Update model.py

model.py

@@ -12,19 +12,18 @@ from nltk.tokenize import sent_tokenize
 from transformers import pipeline
 import numpy as np
 
-# Load summarizer and Q&A pipeline
-summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
+# === Load Hugging Face Pipelines ===
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
+emotion_pipeline = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=1)
 
-# --- Summarization Functions ---
+# === Summarization Functions ===
 def summarize_review(text, max_len=60, min_len=10):
-    """Standard transformer-based summarization"""
+    """Transformer-based summarization (brief)"""
     return summarizer(text, max_length=max_len, min_length=min_len, do_sample=False)[0]["summary_text"]
+
 def smart_summarize(text, n_clusters=1):
-    """
-    Clustering + cosine similarity-based summarization
-    Selects most representative sentence(s) from each cluster
-    """
+    """TF-IDF Clustering based summarization"""
     sentences = sent_tokenize(text)
     if len(sentences) <= 1:
         return text
@@ -49,7 +48,45 @@ def smart_summarize(text, n_clusters=1):
 
     return " ".join(sorted(summary_sentences, key=sentences.index))
 
-# --- Rule-based Category Detectors ---
+# === Emotion Detection ===
+def detect_emotion(text):
+    try:
+        result = emotion_pipeline(text)[0]
+        return result["label"]
+    except Exception:
+        return "unknown"
+
+# === Follow-up Q&A (single or multi) ===
+def answer_followup(text, question, verbosity="brief"):
+    try:
+        if isinstance(question, list):
+            answers = []
+            for q in question:
+                response = qa_pipeline({"question": q, "context": text})
+                answer = response.get("answer", "")
+                if verbosity.lower() == "detailed":
+                    answers.append(f"**{q}** → {answer}")
+                else:
+                    answers.append(answer)
+            return answers
+        else:
+            response = qa_pipeline({"question": question, "context": text})
+            answer = response.get("answer", "")
+            if verbosity.lower() == "detailed":
+                return f"Based on the review, the answer is: **{answer}**"
+            return answer
+    except Exception:
+        return "Sorry, I couldn't generate a follow-up answer."
+
+# === Optional Explanation Generator ===
+def generate_explanation(text):
+    try:
+        explanation = summarizer(text, max_length=60, min_length=20, do_sample=False)[0]["summary_text"]
+        return f"🧠 This review can be explained as: {explanation}"
+    except Exception:
+        return "⚠️ Explanation could not be generated."
+
+# === Industry Detector ===
 def detect_industry(text):
     text = text.lower()
     if any(k in text for k in ["doctor", "hospital", "health", "pill", "med"]):
@@ -76,6 +113,7 @@ def detect_industry(text):
         return "E-commerce"
     return "Generic"
 
+# === Product Category Detector ===
 def detect_product_category(text):
     text = text.lower()
     if any(k in text for k in ["mobile", "smartphone", "iphone", "samsung", "phone"]):
@@ -89,14 +127,3 @@ def detect_product_category(text):
     if any(k in text for k in ["app", "portal", "site", "website"]):
         return "Web App"
     return "General"
-
-# --- Follow-up Q&A ---
-def answer_followup(text, question, verbosity="brief"):
-    try:
-        response = qa_pipeline({"question": question, "context": text})
-        answer = response.get("answer", "")
-        if verbosity.lower() == "detailed":
-            return f"Based on the review, the answer is: **{answer}**"
-        return answer
-    except Exception:
-        return "Sorry, I couldn't generate a follow-up answer."