Update app.py

app.py

@@ -1,4 +1,4 @@
-# app.py - FactoryGPT 5.0: Predictive Maintenance with Technical Expert GPT
+# app.py - FactoryGPT 5.0: Role-Differentiated Technical Assistant
 
 import streamlit as st
 import pandas as pd
@@ -7,14 +7,14 @@ from sentence_transformers import SentenceTransformer
 from transformers import pipeline
 from sklearn.ensemble import IsolationForest
 
-# Page setup
+# App Config
 st.set_page_config(
-    page_title="FactoryGPT 5.0 – Predictive Maintenance Expert",
+    page_title="FactoryGPT 5.0 – Technical Role-Based Maintenance Assistant",
     page_icon="🧠",
     layout="wide"
 )
 
-# Dark mode CSS
+# Styling
 st.markdown("""
     <style>
     html, body, [class*="css"] {
@@ -36,28 +36,28 @@ st.markdown("""
 # Header
 st.markdown("""
     <div style='text-align: center;'>
-        <h1 style='color: #58a6ff;'>🏭 FactoryGPT 5.0 – Predictive Maintenance Assistant</h1>
-        <p style='color: #bbb;'>Sensor-Driven Diagnostics | Role-Based Expert Assistant | Industry 5.0 Ready</p>
+        <h1 style='color: #58a6ff;'>🏭 FactoryGPT 5.0 – Predictive Maintenance AI</h1>
+        <p style='color: #bbb;'>Role-Based Technical Assistant • Sensor Intelligence • Industry 5.0</p>
         <hr style='border-top: 2px solid #888;'>
     </div>
 """, unsafe_allow_html=True)
 
-# Load NLP models
+# Load NLP Models
 EMBED_MODEL = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
 GEN_MODEL = pipeline('text2text-generation', model='google/flan-t5-base')
 
-# Upload data
-uploaded_file = st.sidebar.file_uploader("📂 Upload your sensor CSV", type=["csv"])
+# File Upload
+uploaded_file = st.sidebar.file_uploader("📂 Upload sensor log (CSV)", type=["csv"])
 
 if uploaded_file:
     df = pd.read_csv(uploaded_file)
     numeric_cols = df.select_dtypes(include=np.number).columns.tolist()
-    st.success("✅ Sensor log loaded!")
+    st.success("✅ Sensor log successfully loaded.")
 
-    st.markdown("### 📊 Sensor Data Preview")
+    st.markdown("### 📊 Sensor Data Snapshot")
     st.dataframe(df.head(), use_container_width=True)
 
-    # Prepare vector chunks
+    # Vector Chunking for RAG
     def convert_to_chunks(df):
         return [f"[Entry {i}] " + ", ".join([f"{col}: {row[col]:.2f}" for col in numeric_cols]) for i, row in df.iterrows()]
 
@@ -67,61 +67,69 @@ if uploaded_file:
         st.session_state.chunks = chunks
         st.session_state.embeddings = embeddings
 
-    # Predict machine status
-    st.markdown("### 🔍 Equipment Status Prediction")
+    # Predictive Anomaly Detection
+    st.markdown("### 🔎 Machine Health Assessment")
     iso = IsolationForest(contamination=0.02)
     labels = iso.fit_predict(df[numeric_cols])
-    df['status'] = ['❌ Faulty' if x == -1 else '✅ OK' for x in labels]
-    df['maintenance_flag'] = ['🔧 Action Required' if x == -1 else '🟢 Normal' for x in labels]
+    df['status'] = ['❌ Fault Detected' if x == -1 else '✅ Healthy' for x in labels]
+    df['maintenance_flag'] = ['🔧 Inspect Required' if x == -1 else '🟢 Stable' for x in labels]
     st.dataframe(df[['status', 'maintenance_flag'] + numeric_cols].head(), use_container_width=True)
 
-    # Role-based assistant
-    st.markdown("### 💬 Role-Based Technical Assistant")
+    # Role-based Response Logic
+    st.markdown("### 💬 Technical Assistant by Role")
     roles = {
-        "Operator": (
-            "You are a senior machine operator. Based on sensor logs, identify abnormal conditions in real-time operation. "
-            "Explain deviations clearly and suggest next steps to the floor team."
-        ),
-        "Maintenance": (
-            "You are a certified maintenance technician. Analyze anomalous sensor readings, reference maintenance schedules, "
-            "and recommend immediate actions or predictive interventions with justification."
-        ),
-        "Engineer": (
-            "You are a reliability and control systems engineer. Provide a detailed root cause analysis from the sensor logs, "
-            "explain what failure modes may be emerging (e.g., torque drift, PID lag), and propose technical mitigations."
-        )
+        "Operator": {
+            "description": "Focus on simple equipment behavior. Identify unusual patterns and suggest if operator actions are needed.",
+            "style": (
+                "Explain in clear and simple terms. Focus on sensor changes, safe operation, and when to escalate to maintenance. "
+                "Avoid deep technical jargon."
+            )
+        },
+        "Maintenance": {
+            "description": "Examine possible fault conditions. Reference symptoms, parts affected, and recommend procedural maintenance actions.",
+            "style": (
+                "Give a technical breakdown of what components may be degrading. Recommend maintenance steps and cite related sensor evidence. "
+                "Use concise, technician-friendly language."
+            )
+        },
+        "Engineer": {
+            "description": "Perform data-driven diagnostics. Detect systemic issues, control instability, or potential root causes.",
+            "style": (
+                "Provide a structured root cause analysis using engineering language. Mention potential failure modes (e.g., drift, thermal loss, PID lag), "
+                "anomaly thresholds, and corrective engineering strategies."
+            )
+        }
     }
 
-    role = st.selectbox("👤 Select your role for technical insights", list(roles.keys()))
+    role = st.selectbox("👤 Select your role", roles.keys())
 
     if 'chat_history' not in st.session_state:
         st.session_state.chat_history = []
 
-    user_input = st.text_input("🧠 Ask FactoryGPT a technical question about the machine behavior")
+    user_input = st.text_input("🧠 Ask a question about equipment behavior")
 
     if user_input:
-        # Retrieve relevant context from logs
         query_vec = EMBED_MODEL.encode([user_input])[0]
         sims = np.dot(st.session_state.embeddings, query_vec)
         top_idxs = np.argsort(sims)[-5:][::-1]
         context = "\n".join([st.session_state.chunks[i] for i in top_idxs])
 
-        # Prompt Engineering
-        system_prompt = (
-            f"ROLE CONTEXT: {roles[role]}\n\n"
+        # Build Prompt
+        system_instruction = (
+            f"ROLE: {role}\n"
+            f"RESPONSIBILITIES: {roles[role]['description']}\n"
+            f"COMMUNICATION STYLE: {roles[role]['style']}\n\n"
             f"DATA CONTEXT:\n{context}\n\n"
-            f"INSTRUCTION:\nPlease respond with a technical explanation that includes sensor-based reasoning, terminology, and if possible, an action plan.\n"
+            f"QUESTION:\n{user_input}\n\n"
+            f"ANSWER AS {role.upper()}:\n"
         )
-        full_prompt = f"{system_prompt}\nUser Query: {user_input}"
-        reply = GEN_MODEL(full_prompt, max_length=350)[0]['generated_text']
+        response = GEN_MODEL(system_instruction, max_length=400)[0]['generated_text']
 
-        # Record conversation
-        st.session_state.chat_history.append((f"👤 You ({role})", user_input))
-        st.session_state.chat_history.append(("🤖 FactoryGPT", reply))
+        st.session_state.chat_history.append((f"👤 {role}", user_input))
+        st.session_state.chat_history.append(("🤖 FactoryGPT", response))
 
-    # Show chat
     for speaker, msg in st.session_state.chat_history[-10:]:
         st.markdown(f"<div style='margin-bottom: 10px;'><b>{speaker}:</b><br>{msg}</div>", unsafe_allow_html=True)
 
 else:
-    st.info("👈 Please upload a CSV file containing numeric sensor logs to begin analysis.")
+    st.info("👈 Upload a CSV sensor log to begin.")