Merge pull request supabase#17369 from supabase/or/ai-docs-split

Separate python/js ai docs

apps/docs/components/Navigation/NavigationMenu/NavigationMenu.constants.ts

@@ -964,34 +964,9 @@ export const ai = {
       url: '/guides/ai/structured-unstructured',
     },
     {
-      name: 'Quickstarts',
-      url: undefined,
-      items: [
-        { name: 'Developing locally with Vecs', url: '/guides/ai/vecs-python-client' },
-        { name: 'Creating and managing collections', url: '/guides/ai/quickstarts/hello-world' },
-        {
-          name: 'Generate Embeddings',
-          url: '/guides/ai/quickstarts/generate-text-embeddings',
-        },
-        { name: 'Text Deduplication', url: '/guides/ai/quickstarts/text-deduplication' },
-        { name: 'Face similarity search', url: '/guides/ai/quickstarts/face-similarity' },
-      ],
-    },
-    {
-      name: 'Python Client',
-      url: undefined,
-      items: [
-        { name: 'API', url: '/guides/ai/python/api' },
-        { name: 'Collections', url: '/guides/ai/python/collections' },
-        { name: 'Indexes', url: '/guides/ai/python/indexes' },
-        { name: 'Metadata', url: '/guides/ai/python/metadata' },
-      ],
-    },
-    {
-      name: 'Guides',
+      name: 'Learn',
       url: undefined,
       items: [
-        { name: 'Managing collections', url: '/guides/ai/managing-collections' },
         { name: 'Vector columns', url: '/guides/ai/vector-columns' },
         { name: 'Vector indexes', url: '/guides/ai/vector-indexes', items: vectorIndexItems },
         { name: 'Engineering for scale', url: '/guides/ai/engineering-for-scale' },
@@ -1000,25 +975,23 @@ export const ai = {
       ],
     },
     {
-      name: 'Examples',
+      name: 'JavaScript Examples',
       url: undefined,
       items: [
         {
           name: 'OpenAI completions using Edge Functions',
           url: '/guides/ai/examples/openai',
         },
-        {
-          name: 'Image search with OpenAI CLIP',
-          url: '/guides/ai/examples/image-search-openai-clip',
-        },
+
         {
           name: 'Generate image captions using Hugging Face',
           url: '/guides/ai/examples/huggingface-image-captioning',
         },
         {
-          name: 'Building ChatGPT Plugins',
-          url: '/guides/ai/examples/building-chatgpt-plugins',
+          name: 'Generate Embeddings',
+          url: '/guides/ai/quickstarts/generate-text-embeddings',
         },
+
         {
           name: 'Adding generative Q&A to your documentation',
           url: '/guides/ai/examples/headless-vector-search',
@@ -1029,6 +1002,36 @@ export const ai = {
         },
       ],
     },
+    {
+      name: 'Python Client',
+      url: undefined,
+      items: [
+        { name: 'Choosing a Client', url: '/guides/ai/python-clients' },
+        { name: 'API', url: '/guides/ai/python/api' },
+        { name: 'Collections', url: '/guides/ai/python/collections' },
+        { name: 'Indexes', url: '/guides/ai/python/indexes' },
+        { name: 'Metadata', url: '/guides/ai/python/metadata' },
+      ],
+    },
+    {
+      name: 'Python Examples',
+      url: undefined,
+      items: [
+        { name: 'Developing locally with Vecs', url: '/guides/ai/vecs-python-client' },
+        { name: 'Creating and managing collections', url: '/guides/ai/quickstarts/hello-world' },
+
+        { name: 'Text Deduplication', url: '/guides/ai/quickstarts/text-deduplication' },
+        { name: 'Face similarity search', url: '/guides/ai/quickstarts/face-similarity' },
+        {
+          name: 'Image search with OpenAI CLIP',
+          url: '/guides/ai/examples/image-search-openai-clip',
+        },
+        {
+          name: 'Building ChatGPT Plugins',
+          url: '/guides/ai/examples/building-chatgpt-plugins',
+        },
+      ],
+    },
     {
       name: 'Third-Party Tools',
       url: undefined,

apps/docs/pages/guides/ai/python-clients.mdx

@@ -0,0 +1,18 @@
+import Layout from '~/layouts/DefaultGuideLayout'
+
+export const meta = {
+  id: 'ai-python-clients',
+  title: 'Choosing a Client',
+  description: 'Learn how to manage vectors using Python',
+  sidebar_label: 'Choosing a Client',
+}
+
+As described in [Structured & Unstructured Embeddings](/docs/guides/ai/structured-unstructured), AI workloads come in many forms.
+
+For data science or ephemeral workloads, the [Supabase Vecs](https://supabase.github.io/vecs/) client gets you started quickly. All you need is a connection string and vecs handles setting up your database to store and query vectors with associated metadata.
+
+For production python applications with version controlled migrations, we recommend adding first class vector support to your toolchain by [registering the vector type with your ORM](https://github.com/pgvector/pgvector-python). pgvector provides bindings for the most commonly used SQL drivers/libraries including Django, SQLAlchemy, SQLModel, psycopg, asyncpg and Peewee.
+
+export const Page = ({ children }) => <Layout meta={meta} children={children} />
+
+export default Page

apps/docs/pages/guides/ai/vecs-python-client.mdx

@@ -79,7 +79,7 @@ docs.query(
 
 ## Deep Dive
 
-For a more in-depth guide on `vecs` collections, see [Managing collections](/docs/guides/ai/managing-collections).
+For a more in-depth guide on `vecs` collections, see [API](/docs/guides/ai/python/api).
 
 ## Resources
 

apps/docs/pages/guides/ai/vector-columns.mdx

@@ -7,7 +7,7 @@ export const meta = {
   sidebar_label: 'Vector columns',
 }
 
-Supabase offers a number of different ways to store and query vectors within Postgres. If you prefer to use Python to store and query your vectors using collections, see [Managing collections](/docs/guides/ai/managing-collections). If you want more control over vectors within your own Postgres tables or would like to interact with them using a different language like JavaScript, keep reading.
+Supabase offers a number of different ways to store and query vectors within Postgres. The SQL included in this guide is applicable for clients in all programming languages. If you are a Python user see your [Python client options](/docs/guides/ai/python-clients) after reading the `Learn` section.
 
 Vectors in Supabase are enabled via [pgvector](https://github.com/pgvector/pgvector/), a PostgreSQL extension for storing and querying vectors in Postgres. It can be used to store [embeddings](/docs/guides/ai/concepts#what-are-embeddings).
 

apps/docs/pages/guides/ai/vector-indexes.mdx

@@ -30,8 +30,6 @@ Indexes can be used to improve performance of nearest neighbor search using vari
 
 Currently vectors with up to 2,000 dimensions can be indexed.
 
-If you are using the `vecs` Python library, follow the instructions in [Managing collections](/docs/guides/ai/managing-collections#create-an-index) to create indexes.
-
 ## Resources
 
 Read more about indexing on `pgvector`'s [GitHub page](https://github.com/pgvector/pgvector#indexing).

apps/docs/pages/guides/ai/vector-indexes/hnsw-indexes.mdx

@@ -41,8 +41,6 @@ create index on items using hnsw (column_name vector_cosine_ops);
 
 Currently vectors with up to 2,000 dimensions can be indexed.
 
-If you are using the `vecs` Python library, follow the instructions in [Managing collections](/docs/guides/ai/managing-collections#create-an-index) to create indexes.
-
 ## How does HNSW work?
 
 HNSW uses proximity graphs (graphs connecting nodes based on distance between them) to approximate nearest-neighbor search. To understand HNSW, we can break it down into 2 parts:

apps/docs/pages/guides/ai/vector-indexes/ivf-indexes.mdx

@@ -50,8 +50,6 @@ create index on items using ivfflat (column_name vector_cosine_ops) with (lists
 
 Currently vectors with up to 2,000 dimensions can be indexed.
 
-If you are using the `vecs` Python library, follow the instructions in [Managing collections](/docs/guides/ai/managing-collections#create-an-index) to create indexes.
-
 ## How does IVFFlat work?
 
 IVF stands for 'inverted file indexes'. It works by clustering your vectors in order to reduce the similarity search scope. Rather than comparing a vector to every other vector, the vector is only compared against vectors within the same cell cluster (or nearby clusters, depending on your configuration).