"""pgvector embeddings

Revision ID: 0003_pgvector_embeddings
Revises: 0002_extend_tags
Create Date: 2026-04-10

Rewrite the embeddings table to use pgvector Vector(512) instead of
LargeBinary. Add composite PK (photo_id, model), created_at, and
HNSW index on vector column.
"""
from typing import Sequence, Union

from alembic import op
import sqlalchemy as sa

revision: str = "0003_pgvector_embeddings"
down_revision: Union[str, None] = "0002_extend_tags"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None


def upgrade() -> None:
    # Drop the old placeholder table and recreate with pgvector types.
    # No data to preserve — it was never populated.
    op.execute("DROP TABLE IF EXISTS embeddings")
    op.execute("""
        CREATE TABLE embeddings (
            photo_id VARCHAR NOT NULL REFERENCES photos(id) ON DELETE CASCADE,
            model VARCHAR(64) NOT NULL,
            vector vector(512),
            created_at TIMESTAMPTZ DEFAULT now(),
            PRIMARY KEY (photo_id, model)
        )
    """)
    # HNSW index for cosine similarity search.
    # Defer creation on large backfills — drop and recreate afterward.
    op.execute("""
        CREATE INDEX IF NOT EXISTS ix_embeddings_vector_hnsw
        ON embeddings USING hnsw (vector vector_cosine_ops)
    """)


def downgrade() -> None:
    op.execute("DROP TABLE IF EXISTS embeddings")
    op.execute("""
        CREATE TABLE embeddings (
            photo_id VARCHAR NOT NULL REFERENCES photos(id) ON DELETE CASCADE,
            model VARCHAR,
            vector BYTEA,
            PRIMARY KEY (photo_id)
        )
    """)