migrations/001_init.sql

Rama main · réplica de lectura del repositorio original.

CREATE EXTENSION IF NOT EXISTS vector;

CREATE TABLE IF NOT EXISTS documents (
  id BIGSERIAL PRIMARY KEY,
  source_type TEXT NOT NULL,
  source_ref TEXT NOT NULL,
  source_url TEXT,
  title TEXT,
  content_hash TEXT NOT NULL UNIQUE,
  mime_type TEXT,
  file_type TEXT,
  extracted_text TEXT NOT NULL,
  metadata JSONB NOT NULL DEFAULT '{}'::jsonb,
  status TEXT NOT NULL DEFAULT 'ready',
  created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
  updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);

CREATE TABLE IF NOT EXISTS document_chunks (
  id BIGSERIAL PRIMARY KEY,
  document_id BIGINT NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
  chunk_index INTEGER NOT NULL,
  content TEXT NOT NULL,
  token_estimate INTEGER NOT NULL DEFAULT 0,
  metadata JSONB NOT NULL DEFAULT '{}'::jsonb,
  embedding VECTOR(768) NOT NULL,
  created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
  UNIQUE (document_id, chunk_index)
);

CREATE INDEX IF NOT EXISTS idx_documents_source_ref ON documents (source_ref);
CREATE INDEX IF NOT EXISTS idx_documents_source_url ON documents (source_url);
CREATE INDEX IF NOT EXISTS idx_document_chunks_document_id ON document_chunks (document_id);
CREATE INDEX IF NOT EXISTS idx_document_chunks_embedding ON document_chunks USING ivfflat (embedding vector_cosine_ops) WITH (lists = 100);

CREATE TABLE IF NOT EXISTS scheduled_jobs (
  id BIGSERIAL PRIMARY KEY,
  job_type TEXT NOT NULL,
  cron_expression TEXT NOT NULL,
  payload JSONB NOT NULL DEFAULT '{}'::jsonb,
  enabled BOOLEAN NOT NULL DEFAULT TRUE,
  created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
  updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);

CREATE INDEX IF NOT EXISTS idx_scheduled_jobs_enabled ON scheduled_jobs (enabled);