feat(): optimize queries by adding indexes, defining vector length and defining ef-search local parameter

src/template_project/adapters/data_gateways/tables.py

@@ -8,6 +8,7 @@ from sqlalchemy import (
     DateTime,
     Enum,
     ForeignKey,
+    Index,
     Integer,
     MetaData,
     Numeric,
@@ -178,7 +179,7 @@ resume_embedding_table: Final = Table(
     Column("deleted_at", DateTime(timezone=True)),
     Column("created_at", DateTime(timezone=True), nullable=False),
     Column("resume_id", UUID, ForeignKey("resume.id", ondelete="CASCADE"), nullable=False),
-    Column("vector", Vector, nullable=False),
+    Column("vector", Vector(384), nullable=False),
 )
 resume_prediction_table: Final = Table(
     "resume_prediction",
@@ -255,7 +256,22 @@ vacancy_embedding_table: Final = Table(
     Column("deleted_at", DateTime(timezone=True)),
     Column("created_at", DateTime(timezone=True), nullable=False),
     Column("vacancy_id", UUID, ForeignKey("vacancy.id", ondelete="CASCADE"), nullable=False),
-    Column("vector", Vector, nullable=False),
+    Column("vector", Vector(384), nullable=False),
+)
+
+key_skills_name_trgm_index: Final = Index(
+    "ix_key_skills_name_trgm",
+    key_skills_table.c.name,
+    postgresql_using="gin",
+    postgresql_ops={"name": "gin_trgm_ops"},
+)
+
+vacancy_embedding_vector_cosine_index: Final = Index(
+    "ix_vacancy_embedding_vector_cosine",
+    vacancy_embedding_table.c.vector,
+    postgresql_using="hnsw",
+    postgresql_ops={"vector": "vector_cosine_ops"},
+    postgresql_with={"m": 32, "ef_construction": 256},
 )
 
 

src/template_project/adapters/data_gateways/vacancy.py

@@ -1,7 +1,7 @@
 from collections.abc import Sequence
 from typing import override
 
-from sqlalchemy import label, select
+from sqlalchemy import label, select, text
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from template_project.adapters.data_gateways.tables import vacancy_embedding_table, vacancy_table
@@ -16,6 +16,7 @@ class DefaultVacancyDataGateway(VacancyDataGateway):
 
     @override
     async def get_suitable(self, vector: list[float]) -> Sequence[SuitableVacancy]:
+        await self._session.execute(text("SET LOCAL hnsw.ef_search = 128"))
         distance_expr = vacancy_embedding_table.c.vector.cosine_distance(vector)
         similarity_expr = 1 - distance_expr
         statement = (

src/template_project/migrations/versions/2c99db38e99b_.py

@@ -0,0 +1,37 @@
+"""empty message
+
+Revision ID: 2c99db38e99b
+Revises: 9a32674539dd
+Create Date: 2025-11-23 12:08:50.774495
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '2c99db38e99b'
+down_revision: Union[str, Sequence[str], None] = '9a32674539dd'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    op.execute("CREATE EXTENSION IF NOT EXISTS pg_trgm")
+    op.execute("ALTER TABLE vacancy_embedding ALTER COLUMN vector TYPE vector(384)")
+    op.execute("ALTER TABLE resume_embedding ALTER COLUMN vector TYPE vector(384)")
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_index('ix_key_skills_name_trgm', 'key_skills', ['name'], unique=False, postgresql_using='gin', postgresql_ops={'name': 'gin_trgm_ops'})
+    op.create_index('ix_vacancy_embedding_vector_cosine', 'vacancy_embedding', ['vector'], unique=False, postgresql_using='hnsw', postgresql_ops={'vector': 'vector_cosine_ops'}, postgresql_with={'m': 32, 'ef_construction': 256})
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index('ix_vacancy_embedding_vector_cosine', table_name='vacancy_embedding', postgresql_using='hnsw', postgresql_ops={'vector': 'vector_cosine_ops'}, postgresql_with={'m': 32, 'ef_construction': 256})
+    op.drop_index('ix_key_skills_name_trgm', table_name='key_skills', postgresql_using='gin', postgresql_ops={'name': 'gin_trgm_ops'})
+    # ### end Alembic commands ###