Update process_interview.py

process_interview.py

@@ -387,23 +387,27 @@ def analyze_interviewee_voice(audio_path: str, utterances: List[Dict]) -> Dict:
         return {'error': f'Voice analysis incomplete due to audio processing issues: {str(e)}'}
 
 def generate_voice_interpretation(analysis: Dict) -> str:
-    if 'error' in analysis:
-        return f"Voice analysis unavailable: {analysis['error']}"
-    interpretation_lines = [
-        f"- Speaking rate: {analysis['speaking_rate', 0):.2f} words/sec (Benchmark: 2.0}-{3.0}; affects clarity)",
-        f"- Filler words: {analysis['filler_ratio'] * 100:.1f}% (High usage reduces credibility)",
-        f"- Anxiety: {analysis['interpretation']['anxiety_level']} (Score: {analysis['composite_scores']['anxiety']:.3f}; stress response)",
-        f"- Confidence: {analysis['interpretation']['confidence_level']} (Score: {analysis['composite_scores']['confidence']:.3f}; vocal strength)",
-        f"- Fluency: {analysis['interpretation']['fluency_level']} (Drives engagement)",
-        "",
-        "HR Insights:",
-        "- Rapid speech (>3.0 wps) may reduce clarity; slower pacing enhances professionalism.",
-        "- High filler word usage undermines perceived credibility.",
-        "- Elevated anxiety suggests pressure; training can improve resilience.",
-        "- Strong confidence supports leadership presence.",
-        "- Fluent speech enhances engagement in team settings."
-    ]
-    return "\n".join(interpretation_lines)
+    try:
+        if 'error' in analysis:
+            return f"Voice analysis unavailable: {analysis['error']}"
+        interpretation_lines = [
+            f"- Speaking rate: {analysis.get('speaking_rate', 0):.2f} words/sec (Benchmark: 2.0-3.0; affects clarity)",  # Fixed syntax error
+            f"- Filler words: {analysis.get('filler_ratio', 0) * 100:.1f}% (High usage reduces credibility)",
+            f"- Anxiety: {analysis.get('interpretation', {}).get('anxiety_level', 'N/A')} (Score: {analysis.get('composite_scores', {}).get('anxiety', 0):.3f}; stress response)",
+            f"- Confidence: {analysis.get('interpretation', {}).get('confidence_level', 'N/A')} (Score: {analysis.get('composite_scores', {}).get('confidence', 0):.3f}; vocal strength)",
+            f"- Fluency: {analysis.get('interpretation', {}).get('fluency_level', 'N/A')} (Drives engagement)",
+            "",
+            "HR Insights:",
+            "- Rapid speech (>3.0 wps) may reduce clarity; slower pacing enhances professionalism.",
+            "- High filler word usage undermines perceived credibility.",
+            "- Elevated anxiety suggests pressure; training can improve resilience.",
+            "- Strong confidence supports leadership presence.",
+            "- Fluent speech enhances engagement in team settings."
+        ]
+        return "\n".join(interpretation_lines)
+    except Exception as e:
+        logger.error(f"Error generating voice interpretation: {str(e)}")
+        return f"Voice analysis unavailable: Error in interpretation formatting"
 
 def generate_anxiety_confidence_chart(composite_scores: Dict, chart_buffer):
     try:
@@ -457,8 +461,9 @@ def generate_report(analysis_data: Dict) -> str:
         interviewee_responses = [u['text'] for u in analysis_data['transcript'] if u['role'] == 'Interviewee']
         if not interviewee_responses:
             logger.warning("No interviewee responses found for report generation")
-            return """**1. Executive Summary**
+            return f"""**1. Executive Summary**
 - Insufficient interviewee content to generate a summary.
+- Interview duration suggests limited engagement.
 
 **2. Communication and Vocal Dynamics**
 {voice_interpretation}
@@ -485,14 +490,15 @@ def generate_report(analysis_data: Dict) -> str:
             acceptance_line += "HR Verdict: Limited fit, significant improvement required."
         transcript_text = "\n".join([f"- {u['speaker']}: {u['text']}" for u in analysis_data['transcript']])
         prompt = f"""
-You are EvalBot, a senior HR consultant delivering a professional interview analysis report. Use clear headings with '**', bullet points ('-'), complete sentences, and formal language. Avoid redundancy, vague terms, and special characters that could break formatting (e.g., parentheses). Ensure each section is unique, actionable, and at least 2-3 bullet points long. If content is limited, provide reasonable inferences based on available data.
+You are EvalBot, a senior HR consultant delivering a professional interview analysis report. Use clear headings with '**', bullet points ('-'), complete sentences, and formal language. Avoid redundancy, vague terms, and special characters that could break formatting (e.g., parentheses). Ensure each section is unique, actionable, and contains at least 2-3 bullet points. If content is limited, provide reasonable inferences based on available data.
 
 **Input Data**
 - Suitability Score: {acceptance_prob:.2f}%
 - Interview Duration: {analysis_data['text_analysis']['total_duration']:.2f} seconds
 - Speaker Turns: {analysis_data['text_analysis']['speaker_turns']}
 - Participants: {', '.join(sorted(set(u['speaker'] for u in analysis_data['transcript'])))}
-- Voice Analysis: {voice_interpretation}
+- Voice Analysis: 
+{voice_interpretation}
 - Transcript Sample: 
 {transcript_text[:1000]}...
 
@@ -523,7 +529,7 @@ You are EvalBot, a senior HR consultant delivering a professional interview anal
 """
         response = gemini_model.generate_content(prompt)
         report_text = re.sub(r'[^\x00-\x7F]+|[()]+', '', response.text)
-        logger.info(f"Generated Gemini report: {report_text[:500]}...")  # Log first 500 chars for debugging
+        logger.info(f"Generated Gemini report: {report_text[:500]}...")  # Log for debugging
         return report_text
     except Exception as e:
         logger.error(f"Report generation failed: {str(e)}", exc_info=True)
@@ -562,7 +568,7 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
             canvas.saveState()
             canvas.setFont('Helvetica', 7)
             canvas.setFillColor(colors.HexColor('#666666'))
-            canvas.drawString(doc.leftMargin, 0.5*inch, f"Page {doc.page} | EvalBot HR Interview Report | Confidential")
+            canvas.drawString(doc.leftMargin, 0.5*inch, f"Page {doc.page} | EvalBot HR Interview Report | Confidential")  # Fixed typo
             canvas.setStrokeColor(colors.HexColor('#0050BC'))
             canvas.setLineWidth(0.5)
             canvas.line(doc.leftMargin, doc.height + 0.9*inch, doc.width + doc.leftMargin, doc.height + 0.9*inch)
@@ -609,8 +615,8 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
             ('TOPPADDING', (0,0), (-1,0), 6),
             ('BACKGROUND', (0,1), (-1,-1), colors.HexColor('#F5F6FA')),
             ('GRID', (0,0), (-1,-1), 0.4, colors.HexColor('#DDE4EB')),
-            ('LEFTPADDING', (1,3), (1,3), 10),  # Add padding for Participants
-            ('WORDWRAP', (1,3), (1,3), 'CJK'),  # Enable word wrapping
+            ('LEFTPADDING', (1,3), (1,3), 10),
+            ('WORDWRAP', (1,3), (1,3), 'CJK'),
         ]))
         story.append(table)
         story.append(Spacer(1, 0.3*inch))
@@ -695,7 +701,7 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
                 clean_line = line.lstrip('-').strip()
                 if not clean_line:
                     continue
-                clean_line = re.sub(r'[^\w\s.,;:-]', '', clean_line)  # Enhanced sanitization
+                clean_line = re.sub(r'[^\w\s.,;:-]', '', clean_line)
                 if current_section == 'Competency':
                     if any(k in clean_line.lower() for k in ['leader', 'problem', 'commun', 'adapt', 'achieve', 'skill', 'success']):
                         current_subsection = 'Strengths'
@@ -712,7 +718,7 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
                         sections[current_section][current_subsection].append(clean_line)
                 else:
                     sections[current_section].append(clean_line)
-            elif current_section and line:  # Handle non-bulleted lines
+            elif current_section and line:
                 clean_line = re.sub(r'[^\w\s.,;:-]', '', line)
                 sections[current_section].append(clean_line)