Spaces:
Sleeping
Sleeping
File size: 3,967 Bytes
1e0aa4f eb7ed70 1e0aa4f eb7ed70 1e0aa4f eb7ed70 1e0aa4f eb7ed70 fc1fade 1e0aa4f fc1fade 1e0aa4f fc1fade eb7ed70 1e0aa4f fc1fade eb7ed70 1e0aa4f eb7ed70 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
import json
import logging
from typing import Dict, Any, List
from src.config import load_pdf
from src.agents.cv_agents import CVAgentOrchestrator
from src.agents.scoring_agent import SimpleScoringAgent
logger = logging.getLogger(__name__)
class CVParsingService:
def __init__(self, models: Dict[str, Any]):
self.models = models
self.orchestrator = CVAgentOrchestrator(models.get("llm"))
self.scoring_agent = SimpleScoringAgent()
def parse_cv(self, pdf_path: str) -> Dict[str, Any]:
cv_text = load_pdf(pdf_path)
if not cv_text or not cv_text.strip():
return self._create_fallback_data()
logger.info(f"CV text loaded: {len(cv_text)} characters")
sections = self.orchestrator.split_cv_sections(cv_text)
logger.info(f"Sections extracted: {list(sections.keys())}")
cv_data = self.orchestrator.extract_all_sections(sections)
logger.info(f"CV data extracted: {cv_data is not None}")
if not cv_data or not cv_data.get("candidat") or not self._is_valid_extraction(cv_data):
logger.warning("Agent extraction failed or incomplete, using fallback extraction")
return self.fallback_extractor.extract_basic_info(cv_text)
logger.info("Calculating skill levels...")
scores = self.scoring_agent.calculate_scores(cv_data["candidat"])
if scores and scores.get("analyse_competences"):
cv_data["candidat"].update(scores)
skills_count = len(scores.get("analyse_competences", []))
levels_summary = self._get_levels_summary(scores.get("analyse_competences", []))
logger.info(f"Skill levels calculated: {skills_count} skills - {levels_summary}")
else:
logger.warning("No skill levels calculated, adding empty analysis")
cv_data["candidat"]["analyse_competences"] = []
return cv_data
def _get_levels_summary(self, competences: List[Dict[str, Any]]) -> str:
"""Génère un résumé des niveaux de compétences"""
levels_count = {}
for comp in competences:
level = comp.get("level", "unknown")
levels_count[level] = levels_count.get(level, 0) + 1
return ", ".join([f"{count} {level}" for level, count in levels_count.items()])
def _is_valid_extraction(self, cv_data: Dict[str, Any]) -> bool:
"""Vérifie si l'extraction contient des données valides"""
candidat = cv_data.get("candidat", {})
has_info = bool(candidat.get("informations_personnelles", {}).get("nom", "").strip())
has_skills = bool(candidat.get("compétences", {}).get("hard_skills", []) or
candidat.get("compétences", {}).get("soft_skills", []))
has_experience = bool(candidat.get("expériences", []))
return has_info or has_skills or has_experience
logger.info("Calculating scores...")
scores = self.scoring_agent.calculate_scores(cv_data["candidat"])
if scores and scores.get("analyse_competences"):
cv_data["candidat"].update(scores)
logger.info(f"Scores calculated: {len(scores.get('analyse_competences', []))} skills scored")
else:
logger.warning("No scores calculated, adding empty analysis")
cv_data["candidat"]["analyse_competences"] = []
return cv_data
def _is_valid_extraction(self, cv_data: Dict[str, Any]) -> bool:
"""Vérifie si l'extraction contient des données valides"""
candidat = cv_data.get("candidat", {})
has_info = bool(candidat.get("informations_personnelles", {}).get("nom", "").strip())
has_skills = bool(candidat.get("compétences", {}).get("hard_skills", []) or
candidat.get("compétences", {}).get("soft_skills", []))
has_experience = bool(candidat.get("expériences", []))
return has_info or has_skills or has_experience |