菜单
Expert guidance on Supabase/PostgreSQL implementation for RAG, including pgvector semantic search and full-text search.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Help the team document and maintain Architecture Decision Records (ADRs).
Expert guidance on document processing with Docling and audio transcription with Whisper.
Standard for creating technical documentation in this repository. Use this when writing new documentation in docs/ to ensure consistent hierarchy and formatting.
Expert guidance on creating accurate, visually polished Mermaid diagrams for architecture documentation.
Expert guidance on MongoDB implementation for RAG, including aggregation pipelines and search patterns.
Expert guidance on building agents and tools with Pydantic AI.
| name | supabase |
| description | Expert guidance on Supabase/PostgreSQL implementation for RAG, including pgvector semantic search and full-text search. |
This skill provides patterns for implementing RAG logic with Supabase and the pgvector extension.
documents: Stores source document text and global metadata.chunks: Stores text fragments, embedding (vector), and a foreign key document_id (UUID).ON DELETE CASCADE from chunks to documents for clean deletions.Semantic Search (pgvector):
match_chunks exists in the database.query_embedding (vector), match_threshold (float), match_count (int).self.client.rpc("match_chunks", rpc_params).execute().Text Search (WFTS):
self.client.table("chunks").select("...").filter("content", "wfts", query).range(0, limit - 1).execute().supabase Python library (create_client).match_chunks RPC is properly defined in the database schema before use.threshold for semantic matches is usually configurable in the repository's __init__.