Adds semantic search example using Supabase Vector

[gregnr]

Summary

Adds a cookbook example to store and query OpenAI embeddings in Supabase using pgvector and Supabase's auto-generated REST API. This guide is written for JavaScript developers, but also adds callouts that explain how they can modify it for other languages.

Motivation

Many Supabase customers use OpenAI embeddings in their DB (via pgvector) to perform semantic search and RAG over their data. This PR adds a guide that demonstrates exactly how to implement semantic search in Supabase using OpenAI embeddings while also following database best practices (like HNSW indexes, row level security, etc).

Supabase exposes an auto-generated REST API (based on the user's table schema), so this guide walks users through how to interact with their data via this API. There also aren't too many cookbook examples written for JavaScript developers, so this guide targets this audience and explains how to implement semantic search for multiple JavaScript runtimes (Node.js, Deno, Edge Functions). Since this focuses on JavaScript, the guide was written as mdx, but let me know if ipynb is preferred here!

---

For new content

When contributing new content, read through our contribution guidelines, and mark the following action items as completed:

• I have added a new entry in registry.yaml (and, optionally, in authors.yaml) so that my content renders on the cookbook website.
• I have conducted a self-review of my content based on the contribution guidelines:
  • Relevance: This content is related to building with OpenAI technologies and is useful to others.
  • Uniqueness: I have searched for related examples in the OpenAI Cookbook, and verified that my content offers new insights or unique information compared to existing documentation.
  • Spelling and Grammar: I have checked for spelling or grammatical mistakes.
  • Clarity: I have done a final read-through and verified that my submission is well-organized and easy to understand.
  • Correctness: The information I include is correct and all of my code executes successfully.
  • Completeness: I have explained everything fully, including all necessary references and citations.

We will rate each of these areas on a scale from 1 to 4, and will only accept contributions that score 3 or higher on all areas. Refer to our contribution guidelines for more details.

[logankilpatrick]

LGTM pending small changes

[gregnr]

@logankilpatrick thanks for reviewing! Suggested changes have been added.