Update app.py

app.py

@@ -9,12 +9,16 @@ from io import BytesIO
 
 # App Config
 st.set_page_config(
-    page_title="FactoryGPT 5.0 – Technical Role-Based Maintenance Assistant",
+    page_title="FactoryGPT 5.0 – Maintenance Dashboard",
     page_icon="🧠",
     layout="wide"
 )
 
-# Styling
+# Load NLP + Anomaly Models
+EMBED_MODEL = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+GEN_MODEL = pipeline('text2text-generation', model='google/flan-t5-base')
+
+# Custom Style
 st.markdown("""
     <style>
     html, body, [class*="css"] {
@@ -22,14 +26,18 @@ st.markdown("""
         background-color: #0f1117;
         color: #f0f0f0;
     }
-    .stTextInput>div>div>input,
-    .stSelectbox>div>div>div>div,
-    .stFileUploader>div>div {
+    .card {
         background-color: #1a1c23;
-        color: #fff;
+        padding: 1rem;
+        border-radius: 10px;
+        margin-bottom: 1rem;
+        box-shadow: 0 0 8px rgba(88,166,255,0.2);
     }
-    .stDataFrame .blank {
-        background-color: #0f1117 !important;
+    .metric-box {
+        background-color: #1f2937;
+        padding: 0.75rem;
+        border-radius: 8px;
+        margin-top: 0.5rem;
     }
     </style>
 """, unsafe_allow_html=True)
@@ -37,78 +45,82 @@ st.markdown("""
 # Header
 st.markdown("""
     <div style='text-align: center;'>
-        <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>
+        <h1 style='color: #58a6ff;'>🏭 FactoryGPT 5.0 – Technical Maintenance Dashboard</h1>
+        <p style='color: #bbb;'>Anomaly Monitoring • Parameter Trends • Role-Based Intelligence</p>
         <hr style='border-top: 2px solid #888;'>
     </div>
 """, unsafe_allow_html=True)
 
-# Load NLP Models
-EMBED_MODEL = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
-GEN_MODEL = pipeline('text2text-generation', model='google/flan-t5-base')
-
-# File Upload
+# Upload CSV
 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 successfully loaded.")
-
-    st.markdown("### 📊 Sensor Data Snapshot")
-    st.dataframe(df.head(), use_container_width=True)
 
-    # Run Vector Chunking
-    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()]
-
-    if 'chunks' not in st.session_state or 'embeddings' not in st.session_state:
-        chunks = convert_to_chunks(df)
-        embeddings = EMBED_MODEL.encode(chunks)
-        st.session_state.chunks = chunks
-        st.session_state.embeddings = embeddings
-
-    # Detect Anomalies
+    # Run Anomaly Detection
     iso = IsolationForest(contamination=0.02)
     labels = iso.fit_predict(df[numeric_cols])
     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.markdown("### 🔎 Machine Health Assessment")
-    st.dataframe(df[['status', 'maintenance_flag'] + numeric_cols].head(), use_container_width=True)
-
-    # Health Overview Chart
-    st.markdown("### 📈 Machine Health Summary")
-    status_counts = df['status'].value_counts()
-    fig1, ax1 = plt.subplots()
-    ax1.bar(status_counts.index, status_counts.values, color=["red", "green"])
-    ax1.set_title("Machine Health Status")
-    ax1.set_ylabel("Occurrences")
-    ax1.set_facecolor("#0f1117")
-    ax1.tick_params(colors='white')
-    ax1.title.set_color('white')
-    ax1.yaxis.label.set_color('white')
-    for spine in ax1.spines.values():
-        spine.set_edgecolor('white')
-    st.pyplot(fig1)
+    # NLP Embeddings for RAG
+    if 'chunks' not in st.session_state or 'embeddings' not in st.session_state:
+        chunks = [
+            f"[Entry {i}] " + ", ".join([f"{col}: {row[col]:.2f}" for col in numeric_cols])
+            for i, row in df.iterrows()
+        ]
+        embeddings = EMBED_MODEL.encode(chunks)
+        st.session_state.chunks = chunks
+        st.session_state.embeddings = embeddings
 
-    # Parameter Trend Chart
-    st.markdown("### 📉 Sensor Parameter Trend")
-    time_col = st.selectbox("🕒 Select Time Column (optional)", ["None"] + list(df.columns))
-    param = st.selectbox("📌 Choose a Parameter to Visualize", numeric_cols)
+    # Dashboard Layout
+    col1, col2 = st.columns(2)
+
+    with col1:
+        st.markdown("### 🧠 Machine Health Summary")
+        status_counts = df['status'].value_counts()
+        fig1, ax1 = plt.subplots()
+        ax1.bar(status_counts.index, status_counts.values, color=["red", "green"])
+        ax1.set_title("Health Status Count")
+        ax1.set_ylabel("Instances")
+        ax1.set_facecolor("#0f1117")
+        ax1.tick_params(colors='white')
+        ax1.title.set_color('white')
+        ax1.yaxis.label.set_color('white')
+        for spine in ax1.spines.values():
+            spine.set_edgecolor('white')
+        st.pyplot(fig1)
+
+    with col2:
+        st.markdown("### 🧪 Parameters Monitored")
+        st.markdown(f"""
+            <div class="card">
+                <div style='line-height: 1.8;'>{' • '.join(numeric_cols)}</div>
+            </div>
+        """, unsafe_allow_html=True)
+
+    st.markdown("### 📉 Sensor Trend (with Fault Overlay)")
+    col3, col4 = st.columns(2)
+    time_col = col3.selectbox("🕒 Time Column", ["None"] + list(df.columns))
+    trend_param = col4.selectbox("📌 Select Parameter", numeric_cols)
 
     if time_col != "None":
         df = df.sort_values(by=time_col)
 
-    fig2, ax2 = plt.subplots()
     x_vals = df[time_col] if time_col != "None" else df.index
-    ax2.plot(x_vals, df[param], label=param, color="skyblue")
-    anomaly_x = x_vals[df['status'] == '❌ Fault Detected']
-    anomaly_y = df[param][df['status'] == '❌ Fault Detected']
-    ax2.scatter(anomaly_x, anomaly_y, color='red', label='Fault Detected', zorder=5)
-    ax2.set_title(f"{param} Over Time")
+    y_vals = df[trend_param]
+
+    fig2, ax2 = plt.subplots()
+    ax2.plot(x_vals, y_vals, label=trend_param, color="skyblue")
+    ax2.scatter(
+        x_vals[df['status'] == '❌ Fault Detected'],
+        y_vals[df['status'] == '❌ Fault Detected'],
+        color='red', label='Fault Detected', zorder=5
+    )
+    ax2.set_title(f"{trend_param} Trend")
     ax2.set_xlabel("Time" if time_col != "None" else "Index")
-    ax2.set_ylabel(param)
+    ax2.set_ylabel(trend_param)
     ax2.legend()
     ax2.set_facecolor("#0f1117")
     ax2.tick_params(colors='white')
@@ -119,62 +131,45 @@ if uploaded_file:
         spine.set_edgecolor('white')
     st.pyplot(fig2)
 
-    # Parameter List
-    st.markdown("### 🧪 Parameters Monitored")
-    st.markdown(", ".join(numeric_cols))
-
-    # Export Anomalies
-    st.markdown("### 📤 Export Flagged Anomalies")
+    # Export Fault Records
+    st.markdown("### 📤 Export Anomalies")
     anomalies_df = df[df['status'] == '❌ Fault Detected']
     buffer = BytesIO()
     anomalies_df.to_csv(buffer, index=False)
     st.download_button(
-        label="⬇️ Download Fault Records",
+        label="⬇️ Download Fault Log",
         data=buffer.getvalue(),
-        file_name="fault_records.csv",
+        file_name="fault_anomalies.csv",
         mime="text/csv"
     )
 
-    # Fault Correlation if Metadata Exists
+    # Fault Correlation
     st.markdown("### 🏷️ Fault Distribution by Machine/Component")
     metadata_cols = [col for col in df.columns if 'machine' in col.lower() or 'component' in col.lower()]
-    for col in metadata_cols:
-        st.markdown(f"**{col.capitalize()} – Fault Frequency**")
-        fault_counts = df[df['status'] == '❌ Fault Detected'][col].value_counts()
-        st.bar_chart(fault_counts)
+    for meta in metadata_cols:
+        st.markdown(f"**{meta} – Fault Frequency**")
+        meta_counts = df[df['status'] == '❌ Fault Detected'][meta].value_counts()
+        st.bar_chart(meta_counts)
 
-    # Role-based Technical Assistant
+    # Role Assistant
     st.markdown("### 💬 Technical Assistant by Role")
     roles = {
         "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."
-            )
+            "description": "Focus on equipment behavior. Spot abnormal patterns and guide simple actions.",
+            "style": "Explain simply. Emphasize safety and when to alert maintenance."
         },
         "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."
-            )
+            "description": "Diagnose machine issues. Recommend parts to inspect or replace.",
+            "style": "Use technical language. Mention symptoms and sensor causes."
         },
         "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."
-            )
+            "description": "Analyze system behavior. Identify root causes or instability.",
+            "style": "Use RCA format. Discuss fault thresholds, control issues, and next steps."
         }
     }
 
     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 a question about equipment behavior")
+    user_input = st.text_input("🧠 Ask a question")
 
     if user_input:
         query_vec = EMBED_MODEL.encode([user_input])[0]
@@ -182,22 +177,16 @@ if uploaded_file:
         top_idxs = np.argsort(sims)[-5:][::-1]
         context = "\n".join([st.session_state.chunks[i] for i in top_idxs])
 
-        # Prompt Assembly
-        system_instruction = (
+        prompt = (
             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"QUESTION:\n{user_input}\n\n"
-            f"ANSWER AS {role.upper()}:\n"
+            f"ANSWER:\n"
         )
-        response = GEN_MODEL(system_instruction, max_length=400)[0]['generated_text']
-
-        st.session_state.chat_history.append((f"👤 {role}", user_input))
-        st.session_state.chat_history.append(("🤖 FactoryGPT", response))
-
-    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)
+        result = GEN_MODEL(prompt, max_length=400)[0]['generated_text']
+        st.markdown(f"**🤖 Response:**\n\n{result}")
 
 else:
-    st.info("👈 Upload a CSV sensor log to begin.")
+    st.info("👈 Upload a sensor CSV file to generate your technical dashboard.")