You've already forked RekomenciBackend
72 lines
2.4 KiB
Python
72 lines
2.4 KiB
Python
from collections.abc import Callable
|
|
|
|
from Levenshtein import ratio
|
|
|
|
from template_project.application.common.unit_of_work import UnitOfWork
|
|
from template_project.application.resume.data_gateway import ResumeDataGateway
|
|
from template_project.application.resume.entity import Resume, ResumeEmbedding, ResumePrediction
|
|
from template_project.application.resume.vector_generator import ResumeEmbeddingVectorGenerator
|
|
|
|
|
|
def suitable_resumes_key(
|
|
resume: Resume,
|
|
) -> Callable[[Resume], bool]:
|
|
def wrapper(suitable_resume: Resume) -> bool:
|
|
count_skills = 0
|
|
ratio_skill_sum = 0.0
|
|
for resum_key_skill in resume.key_skills:
|
|
for suitable_resume_key_skill in suitable_resume.key_skills:
|
|
ratio_skill = ratio(resum_key_skill, suitable_resume_key_skill)
|
|
if ratio_skill != 0:
|
|
count_skills += 1
|
|
ratio_skill_sum += ratio_skill
|
|
|
|
try:
|
|
matching_skills = ratio_skill_sum / count_skills
|
|
except ZeroDivisionError:
|
|
matching_skills = 0
|
|
|
|
return resume.experience_type == suitable_resume.experience_type and matching_skills >= 50
|
|
|
|
return wrapper
|
|
|
|
|
|
class ResumeEmbeddingPipeline:
|
|
def __init__(
|
|
self,
|
|
unit_of_work: UnitOfWork,
|
|
resume_data_gateway: ResumeDataGateway,
|
|
vector_generator: ResumeEmbeddingVectorGenerator,
|
|
) -> None:
|
|
self.unit_of_work = unit_of_work
|
|
self.resume_data_gateway = resume_data_gateway
|
|
self.vector_generator = vector_generator
|
|
|
|
async def run(
|
|
self,
|
|
resume: Resume,
|
|
) -> ResumePrediction:
|
|
vector = await self.vector_generator.generate(
|
|
position=resume.position,
|
|
about_me=resume.about_me,
|
|
key_skills=resume.key_skills,
|
|
)
|
|
resume_embedding = ResumeEmbedding.factory(
|
|
resume_id=resume.id,
|
|
vector=vector,
|
|
)
|
|
|
|
suitable_resumes = await self.resume_data_gateway.get_suitable_resumes(resume_embedding.id)
|
|
suitable_resumes_filtered = sorted(
|
|
suitable_resumes,
|
|
key=suitable_resumes_key(resume),
|
|
)
|
|
suitable_resumes = suitable_resumes_filtered[:50]
|
|
|
|
# TODO: тут надо сделать отправку в ИИ
|
|
|
|
await self.unit_of_work.add(resume_embedding)
|
|
await self.unit_of_work.commit()
|
|
|
|
raise NotImplementedError
|