Update app.py

app.py

@@ -1,3 +1,54 @@
+import os
+import numpy as np
+import pandas as pd
+import streamlit as st
+from transformers import (
+    pipeline,
+    AutoTokenizer,
+    AutoModelForSequenceClassification,
+    AutoModelForSeq2SeqLM
+)
+from keybert import KeyBERT
+
+# ─── Sentiment & Keyword Models ─────────────────────────────────────────────
+@st.cache_resource
+def load_sentiment_pipeline():
+    model_name = "mayf/amazon_reviews_bert_ft"
+    tok = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
+    mdl = AutoModelForSequenceClassification.from_pretrained(
+        model_name,
+        use_auth_token=True
+    )
+    return pipeline(
+        "sentiment-analysis",
+        model=mdl,
+        tokenizer=tok,
+        return_all_scores=True
+    )
+
+@st.cache_resource
+def load_keybert_model():
+    return KeyBERT(model="all-MiniLM-L6-v2")
+
+# ─── FLAN-T5 Generation Pipeline ────────────────────────────────────────────
+@st.cache_resource
+def load_flant5_pipeline():
+    seq_tok = AutoTokenizer.from_pretrained("google/flan-t5-base")
+    seq_model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
+    return pipeline(
+        "text2text-generation",
+        model=seq_model,
+        tokenizer=seq_tok,
+        max_new_tokens=300,
+        do_sample=True,
+        temperature=0.7
+    )
+
+LABEL_MAP = {
+    "LABEL_0": "Very Negative",
+    "LABEL_1": "Negative",
+    "LABEL_2": "Neutral",
+    "LABEL_3": "Positive",
     "LABEL_4": "Very Positive"
 }
 
@@ -73,7 +124,8 @@ Customer Review:
 
 Instructions: Analyze the feedback and provide three distinct, actionable improvement recommendations. For each, include a concise title and a detailed explanation in 5–7 sentences, plus a bullet list of 3–5 execution steps and a measure of impact.
 
-**Output only the recommendations as numbered items (1–3).*"""
+Output only the three numbered recommendations (1–3), each with its title, detailed explanation, steps, and impact measure.
+"""
         response = generation_pipeline(prompt)
         detailed = response[0]["generated_text"]
         st.markdown(detailed)