Create src/services/cv_service.py

src/services/cv_service.py

@@ -0,0 +1,56 @@
+import json
+import logging
+from typing import Dict, Any
+from src.config import load_pdf
+from src.agents.cv_agents import CVAgentOrchestrator
+from src.agents.scoring_agent import ScoringAgent
+
+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 = ScoringAgent()
+    
+    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()
+        
+        sections = self.orchestrator.split_cv_sections(cv_text)
+        cv_data = self.orchestrator.extract_all_sections(sections)
+        
+        if cv_data and cv_data.get("candidat"):
+            scores = self.scoring_agent.calculate_scores(cv_data["candidat"])
+            cv_data["candidat"].update(scores)
+        
+        return cv_data
+    
+    def _create_fallback_data(self) -> Dict[str, Any]:
+        return {
+            "candidat": {
+                "informations_personnelles": {
+                    "nom": "Non spécifié",
+                    "email": "Non spécifié",
+                    "numero_de_telephone": "Non spécifié",
+                    "localisation": "Non spécifiée"
+                },
+                "compétences": {
+                    "hard_skills": [],
+                    "soft_skills": []
+                },
+                "expériences": [],
+                "projets": {
+                    "professional": [],
+                    "personal": []
+                },
+                "formations": [],
+                "reconversion": {
+                    "is_reconversion": False,
+                    "analysis": "Analyse non disponible"
+                },
+                "analyse_competences": []
+            }
+        }