Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 import os
+from datetime import datetime
 from typing import List, Dict, Tuple
 from extractors import extract_docx, extract_pdf, validate_extraction
 from tagging import tag_speakers_advanced
@@ -8,8 +9,36 @@ from llm import query_llm, extract_structured_data
 from reporting import generate_enhanced_csv, generate_enhanced_pdf
 from dashboard import generate_comprehensive_dashboard
 from validation import validate_transcript_quality, check_data_completeness
-#from audio_transcriber import transcribe_with_diarization_streaming
+from audio_transcriber import transcribe_with_diarization_streaming
 
+# HuggingFace Spaces Configuration
+import os
+os.environ["LLM_BACKEND"] = "hf_api"
+os.environ["LLM_TIMEOUT"] = "25"
+os.environ["MAX_TOKENS_PER_REQUEST"] = "100"
+print("🚀 Running on HuggingFace Spaces - Optimized Configuration Loaded")
+
+def preprocess_audio(audio_files, num_speakers):
+    """Convert audio to transcripts"""
+    if not audio_files:
+        return None, "No audio files provided"
+    
+    transcript_paths = []
+    status = ""
+    
+    for audio in audio_files:
+        try:
+            # Get the actual file path
+            audio_path = audio.name if hasattr(audio, 'name') else str(audio)
+            
+            transcript_path = transcribe_with_diarization(audio_path, num_speakers)
+            transcript_paths.append(transcript_path)
+            status += f"✓ {os.path.basename(audio_path)} → {transcript_path}\n"
+        except Exception as e:
+            status += f"✗ {os.path.basename(audio_path)}: {str(e)}\n"
+    
+    # Return list of paths for file component
+    return transcript_paths if transcript_paths else None, status
 
 
 def analyze(files, file_type, user_comments, role_hint, debug_mode, interviewee_type, progress=gr.Progress()):
@@ -173,16 +202,44 @@ Additional Instructions:
             print(f"[File {i+1}] ✓ Processing complete")
             
         except Exception as e:
-            error_msg = f"[Error] {file_name} failed: {str(e)}"
+            # Enhanced error tracking with type and traceback
+            import traceback
+            error_type = type(e).__name__
+            error_details = str(e)
+            error_traceback = traceback.format_exc()
+
+            error_msg = f"[{error_type}] {file_name}: {error_details}"
             print(error_msg)
-            processing_errors.append(error_msg)
+
+            # Store comprehensive error information
+            processing_errors.append({
+                "transcript_id": f"Transcript {i+1}",
+                "file_name": file_name,
+                "error_type": error_type,
+                "error_message": error_details[:200],  # Truncate long messages
+                "timestamp": datetime.now().isoformat()
+            })
+
             all_results.append({
                 "transcript_id": f"Transcript {i+1}",
                 "file_name": file_name,
                 "full_text": error_msg,
                 "structured_data": {},
                 "quality_score": 0.0,
-                "word_count": 0
+                "word_count": 0,
+                "processing_status": "FAILED",
+                "error_type": error_type
+            })
+
+            # Add to CSV with error metadata
+            csv_rows.append({
+                "Transcript ID": f"Transcript {i+1}",
+                "File Name": file_name,
+                "Quality Score": 0.0,
+                "Word Count": 0,
+                "Processing Status": "FAILED",
+                "Error Type": error_type,
+                "Error Message": error_details[:100]
             })
     
     # Generate cross-transcript summary
@@ -256,16 +313,96 @@ Additional Instructions:
     Be specific. Use numbers. Cite transcript IDs. Flag weak evidence.
     """
         
-        summary, summary_data = query_llm(
-            summary_prompt, 
-            user_context, 
-            interviewee_type,
-            extract_structured=False,
-            is_summary=True
+        # Use robust LLM with aggressive timeout protection
+        print("[Summary] Generating cross-transcript summary...")
+        print("[Summary] Note: This may take 30-60 seconds for large datasets")
+
+        try:
+            from llm_robust import query_llm_with_timeout
+
+            summary, summary_data = query_llm_with_timeout(
+                summary_prompt,
+                user_context,
+                interviewee_type,
+                extract_structured=False,
+                is_summary=True,
+                max_timeout=60  # 60 second hard timeout
+            )
+        except Exception as e:
+            # Ultimate fallback
+            print(f"[Summary] Critical error: {e}")
+            print("[Summary] Using emergency fallback...")
+            from llm_robust import generate_emergency_summary
+            summary, summary_data = generate_emergency_summary(interviewee_type)
+
+        # Validate summary quality and retry if needed
+        from validation import validate_summary_quality
+        summary_score, summary_issues = validate_summary_quality(
+            summary,
+            len(valid_results)
         )
-        
-        print("[Summary] ✓ Generated")
-        
+
+        if summary_score < 0.7:  # Quality threshold
+            print(f"[Warning] Summary quality issues (score: {summary_score:.2f}): {summary_issues}")
+            print("[Summary] Retrying with stricter validation...")
+
+            # Retry with enhanced prompt emphasizing validation failures
+            retry_prompt = summary_prompt + f"""
+
+CRITICAL: Previous attempt failed validation with these issues:
+{chr(10).join('- ' + issue for issue in summary_issues)}
+
+MANDATORY CORRECTIONS:
+- Use ONLY specific numbers (e.g., "8 out of {len(valid_results)}" not "most")
+- Include percentages in parentheses
+- Cite transcript numbers for every claim
+- Minimum length: 500 words
+- No absolute terms (all/everyone/never/always) without 100% evidence
+"""
+
+            try:
+                summary, summary_data = query_llm_with_timeout(
+                    retry_prompt,
+                    user_context,
+                    interviewee_type,
+                    extract_structured=False,
+                    is_summary=True,
+                    max_timeout=60  # 60 second hard timeout for retry
+                )
+            except Exception as e:
+                print(f"[Summary] Retry also failed: {e}")
+                print("[Summary] Using emergency fallback for retry...")
+                summary, summary_data = generate_emergency_summary(interviewee_type)
+
+            # Re-validate
+            summary_score, summary_issues = validate_summary_quality(summary, len(valid_results))
+
+            if summary_score < 0.7:
+                # Add quality warning to summary header
+                warning_header = f"""[QUALITY WARNING - Score: {summary_score:.2f}]
+Validation issues detected: {'; '.join(summary_issues)}
+Please review findings carefully and verify against source data.
+
+{'='*60}
+
+"""
+                summary = warning_header + summary
+                print(f"[Warning] Summary still has issues after retry (score: {summary_score:.2f})")
+            else:
+                print(f"[Summary] ✓ Validation passed after retry (score: {summary_score:.2f})")
+        else:
+            print(f"[Summary] ✓ Validation passed (score: {summary_score:.2f})")
+
+        # Verify consensus claims against actual data
+        from validation import verify_consensus_claims
+        consensus_warnings = verify_consensus_claims(summary, valid_results)
+        if consensus_warnings:
+            print(f"[Warning] Consensus verification issues: {len(consensus_warnings)} found")
+            consensus_note = "\n\n[CONSENSUS VERIFICATION NOTES]:\n" + "\n".join(f"- {w}" for w in consensus_warnings) + "\n\n"
+            summary = summary + consensus_note
+        else:
+            print("[Summary] ✓ Consensus claims verified")
+
         # Generate enhanced reports
         csv_path = generate_enhanced_csv(csv_rows, interviewee_type)
         print(f"[CSV] ✓ Saved to {csv_path}")
@@ -373,7 +510,39 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     
     with gr.Tabs():
      
-        
+        with gr.TabItem("🎤 Audio Preprocessing"):
+            gr.Markdown("""
+            Upload audio interviews to auto-transcribe with speaker identification.
+            Outputs DOCX files ready for analysis.
+            """)
+            
+            with gr.Row():
+                audio_input = gr.File(
+                    label="Upload Audio Files",
+                    file_types=[".mp3", ".wav", ".m4a", ".flac"],
+                    file_count="multiple"
+                )
+                num_speakers_input = gr.Slider(
+                    minimum=1,
+                    maximum=5,
+                    value=2,
+                    step=1,
+                    label="Number of Speakers"
+                )
+            
+            transcribe_btn = gr.Button("🎙️ Transcribe Audio", variant="primary")
+            transcribe_status = gr.Textbox(label="Status", lines=10)
+            transcript_files = gr.File(label="Download Transcripts", file_count="multiple")
+            
+            transcribe_btn.click(
+                fn=preprocess_audio,
+                inputs=[audio_input, num_speakers_input],
+                outputs=[transcript_files, transcribe_status]
+            )
+            
+            gr.Markdown("""
+            **Next:** Download transcripts, then go to "Transcript Analysis" tab to analyze them.
+            """)
         
         
               
@@ -526,4 +695,12 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     """)
 
 if __name__ == "__main__":
-    demo.launch()
+demo.queue(
+    concurrency_count=1,
+    max_size=10,
+    api_open=False
+).launch(
+    server_name="0.0.0.0",
+    server_port=7860,
+    show_error=True
+)