Upload 5 files

Dockerfile

@@ -1,20 +1,13 @@
-FROM python:3.13.5-slim
+FROM python:3.10-slim
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+COPY requirements.txt .
 
-COPY requirements.txt ./
-COPY src/ ./src/
+RUN pip install --no-cache-dir -r requirements.txt
 
-RUN pip3 install -r requirements.txt
+COPY . .
 
 EXPOSE 8501
 
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,240 @@
+# Paste your full Streamlit code here
+# Include:
+# - Chat UI
+# - Preset questions
+# - Filters by rating
+# - Analytics charts (Rating & Sentiment)
+# - RAG chain with Groq LLM
+# - Executive summary generation
+# - PDF and CSV download
+import streamlit as st
+import os
+import pandas as pd
+import tempfile
+
+from langchain_groq import ChatGroq
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_core.prompts import PromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+
+from reportlab.platypus import SimpleDocTemplate, Paragraph
+from reportlab.lib.styles import getSampleStyleSheet
+
+# --------------------------------------------------
+# PAGE CONFIG
+# --------------------------------------------------
+st.set_page_config(
+    page_title="E-Commerce Review Intelligence",
+    layout="wide"
+)
+
+st.title("🛍️ Customer Review Intelligence System")
+st.caption("GenAI-powered insights using RAG (Groq + FAISS)")
+
+# --------------------------------------------------
+# SIDEBAR
+# --------------------------------------------------
+st.sidebar.header("🔐 Configuration")
+groq_key = st.sidebar.text_input("Groq API Key", type="password")
+
+if not groq_key:
+    st.warning("Please enter your Groq API key")
+    st.stop()
+
+os.environ["GROQ_API_KEY"] = groq_key
+
+rating_filter = st.sidebar.selectbox(
+    "Filter by Rating",
+    ["All", "Low (1–2)", "Medium (3)", "High (4–5)"]
+)
+
+# --------------------------------------------------
+# LOAD DATA
+# --------------------------------------------------
+@st.cache_data
+def load_data():
+    df = pd.read_csv("Womens Clothing E-Commerce Reviews.csv")
+    df = df.dropna(subset=["Review Text"])
+    return df
+
+df = load_data()
+
+def map_sentiment(r):
+    if r <= 2:
+        return "Negative"
+    elif r == 3:
+        return "Neutral"
+    else:
+        return "Positive"
+
+df["Sentiment"] = df["Rating"].apply(map_sentiment)
+
+# --------------------------------------------------
+# ANALYTICS
+# --------------------------------------------------
+st.subheader("📊 Customer Sentiment Overview")
+
+col1, col2 = st.columns(2)
+with col1:
+    st.bar_chart(df["Rating"].value_counts().sort_index())
+with col2:
+    st.bar_chart(df["Sentiment"].value_counts())
+
+# --------------------------------------------------
+# LOAD VECTOR STORE
+# --------------------------------------------------
+@st.cache_resource
+def load_vectorstore():
+    embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-MiniLM-L6-v2"
+    )
+    return FAISS.load_local(
+        "vectorstore",
+        embeddings,
+        allow_dangerous_deserialization=True
+    )
+
+vectorstore = load_vectorstore()
+retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
+
+# --------------------------------------------------
+# LOAD LLM
+# --------------------------------------------------
+llm = ChatGroq(
+    model="llama-3.1-8b-instant",
+    temperature=0
+)
+
+# --------------------------------------------------
+# RAG PROMPT
+# --------------------------------------------------
+rag_prompt = PromptTemplate(
+    input_variables=["context", "question", "rating"],
+    template="""
+    You are an AI assistant for an e-commerce company.
+
+    Rating Filter: {rating}
+
+    Customer Reviews:
+    {context}
+
+    Question:
+    {question}
+
+    Provide clear, actionable business insights.
+    """
+)
+
+rag_chain = (
+    {
+        "context": retriever,
+        "question": RunnablePassthrough(),
+        "rating": RunnablePassthrough()
+    }
+    | rag_prompt
+    | llm
+)
+
+# --------------------------------------------------
+# CHAT UI
+# --------------------------------------------------
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+st.subheader("💬 Ask Questions")
+
+preset = st.selectbox(
+    "Quick Business Questions",
+    [
+        "What are the most common customer complaints?",
+        "What do customers say about sizing?",
+        "Are customers satisfied with fabric quality?",
+        "What improvements should the business prioritize?"
+    ]
+)
+
+user_input = st.chat_input("Ask your own question")
+question = user_input if user_input else preset
+
+if question:
+    st.session_state.messages.append(
+        {"role": "user", "content": question}
+    )
+
+    response = rag_chain.invoke(
+        {"question": question, "rating": rating_filter}
+    )
+
+    st.session_state.messages.append(
+        {"role": "assistant", "content": response.content}
+    )
+
+for msg in st.session_state.messages:
+    st.chat_message(msg["role"]).write(msg["content"])
+
+# --------------------------------------------------
+# EXECUTIVE SUMMARY
+# --------------------------------------------------
+st.subheader("📄 Executive Summary")
+
+exec_prompt = PromptTemplate(
+    input_variables=["reviews"],
+    template="""
+    Generate an executive summary covering:
+    - Overall sentiment
+    - Top complaints
+    - Key strengths
+    - Business recommendations
+
+    Reviews:
+    {reviews}
+    """
+)
+
+summary_text = None
+
+if st.button("Generate Executive Summary"):
+    sample_reviews = " ".join(df["Review Text"].sample(30))
+    summary_text = (exec_prompt | llm).invoke(
+        {"reviews": sample_reviews}
+    ).content
+    st.success(summary_text)
+
+# --------------------------------------------------
+# PDF EXPORT
+# --------------------------------------------------
+def generate_pdf(text):
+    styles = getSampleStyleSheet()
+    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".pdf")
+    doc = SimpleDocTemplate(temp_file.name)
+    doc.build([
+        Paragraph("<b>Executive Summary</b>", styles["Title"]),
+        Paragraph(text.replace("\n", "<br/>"), styles["Normal"])
+    ])
+    return temp_file.name
+
+if summary_text:
+    pdf_path = generate_pdf(summary_text)
+    with open(pdf_path, "rb") as f:
+        st.download_button(
+            "📥 Download Executive Summary (PDF)",
+            f,
+            file_name="executive_summary.pdf",
+            mime="application/pdf"
+        )
+
+# --------------------------------------------------
+# CSV EXPORT
+# --------------------------------------------------
+st.subheader("📥 Download Review Data")
+
+csv = df[["Review Text", "Rating", "Sentiment"]].to_csv(index=False).encode("utf-8")
+
+st.download_button(
+    "Download CSV",
+    csv,
+    "customer_reviews.csv",
+    "text/csv"
+)
+st.write("STREAMLIT APP IS RUNNING SUCCESSFULLY")

requirements.txt

@@ -1,3 +1,9 @@
-altair
+streamlit
 pandas
-streamlit
+numpy
+scikit-learn
+faiss-cpu
+langchain-community
+langchain-core
+sentence-transformers
+groq

vectorstore.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825f0377352c9618a085d7c1dc2d7437ee7d5740ad034e29acd303de4182feae
+size 36503127