add pipline

This commit is contained in:
ivankirpichnikov
2025-11-23 01:42:46 +03:00
parent 7f91b412b8
commit 96e792b122
20 changed files with 219 additions and 43 deletions
@@ -1,11 +1,12 @@
from collections.abc import Sequence
from typing import override
from sqlalchemy import select
from sqlalchemy import label, select
from sqlalchemy.ext.asyncio import AsyncSession
from template_project.adapters.data_gateways.tables import vacancy_embedding_table, vacancy_table
from template_project.application.vacancy.data_gateway import VacancyDataGateway
from template_project.application.vacancy.data_structure import SuitableVacancy
from template_project.application.vacancy.entity import Vacancy, VacancyEmbedding
@@ -14,11 +15,17 @@ class DefaultVacancyDataGateway(VacancyDataGateway):
self._session = session
@override
async def get_suitable(self, vector: list[float]) -> Sequence[Vacancy]:
async def get_suitable(self, vector: list[float]) -> Sequence[SuitableVacancy]:
statement = (
select(Vacancy)
select(Vacancy, label("resume_similarity", vacancy_embedding_table.c.vector.cosine_distance(vector)))
.join(VacancyEmbedding, vacancy_embedding_table.c.id == vacancy_table.c.id)
.where(vacancy_embedding_table.c.vector.cosine_distance(vector) > 0.5)
)
result = await self._session.execute(statement)
return result.scalars().all()
return [
SuitableVacancy(
vacancy=res[0],
resume_similarity=res[1],
)
for res in result.scalars()
]