Update app.py

app.py

@@ -9,7 +9,7 @@ import os
 sentiment_pipeline = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment")
 classification_pipeline = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 ner_pipeline = pipeline("token-classification", model="dslim/bert-base-NER", grouped_entities=True)
-emotion_classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=1)
+emotion_classifier = pipeline("text-classification", model="bhadresh-savani/distilbert-base-uncased-emotion")
 intent_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 summary_generator = pipeline("summarization", model="facebook/bart-large-cnn")
 
@@ -72,29 +72,14 @@ def get_emotion(text: str) -> str:
     except Exception as e:
         return f"Error in emotion detection: {e}"
 '''
-def get_emotion(text: str) -> str:
+
+def detect_emotion(text):
     try:
-        # Get the classification result
-        result = emotion_classifier(text)
-        
-        # Check if the result is a list and has at least one item
-        if result and isinstance(result, list) and len(result) > 0:
-            emotion_label = result[0]['label']  # Access the label of the first result
-            return emotion_label.capitalize()  # Capitalize for readability
-        return "Unknown emotion"  # Fallback if no label found
+        return emotion_classifier(text, truncation=True)[0]['label']
     except Exception as e:
         return f"Error in emotion detection: {e}"
 
 
-# Function to handle long conversations for emotion detection
-def analyze_long_text_emotion(text: str, chunk_size: int = 512) -> str:
-    # Split the text into chunks of the specified size
-    chunks = [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]
-    emotions = [get_emotion(chunk) for chunk in chunks]
-    # Aggregate results by counting the frequency of each emotion
-    emotion_counts = {label: emotions.count(label) for label in set(emotions)}
-    return max(emotion_counts, key=emotion_counts.get)  # Return the most frequent emotion
-        
 # Function to classify issue
 # Function to classify issue with optional user-provided labels
 def classify_issue(text, user_labels=None):
@@ -221,7 +206,7 @@ def analyze_conversation(conversation, custom_labels):
     issue_category = classify_issue(conversation, user_labels=user_labels)
     resolution_status = get_resolution_status(conversation)
     entities = extract_entities(conversation)
-    emotion = analyze_long_text_emotion(conversation)
+    emotion = detect_emotion(conversation)
     intent = detect_intent(conversation)
     agent_metrics = calculate_agent_metrics(conversation)
     topic = generate_topics_with_keybert(conversation)