Update model.py

model.py

@@ -15,16 +15,17 @@ import logging
 import re
 
 # === Pipelines ===
-summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
+summarizer = pipeline("summarization", model="google/pegasus-xsum")
 qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
-emotion_pipeline = pipeline("text-classification", model="bhadresh-savani/distilbert-base-uncased-emotion", top_k=1)
+emotion_model = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=1)
 
 # === Brief Summarization ===
-def summarize_review(text, max_len=80, min_len=20):
+def summarize_review(text, max_len=60, min_len=15):
     try:
-        return summarizer(text, max_length=max_len, min_length=min_len, do_sample=False)[0]["summary_text"]
+        result = summarizer(text, max_length=max_len, min_length=min_len, do_sample=False)
+        return result[0]["summary_text"]
     except Exception as e:
-        logging.warning(f"Summarization fallback used: {e}")
+        logging.warning(f"Fallback to raw text due to summarization error: {e}")
         return text
 
 # === Smart Summarization with Clustering ===
@@ -54,18 +55,11 @@ def smart_summarize(text, n_clusters=1):
 
 # === Emotion Detection (Fixed) ===
 def detect_emotion(text):
-    try:
-        result = emotion_pipeline(text)
-        if isinstance(result, list) and len(result) > 0:
-            item = result[0]
-            if isinstance(item, list):  # Nested list case
-                return item[0]["label"]
-            return item["label"]
-        return "neutral"
-    except Exception as e:
-        logging.warning(f"Emotion detection failed: {e}")
-        return "neutral"
-
+    result = emotion_model(text)
+    if isinstance(result, list) and len(result) > 0:
+        return result[0]["label"]
+    return "neutral"
+    
 # === Follow-up Q&A ===
 def answer_followup(text, question, verbosity="brief"):
     try: