ It is possible to upload more vectors to a single table if Memory allows it (for
 
 ### 384 Dimensions
 
-This benchmark uses the dbpedia-entities-openai-1M dataset, which contains 1,000,000 embeddings of text. Each embedding is 384 dimensions created with the [gte-small](https://huggingface.co/Supabase/gte-small).
+This benchmark uses the dbpedia-entities-openai-1M dataset containing 1,000,000 embeddings of text, regenerated for 384 dimension embeddings. Each embedding is generated using [gte-small](https://huggingface.co/Supabase/gte-small).
 
 <Tabs
   scrollable