Update app.py

app.py

@@ -1,4 +1,4 @@
-# app.py - FactoryRAG+: Condition Monitoring with Dashboard, PDF Export, Anomaly Detection & Digital Twin
+# app.py - FactoryRAG+: Smart Chatbot with Role-Based Assistant, Dashboard, PDF, and Digital Twin
 
 import streamlit as st
 import pandas as pd
@@ -11,7 +11,6 @@ import base64
 from io import BytesIO
 from fpdf import FPDF
 
-# Streamlit config
 st.set_page_config(page_title="FactoryRAG+ - Smart Sensor Twin", layout="wide")
 st.title("🏭 FactoryRAG+: Smart Dashboard with AI Monitoring, PDF Reporting & Digital Twin")
 
@@ -62,23 +61,9 @@ if uploaded_file:
     iso = IsolationForest(contamination=0.02)
     anomaly_labels = iso.fit_predict(df[numeric_cols])
     df['anomaly'] = ['❌' if x == -1 else '' for x in anomaly_labels]
-    st.write("Anomaly Flags:")
     st.dataframe(df[df['anomaly'] == '❌'].head(5))
 
-    # --- Technical Question Answering ---
-    st.subheader("🧠 Ask Expert Questions")
-    query = st.text_input("Ask a question like 'Where is instability?' or 'Are anomalies visible?'")
-    if query:
-        query_vec = EMBED_MODEL.encode([query])[0]
-        sims = np.dot(st.session_state.embeddings, query_vec)
-        top_idxs = np.argsort(sims)[-3:][::-1]
-        context = "\n".join([st.session_state.chunks[i] for i in top_idxs])
-        prompt = f"Context:\n{context}\n\nAs a reliability engineer, answer: {query}"
-        response = GEN_MODEL(prompt, max_length=256)[0]['generated_text']
-        st.subheader("🤖 FactoryGPT Answer")
-        st.markdown(response)
-
-    # --- Digital Twin Metrics ---
+    # --- Digital Twin Summary ---
     st.subheader("🧪 Digital Twin Summary")
     twin_report = ""
     for col in selected_cols:
@@ -99,5 +84,36 @@ if uploaded_file:
     href = f'<a href="data:application/octet-stream;base64,{b64}" download="digital_twin_report.pdf">📄 Download PDF Report</a>'
     st.markdown(href, unsafe_allow_html=True)
 
+    # --- Role-based Factory Assistant ---
+    st.subheader("💬 Factory Assistant Chat")
+
+    roles = {
+        "Operator": "You are a machine operator. Provide practical insights and safety warnings.",
+        "Maintenance": "You are a maintenance technician. Suggest inspections and likely causes of sensor anomalies.",
+        "Engineer": "You are a control systems engineer. Offer analytical interpretations and system-level advice."
+    }
+
+    role = st.selectbox("👤 Choose your role: Operator, Maintenance, or Engineer", list(roles.keys()))
+
+    if 'chat_history' not in st.session_state:
+        st.session_state.chat_history = []
+
+    user_input = st.text_input("Ask FactoryGPT anything (based on uploaded sensor logs):", key="chat_input")
+
+    if user_input:
+        query_vec = EMBED_MODEL.encode([user_input])[0]
+        sims = np.dot(st.session_state.embeddings, query_vec)
+        top_idxs = np.argsort(sims)[-3:][::-1]
+        context = "\n".join([st.session_state.chunks[i] for i in top_idxs])
+        system_prompt = roles[role]
+        full_prompt = f"{system_prompt}\n\nSensor Context:\n{context}\n\nUser Question: {user_input}"
+        reply = GEN_MODEL(full_prompt, max_length=256)[0]['generated_text']
+
+        st.session_state.chat_history.append(("You", user_input))
+        st.session_state.chat_history.append((f"{role} - FactoryGPT", reply))
+
+    for speaker, msg in st.session_state.chat_history[-10:]:
+        st.markdown(f"**{speaker}:** {msg}")
+
 else:
-    st.info("👈 Upload a sensor log CSV file to explore digital twin analysis, waveform charts, anomaly detection, and PDF export.")
+    st.info("👈 Upload a sensor log CSV file to explore digital twin analysis, chatbot Q&A, waveform charts, anomaly detection, and PDF export.")