supabase · Supabase Docs
Supabase AI and Vectors
Implement AI-driven features and semantic search capabilities by leveraging pgvector for storing and querying embeddings, integrated with Supabase Edge Functions and Postgres for building advanced retrieval systems.
Derived skill
Files assembled from official documentation
Viewing SKILL.md
Supabase AI and Vectors
Implement AI-driven features and semantic search capabilities by leveraging pgvector for storing and querying embeddings, integrated with Supabase Edge Functions and Postgres for building advanced retrieval systems.
When To Use
Use when you need to implement semantic search, recommendation engines, or Retrieval-Augmented Generation (RAG) workflows involving vector storage, similarity queries, and AI orchestration.
Reference Files
| File | Contains | Use For |
|---|---|---|
SKILL.md | Entry point: scope, routing table, and workflow. | Start here. |
docs/supabase-vector-md/workflow-guide.md | An overview of Supabase Vector features, use cases, and technical details for storing and querying embeddings with pgvector. | Questions about an overview of Supabase Vector features, use cases, and technical details for storing and querying embeddings with pg... |
What This Skill Covers
- Supabase Vector: Store, index, and query vector embeddings in Postgres with pgvector.
Workflow
- Start with the reference file that matches the question.
- Prefer the most relevant file under
docs/for exact instructions and prose guidance. - Use
schemas/andexamples/for exact contracts, payloads, manifests, requests, and snippets. - Do not add behavior or configuration that is not present in the attached source files.