Update app.py

app.py

@@ -1,54 +1,3 @@
-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"
 }
 
@@ -122,18 +71,9 @@ You are a senior product quality and customer experience specialist at an e-comm
 Customer Review:
 "{review}"
 
-Please analyze this feedback and provide **three** distinct, actionable improvement recommendations designed to reduce customer pain points.
-For each recommendation, include:
-  1. **Recommendation Title**: a concise summary of the action.
-  2. The specific issue or frustration extracted from the review.
-  3. Why this action addresses the pain point and how it will improve the customer experience.
-  4. A bullet-point list of 3–5 clear steps for operations or product teams to execute.
-  5. How to measure the impact.
-
-Write each recommendation in at least 5–7 sentences, grounding every detail in the customer's own words. Avoid generic advice—focus on specifics from the 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.
 
-Recommendations:
-"""
+**Output only the recommendations as numbered items (1–3).*"""
         response = generation_pipeline(prompt)
         detailed = response[0]["generated_text"]
         st.markdown(detailed)
@@ -148,4 +88,3 @@ Recommendations:
 if __name__ == "__main__":
     main()
 
-