Update app.py

app.py

@@ -1,4 +1,4 @@
-from streamlit_webrtc import webrtc_streamer, WebRtcMode
+from streamlit_webrtc import webrtc_streamer, WebRtcMode, AudioProcessorBase
 from sentiment_analysis import analyze_sentiment, transcribe_with_chunks
 from product_recommender import ProductRecommender
 from objection_handler import ObjectionHandler
@@ -11,9 +11,6 @@ import pandas as pd
 import plotly.express as px
 import streamlit as st
 import numpy as np
-from io import BytesIO
-import wave
-import threading
 import queue
 
 # Initialize components
@@ -25,94 +22,20 @@ model = SentenceTransformer('all-MiniLM-L6-v2')
 transcription_queue = queue.Queue()
 
 def generate_comprehensive_summary(chunks):
-    """
-    Generate a comprehensive summary from conversation chunks
-    """
-    # Extract full text from chunks
-    full_text = " ".join([chunk[0] for chunk in chunks])
-    
-    # Perform basic analysis
-    total_chunks = len(chunks)
-    sentiments = [chunk[1] for chunk in chunks]
-    
-    # Determine overall conversation context
-    context_keywords = {
-        'product_inquiry': ['dress', 'product', 'price', 'stock'],
-        'pricing': ['cost', 'price', 'budget'],
-        'negotiation': ['installment', 'payment', 'manage']
-    }
-    
-    # Detect conversation themes
-    themes = []
-    for keyword_type, keywords in context_keywords.items():
-        if any(keyword.lower() in full_text.lower() for keyword in keywords):
-            themes.append(keyword_type)
-    
-    # Basic sentiment analysis
-    positive_count = sentiments.count('POSITIVE')
-    negative_count = sentiments.count('NEGATIVE')
-    neutral_count = sentiments.count('NEUTRAL')
-    
-    # Key interaction highlights
-    key_interactions = []
-    for chunk in chunks:
-        if any(keyword.lower() in chunk[0].lower() for keyword in ['price', 'dress', 'stock', 'installment']):
-            key_interactions.append(chunk[0])
-    
-    # Construct summary
-    summary = f"Conversation Summary:\n"
-    
-    # Context and themes
-    if 'product_inquiry' in themes:
-        summary += "• Customer initiated a product inquiry about items.\n"
-    
-    if 'pricing' in themes:
-        summary += "• Price and budget considerations were discussed.\n"
-    
-    if 'negotiation' in themes:
-        summary += "• Customer and seller explored flexible payment options.\n"
-    
-    # Sentiment insights
-    summary += f"\nConversation Sentiment:\n"
-    summary += f"• Positive Interactions: {positive_count}\n"
-    summary += f"• Negative Interactions: {negative_count}\n"
-    summary += f"• Neutral Interactions: {neutral_count}\n"
-    
-    # Key highlights
-    summary += "\nKey Conversation Points:\n"
-    for interaction in key_interactions[:3]:  # Limit to top 3 key points
-        summary += f"• {interaction}\n"
-    
-    # Conversation outcome
-    if positive_count > negative_count:
-        summary += "\nOutcome: Constructive and potentially successful interaction."
-    elif negative_count > positive_count:
-        summary += "\nOutcome: Interaction may require further follow-up."
-    else:
-        summary += "\nOutcome: Neutral interaction with potential for future engagement."
-    
-    return summary
+    # Your existing function implementation
+    pass
 
 def is_valid_input(text):
-    text = text.strip().lower()
-    if len(text) < 3 or re.match(r'^[a-zA-Z\s]*$', text) is None:
-        return False
-    return True
+    # Your existing function implementation
+    pass
 
 def is_relevant_sentiment(sentiment_score):
-    return sentiment_score > 0.4
+    # Your existing function implementation
+    pass
 
 def calculate_overall_sentiment(sentiment_scores):
-    if sentiment_scores:
-        average_sentiment = sum(sentiment_scores) / len(sentiment_scores)
-        overall_sentiment = (
-            "POSITIVE" if average_sentiment > 0 else
-            "NEGATIVE" if average_sentiment < 0 else
-            "NEUTRAL"
-        )
-    else:
-        overall_sentiment = "NEUTRAL"
-    return overall_sentiment
+    # Your existing function implementation
+    pass
 
 def handle_objection(text):
     query_embedding = model.encode([text])
@@ -122,52 +45,40 @@ def handle_objection(text):
         return "\n".join(responses) if responses else "No objection response found."
     return "No objection response found."
 
-def transcribe_audio(audio_bytes, sample_rate=16000):
-    """Transcribe audio using the transcribe_with_chunks function from sentiment_analysis.py."""
-    try:
-        # Save audio bytes to a temporary WAV file
-        with BytesIO() as wav_buffer:
-            with wave.open(wav_buffer, 'wb') as wf:
-                wf.setnchannels(1)  # Mono audio
-                wf.setsampwidth(2)  # 2 bytes for int16
-                wf.setframerate(sample_rate)  # Sample rate
-                wf.writeframes(audio_bytes)
+class AudioProcessor(AudioProcessorBase):
+    def __init__(self):
+        self.sr = 16000  # Sample rate
+        self.q = transcription_queue
 
+    def recv(self, frame):
+        audio_data = frame.to_ndarray()
+        audio_bytes = (audio_data * 32767).astype(np.int16).tobytes()  # Convert to int16 format
+
+        # Transcribe the audio
+        text = self.transcribe_audio(audio_bytes)
+        if text:
+            self.q.put(text)  # Add transcribed text to the queue
+
+        return frame
+
+    def transcribe_audio(self, audio_bytes):
+        try:
             # Use the transcribe_with_chunks function from sentiment_analysis.py
             chunks = transcribe_with_chunks({})  # Pass an empty objections_dict for now
             if chunks:
                 return chunks[-1][0]  # Return the latest transcribed text
-    except Exception as e:
-        print(f"Error transcribing audio: {e}")
-    return None
-
-def audio_processing_thread(audio_frame):
-    """Thread function to process audio frames."""
-    # Convert audio frame to bytes
-    audio_data = audio_frame.to_ndarray()
-    print(f"Audio data shape: {audio_data.shape}")  # Debug: Check audio data shape
-    print(f"Audio data sample: {audio_data[:10]}")  # Debug: Check first 10 samples
-
-    audio_bytes = (audio_data * 32767).astype(np.int16).tobytes()  # Convert to int16 format
-
-    # Transcribe the audio
-    text = transcribe_audio(audio_bytes)
-    if text:
-        transcription_queue.put(text)  # Add transcribed text to the queue
+        except Exception as e:
+            print(f"Error transcribing audio: {e}")
+        return None
 
 def real_time_analysis():
     st.info("Listening... Say 'stop' to end the process.")
 
-    def audio_frame_callback(audio_frame):
-        # Start a new thread to process the audio frame
-        threading.Thread(target=audio_processing_thread, args=(audio_frame,)).start()
-        return audio_frame
-
     # Start WebRTC audio stream
     webrtc_ctx = webrtc_streamer(
         key="real-time-audio",
         mode=WebRtcMode.SENDONLY,
-        audio_frame_callback=audio_frame_callback,
+        audio_processor_factory=AudioProcessor,
         media_stream_constraints={"audio": True, "video": False},
     )
 
@@ -289,4 +200,4 @@ def run_app():
             st.error(f"Error loading dashboard: {e}")
 
 if __name__ == "__main__":
-    run_app()
+    run_app()