Supabase AI app with semantic search
Postgres with pgvector for embeddings, the AI SDK for model calls, and prompt caching to keep costs down.
作者:Promptu
你最終會得到
An app that stores embeddings in Supabase Postgres (pgvector), answers questions with the AI SDK, and reuses cached prompt prefixes. The prompt helps explain slow queries as the data grows.
建置順序
- 1MCP 伺服器Database access for your agentSupabase MCP server
Connect agents to your Supabase projects: schema, SQL, logs and docs. Scope it to one project and read-only when you can.
- 2技術Embeddingspgvector
Open-source vector similarity search for Postgres. Keep embeddings next to your data, with no separate vector database.
CREATE EXTENSION vector;
- 3技術Model callsAI SDK
TypeScript toolkit for building AI features (streaming, tool calling, structured output) across model providers.
npm install ai
- 4技術CostPrompt caching (Claude API)
Reuse a processed prompt prefix (tools, system, messages) to cut cost and latency on repeated context.
- 5提示詞PerformanceWhy is this Postgres query slow?
執行指令前請先檢查。Promptu 絕不會在你的電腦上執行程式碼。

