Supabase AI app with semantic search
Postgres with pgvector for embeddings, the AI SDK for model calls, and prompt caching to keep costs down.
por Promptu
Lo que obtienes
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.
Orden de montaje
- 1Servidor MCPDatabase 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.
- 2TecnologíaEmbeddingspgvector
Open-source vector similarity search for Postgres. Keep embeddings next to your data, with no separate vector database.
CREATE EXTENSION vector;
- 3TecnologíaModel callsAI SDK
TypeScript toolkit for building AI features (streaming, tool calling, structured output) across model providers.
npm install ai
- 4TecnologíaCostPrompt caching (Claude API)
Reuse a processed prompt prefix (tools, system, messages) to cut cost and latency on repeated context.
- 5PromptPerformanceWhy is this Postgres query slow?
Revisa los comandos antes de ejecutarlos. Promptu nunca ejecuta código en tu equipo.

