Create cv_analyzer.py

cv_analyzer.py

@@ -0,0 +1,76 @@
+import json
+import logging
+from cv_prompt import (
+    ResumeQualityEvaluation,
+    get_section_detection_prompt, 
+    get_content_quality_prompt, 
+    calculate_section_detection_score, 
+    calculate_overall_score,
+    get_completeness_prompt
+)
+from openai_utils import get_ai_response
+from ocr_extractor import process_file
+from langchain.output_parsers import PydanticOutputParser
+from spelling_grammar_checker import evaluate_cv_text
+from personal_information import analyze_personal_info
+
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+def analyze_cv(file_content):
+    try:
+        extracted_text = process_file(file_content, 'ocr_weights.json')
+        logging.info("Text extracted successfully")
+
+        # Section Detection
+        sections_prompt = get_section_detection_prompt(extracted_text)
+        sections_response = get_ai_response([{"role": "user", "content": sections_prompt}])
+        if sections_response is None:
+            return {"error": "Failed to get AI response for sections"}
+
+        sections_data = json.loads(sections_response)
+        detected_sections = sections_data.get('present_sections', [])
+        section_detection_score = calculate_section_detection_score(detected_sections)
+        logging.info(f"Detected sections: {detected_sections}")
+        logging.info(f"Section detection score: {section_detection_score}")
+
+        # Content Quality Analysis
+        quality_prompt = get_content_quality_prompt(extracted_text)
+        quality_response = get_ai_response([{"role": "user", "content": quality_prompt}])
+        
+        if quality_response is None:
+            return {"error": "Failed to get AI response for content quality"}
+
+        parser = PydanticOutputParser(pydantic_object=ResumeQualityEvaluation)
+        evaluation_result = parser.parse(quality_response)
+        
+        overall_score = calculate_overall_score(evaluation_result)
+
+        # Spelling and Grammar Check
+        spelling_grammar_score = evaluate_cv_text(file_content, 'ocr_weights.json')
+
+        # Personal Information Analysis
+        personal_info = json.loads(analyze_personal_info(file_content))
+
+        # Completeness Analysis
+        completeness_prompt = get_completeness_prompt(extracted_text, detected_sections)
+        completeness_response = get_ai_response([{"role": "user", "content": completeness_prompt}])
+        if completeness_response is None:
+            return {"error": "Failed to get AI response for completeness analysis"}
+        completeness_analysis = json.loads(completeness_response)
+
+        logging.info("All analyses completed")
+        logging.info(f"Overall score: {overall_score}")
+
+        return {
+            "extracted_text": extracted_text,
+            "detected_sections": detected_sections,
+            "section_detection_score": section_detection_score,
+            "content_analysis": evaluation_result.dict(),
+            "overall_score": overall_score,
+            "spelling_grammar_score": spelling_grammar_score,
+            "personal_info": personal_info,
+            "completeness_analysis": completeness_analysis
+        }
+    except Exception as e:
+        logging.error(f"Error in CV analysis: {str(e)}", exc_info=True)
+        return {"error": str(e)}