From 18734726cb6b694173435aace26fe0db34cd0abb Mon Sep 17 00:00:00 2001
From: Gabriel Ramos <luisgabrielramosrobles@gmail.com>
Date: Mon, 8 Jun 2026 11:27:02 -0400
Subject: [PATCH] db: create initial schema migration with pgvector

---
 supabase/migrations/00001_initial_schema.sql | 85 ++++++++++++++++++++
 1 file changed, 85 insertions(+)
 create mode 100644 supabase/migrations/00001_initial_schema.sql

diff --git a/supabase/migrations/00001_initial_schema.sql b/supabase/migrations/00001_initial_schema.sql
new file mode 100644
index 0000000..f8b0006
--- /dev/null
+++ b/supabase/migrations/00001_initial_schema.sql
@@ -0,0 +1,85 @@
+-- Enable the pgvector extension to work with embeddings
+CREATE EXTENSION IF NOT EXISTS vector;
+
+-- Users Table (Recruiters / Managers)
+CREATE TABLE IF NOT EXISTS users (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  email TEXT UNIQUE NOT NULL,
+  role TEXT NOT NULL CHECK (role IN ('recruiter', 'manager')),
+  created_at TIMESTAMP WITH TIME ZONE DEFAULT timezone('utc'::text, now()) NOT NULL
+);
+
+-- Jobs Table
+CREATE TABLE IF NOT EXISTS jobs (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  title TEXT NOT NULL,
+  description TEXT NOT NULL,
+  requirements TEXT,
+  embedding vector(1536),
+  created_at TIMESTAMP WITH TIME ZONE DEFAULT timezone('utc'::text, now()) NOT NULL
+);
+
+-- Candidates Table
+CREATE TABLE IF NOT EXISTS candidates (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  name TEXT NOT NULL,
+  email TEXT UNIQUE NOT NULL,
+  phone TEXT,
+  resume_url TEXT,
+  summary TEXT,
+  seniority TEXT,
+  embedding vector(1536),
+  created_at TIMESTAMP WITH TIME ZONE DEFAULT timezone('utc'::text, now()) NOT NULL
+);
+
+-- Interviews Table
+CREATE TABLE IF NOT EXISTS interviews (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  candidate_id UUID REFERENCES candidates(id) ON DELETE CASCADE NOT NULL,
+  job_id UUID REFERENCES jobs(id) ON DELETE CASCADE NOT NULL,
+  scheduled_at TIMESTAMP WITH TIME ZONE NOT NULL,
+  status TEXT NOT NULL CHECK (status IN ('scheduled', 'completed', 'cancelled')) DEFAULT 'scheduled',
+  notes TEXT,
+  created_at TIMESTAMP WITH TIME ZONE DEFAULT timezone('utc'::text, now()) NOT NULL
+);
+
+-- Scores Table
+CREATE TABLE IF NOT EXISTS scores (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  candidate_id UUID REFERENCES candidates(id) ON DELETE CASCADE NOT NULL,
+  job_id UUID REFERENCES jobs(id) ON DELETE CASCADE NOT NULL,
+  interviewer_id UUID REFERENCES users(id) ON DELETE CASCADE,
+  score NUMERIC NOT NULL CHECK (score >= 0 AND score <= 100),
+  evaluation JSONB, -- MUST contain exactly: summary, classification, suggestions, riskLevel
+  created_at TIMESTAMP WITH TIME ZONE DEFAULT timezone('utc'::text, now()) NOT NULL
+);
+
+-- RPC Function to Match Candidates using Cosine Distance
+CREATE OR REPLACE FUNCTION match_candidates (
+  query_embedding vector(1536),
+  match_threshold FLOAT,
+  match_count INT
+)
+RETURNS TABLE (
+  id UUID,
+  name TEXT,
+  email TEXT,
+  seniority TEXT,
+  similarity FLOAT
+)
+LANGUAGE plpgsql
+AS $$
+BEGIN
+  RETURN QUERY
+  SELECT
+    candidates.id,
+    candidates.name,
+    candidates.email,
+    candidates.seniority,
+    (1 - (candidates.embedding <=> query_embedding))::FLOAT AS similarity
+  FROM candidates
+  WHERE (1 - (candidates.embedding <=> query_embedding)) > match_threshold
+  ORDER BY candidates.embedding <=> query_embedding ASC
+  LIMIT match_count;
+END;
+$$;