feat(): load key skills and vacancies scripts

Containerfile

@@ -16,7 +16,6 @@ WORKDIR /app
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
-    PYTHONOPTIMIZE=2 \
     UV_COMPILE_BYTECODE=1 \
     UV_LINK_MODE=copy \
     UV_PROJECT_ENVIRONMENT=/opt/venv
@@ -48,7 +47,6 @@ RUN apt-get update && \
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
-    PYTHONOPTIMIZE=2 \
     PATH="/opt/venv/bin:$PATH" \
     PYTHONPATH="/app:$PYTHONPATH"
 
@@ -73,7 +71,6 @@ RUN apt-get update && \
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
-    PYTHONOPTIMIZE=2 \
     PATH="/opt/venv/bin:$PATH" \
     PYTHONPATH="/app:$PYTHONPATH"
 
@@ -93,7 +90,6 @@ FROM base-builder AS tests
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
-    PYTHONOPTIMIZE=2 \
     PATH="/opt/venv/bin:$PATH" \
     PYTHONPATH="/app:$PYTHONPATH"
 
@@ -115,7 +111,6 @@ FROM base-builder AS migrations
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
-    PYTHONOPTIMIZE=2 \
     PATH="/opt/venv/bin:$PATH" \
     PYTHONPATH="/app:$PYTHONPATH"
 

pyproject.toml

@@ -164,6 +164,7 @@ select = [
     "YTT", # flake8-2020
 ]
 ignore = [
+    "PLR1702",
     "A005", # allow to shadow stdlib and builtin module names
     "COM812", # trailing comma, conflicts with `ruff format`
     # Different doc rules that we don't really care about:

src/dataset/load_skills.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+import asyncio
+import json
+from pathlib import Path
+
+from template_project.adapters.data_gateways.key_skills import KeySkillsDataGateway
+from template_project.adapters.unit_of_work import DefaultUnitOfWork
+from template_project.web_api.configuration import load_configuration
+from template_project.web_api.ioc.make import make_ioc
+
+
+async def main() -> None:
+    config_path = Path("config.toml")
+    configuration = load_configuration(config_path)
+
+    container = make_ioc(configuration)
+
+    try:
+        async with container() as request_container:
+            data_gateway = await request_container.get(KeySkillsDataGateway)
+            unit_of_work = await request_container.get(DefaultUnitOfWork)
+
+            json_path = Path("full_skills_unique.json")
+            with json_path.open("r", encoding="utf-8") as f:
+                all_skills: list[str] = json.load(f)
+
+            skills_to_load = all_skills[:50000]
+
+            print(f"Загружаю {len(skills_to_load)} скиллов в БД...")
+
+            batch_size = 100
+            for i in range(0, len(skills_to_load), batch_size):
+                batch = skills_to_load[i : i + batch_size]
+                await data_gateway.add_skills(batch)
+                await unit_of_work.commit()
+                print(f"Загружено {min(i + batch_size, len(skills_to_load))} / {len(skills_to_load)}")
+
+            print("Готово!")
+    finally:
+        await container.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

src/dataset/load_vacancies.py

@@ -0,0 +1,128 @@
+#!/usr/bin/env python3
+import ast
+import asyncio
+import csv
+from decimal import Decimal
+from pathlib import Path
+
+from template_project.adapters.unit_of_work import DefaultUnitOfWork
+from template_project.application.common.embedding import Embedder
+from template_project.application.common.enums import ExperienceType
+from template_project.application.vacancy.entity import Vacancy, VacancyEmbedding
+from template_project.ml.configuration import load_configuration as load_ml_configuration
+from template_project.ml.ioc.make import make_ioc as make_ml_ioc
+from template_project.web_api.configuration import load_configuration as load_backend_configuration
+from template_project.web_api.ioc.make import make_ioc as make_backend_ioc
+
+
+def parse_skills(skills_str: str) -> list[str]:
+    try:
+        skills = ast.literal_eval(skills_str)
+        if isinstance(skills, list):
+            return [str(skill) for skill in skills]
+        return []  # noqa
+    except (ValueError, SyntaxError):
+        return []
+
+
+def compose_embedding_text(position: str, description: str, key_skills: list[str]) -> str:
+    skills_text = ", ".join(key_skills) if key_skills else ""
+    parts = [position, description, skills_text]
+    return " ".join(filter(None, parts))
+
+
+async def main() -> None:
+    backend_config_path = Path("config.toml")
+    backend_configuration = load_backend_configuration(backend_config_path)
+    backend_container = make_backend_ioc(backend_configuration)
+
+    ml_config_path = Path("infrastructure/configs/ml/config.toml")
+    ml_configuration = load_ml_configuration(ml_config_path)
+    ml_container = make_ml_ioc(ml_configuration)
+
+    csv_path = Path("filtered_vacancies.csv")
+    max_records = 51
+
+    try:
+        async with backend_container() as backend_request_container, ml_container() as ml_request_container:
+            unit_of_work = await backend_request_container.get(DefaultUnitOfWork)
+            embedder = await ml_request_container.get(Embedder)
+
+            print(f"Загружаю первые {max_records} вакансий из {csv_path}...")
+
+            with csv_path.open("r", encoding="utf-8") as f:
+                reader = csv.DictReader(f)
+                batch_size = 50
+                batch = []
+
+                for idx, row in enumerate(reader):
+                    if idx >= max_records:
+                        break
+
+                    try:
+                        vacancy_id_str = row.get("vacancy_id", "").strip()
+                        if not vacancy_id_str:
+                            continue
+
+                        position = row.get("vacancy_nm", "").strip()
+                        if not position:
+                            continue
+
+                        experience_str = row.get("experience", "").strip()
+                        try:
+                            experience_type = ExperienceType(experience_str)
+                        except ValueError:
+                            continue
+
+                        salary_from_str = row.get("salary_from", "").strip()
+                        salary_to_str = row.get("salary_to", "").strip()
+                        try:
+                            salary_from = Decimal(salary_from_str) if salary_from_str else Decimal(0)
+                            salary_to = Decimal(salary_to_str) if salary_to_str else Decimal(0)
+                        except (ValueError, TypeError):
+                            continue
+
+                        description = row.get("vacancy_description", "").strip()
+                        key_skills = parse_skills(row.get("key_skills", "[]"))
+
+                        vacancy = Vacancy.factory(
+                            position=position,
+                            from_salary=salary_from,
+                            to_salary=salary_to,
+                            experience_type=experience_type,
+                            description=description,
+                            key_skills=key_skills,
+                        )
+
+                        embedding_text = compose_embedding_text(position, description, key_skills)
+                        embedding_vector = await embedder.encode(embedding_text)
+
+                        embedding = VacancyEmbedding.factory(
+                            vacancy_id=vacancy.id,
+                            vector=embedding_vector,
+                        )
+
+                        await unit_of_work.add(vacancy, embedding)
+                        batch.append((vacancy.id, position))
+
+                        if len(batch) >= batch_size:
+                            await unit_of_work.commit()
+                            print(f"Загружено {len(batch)} вакансий (всего: {idx + 1})")
+                            batch = []
+
+                    except Exception as e:
+                        print(f"Ошибка при обработке строки {idx + 1}: {e}")
+                        continue
+
+                if batch:
+                    await unit_of_work.commit()
+                    print(f"Загружено {len(batch)} вакансий (всего: {idx + 1})")
+
+            print("Готово!")
+    finally:
+        await backend_container.close()
+        await ml_container.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

src/template_project/adapters/data_gateways/tables.py

@@ -34,6 +34,7 @@ from template_project.application.resume.entity import (
 )
 from template_project.application.user.entity import User
 from template_project.application.user.profile.entity import Profile
+from template_project.application.vacancy.entity import Vacancy, VacancyEmbedding
 
 meta_data: Final = MetaData()
 mapper_registry: Final = registry()
@@ -205,6 +206,30 @@ resume_project_table: Final = Table(
     Column("description", String, nullable=False),
 )
 
+vacancy_table: Final = Table(
+    "vacancy",
+    meta_data,
+    Column("id", UUID, primary_key=True),
+    Column("deleted_at", DateTime(timezone=True)),
+    Column("created_at", DateTime(timezone=True), nullable=False),
+    Column("position", String, nullable=False),
+    Column("from_salary", Numeric, nullable=False),
+    Column("to_salary", Numeric, nullable=False),
+    Column("experience_type", String, nullable=False),
+    Column("description", String, nullable=False),
+    Column("key_skills", StringArrayType(), nullable=False, server_default=text("'[]'::jsonb")),
+)
+
+vacancy_embedding_table: Final = Table(
+    "vacancy_embedding",
+    meta_data,
+    Column("id", UUID, primary_key=True),
+    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),
+)
+
 
 mapper_registry.map_imperatively(User, user_table)
 mapper_registry.map_imperatively(AccessToken, access_token_table)
@@ -229,3 +254,11 @@ mapper_registry.map_imperatively(
 mapper_registry.map_imperatively(ResumeExperience, resume_experience_table)
 mapper_registry.map_imperatively(ResumeEducation, resume_education_table)
 mapper_registry.map_imperatively(ResumeProject, resume_project_table)
+mapper_registry.map_imperatively(
+    Vacancy,
+    vacancy_table,
+    properties={
+        "key_skills": vacancy_table.c.key_skills,
+    },
+)
+mapper_registry.map_imperatively(VacancyEmbedding, vacancy_embedding_table)

src/template_project/application/vacancy/entity.py

@@ -1,12 +1,19 @@
+from datetime import UTC, datetime
 from decimal import Decimal
-from typing import Any
+from typing import NewType, Self
+from uuid import UUID
+
+from uuid_utils.compat import uuid7
 
 from template_project.application.common.entity import Entity, to_entity
 from template_project.application.common.enums import ExperienceType
 
+VacancyId = NewType("VacancyId", UUID)
+VacancyEmbeddingId = NewType("VacancyEmbeddingId", UUID)
+
 
 @to_entity
-class Vacancy(Entity[Any]):
+class Vacancy(Entity[VacancyId]):
     position: str
     from_salary: Decimal
     to_salary: Decimal
@@ -14,8 +21,42 @@ class Vacancy(Entity[Any]):
     description: str
     key_skills: list[str]
 
+    @classmethod
+    def factory(
+        cls,
+        position: str,
+        from_salary: Decimal,
+        to_salary: Decimal,
+        experience_type: ExperienceType,
+        description: str,
+        key_skills: list[str],
+    ) -> Self:
+        return cls(
+            id=VacancyId(uuid7()),
+            created_at=datetime.now(tz=UTC),
+            position=position,
+            from_salary=from_salary,
+            to_salary=to_salary,
+            experience_type=experience_type,
+            description=description,
+            key_skills=key_skills,
+        )
+
 
 @to_entity
-class VacancyEmbedding(Entity[Any]):
-    vacancy_id: Any
+class VacancyEmbedding(Entity[VacancyEmbeddingId]):
+    vacancy_id: VacancyId
     vector: list[float]
+
+    @classmethod
+    def factory(
+        cls,
+        vacancy_id: VacancyId,
+        vector: list[float],
+    ) -> Self:
+        return cls(
+            id=VacancyEmbeddingId(uuid7()),
+            created_at=datetime.now(tz=UTC),
+            vacancy_id=vacancy_id,
+            vector=vector,
+        )

src/template_project/migrations/versions/9a32674539dd_.py

@@ -0,0 +1,58 @@
+"""empty message
+
+Revision ID: 9a32674539dd
+Revises: 892aba57b356
+Create Date: 2025-11-23 01:26:29.515334
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import pgvector.sqlalchemy
+from sqlalchemy import Text
+from sqlalchemy.dialects.postgresql import JSONB, UUID
+import template_project.adapters.data_gateways.tables
+from template_project.adapters.data_gateways.tables import StringArrayType
+
+
+# revision identifiers, used by Alembic.
+revision: str = '9a32674539dd'
+down_revision: Union[str, Sequence[str], None] = '892aba57b356'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('vacancy',
+    sa.Column('id', sa.UUID(), nullable=False),
+    sa.Column('deleted_at', sa.DateTime(timezone=True), nullable=True),
+    sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
+    sa.Column('position', sa.String(), nullable=False),
+    sa.Column('from_salary', sa.Numeric(), nullable=False),
+    sa.Column('to_salary', sa.Numeric(), nullable=False),
+    sa.Column('experience_type', sa.String(), nullable=False),
+    sa.Column('description', sa.String(), nullable=False),
+    sa.Column('key_skills', template_project.adapters.data_gateways.tables.StringArrayType(astext_type=Text()), server_default=sa.text("'[]'::jsonb"), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_table('vacancy_embedding',
+    sa.Column('id', sa.UUID(), nullable=False),
+    sa.Column('deleted_at', sa.DateTime(timezone=True), nullable=True),
+    sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
+    sa.Column('vacancy_id', sa.UUID(), nullable=False),
+    sa.Column('vector', pgvector.sqlalchemy.vector.VECTOR(), nullable=False),
+    sa.ForeignKeyConstraint(['vacancy_id'], ['vacancy.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('vacancy_embedding')
+    op.drop_table('vacancy')
+    # ### end Alembic commands ###