Update app.py

app.py

@@ -13,9 +13,6 @@ st.set_page_config(page_title="Smart Factory RAG Assistant", layout="wide")
 
 st.title("🏠 Industry 5.0 | Smart Factory RAG Assistant (Open Source)")
 
-# Authenticate Hugging Face if using private token
-# login(os.getenv("HUGGING_FACE_HUB_TOKEN"))  # Uncomment if token is needed
-
 # Load open-access model (Zephyr)
 @st.cache_resource(show_spinner=True)
 def load_model():
@@ -36,10 +33,12 @@ if uploaded_file:
     df = pd.read_csv(uploaded_file)
     st.success("✅ File uploaded and loaded!")
 
-    # Custom column selection for preview
-    st.subheader("📃 Data Preview")
-    selected_columns = st.multiselect("Select columns to preview", df.columns.tolist(), default=df.columns.tolist()[:5])
-    st.dataframe(df[selected_columns].head())
+    # Data Summary
+    st.subheader("📃 Data Summary")
+    st.write(f"Number of rows: {df.shape[0]}")
+    st.write(f"Number of columns: {df.shape[1]}")
+    st.write("Column types:")
+    st.dataframe(df.dtypes.astype(str).rename("Type"))
 
     # Descriptive Stats
     st.subheader("📊 Descriptive Statistics")
@@ -80,7 +79,7 @@ if uploaded_file:
     # Pairplot
     if len(numeric_columns) > 1:
         st.subheader("🔄 Pairwise Parameter Relationships")
-        sampled_df = df[numeric_columns].sample(n=200, random_state=1) if len(df) > 200 else df[numeric_columns]
+        sampled_df = df[numeric_columns].sample(n=100, random_state=1) if len(df) > 100 else df[numeric_columns]
         pair_fig = sns.pairplot(sampled_df)
         st.pyplot(pair_fig)
 
@@ -111,8 +110,8 @@ if uploaded_file:
 
     if question:
         with st.spinner("Generating insights..."):
-            summary = df.describe().to_string()
-            corr_text = corr.to_string()
+            summary = df.describe().round(2).to_string()
+            corr_text = corr.round(2).to_string()
             anomaly_count = len(anomalies)
 
             context = f"""
@@ -120,24 +119,20 @@ You are a highly skilled {role} working in a smart manufacturing facility.
 
 Here is a summary of the uploaded data:
 
-STATISTICAL SUMMARY:
+STATISTICS:
 {summary}
 
-PARAMETER CORRELATIONS:
+CORRELATIONS:
 {corr_text}
 
-ANOMALY DETECTION:
-{anomaly_count} anomalies detected using Isolation Forest method.
-
-Based on this context, answer the following question in a clear, technically accurate manner and suggest best decisions from the point of view of a {role}.
+ANOMALIES: {anomaly_count} rows flagged.
 
 QUESTION: {question}
-ANSWER:
+Provide a short, focused response in your role.
 """
             prompt = f"<s>[INST] {context} [/INST]"
-            output = nlp(prompt, max_new_tokens=512, do_sample=True, temperature=0.5)[0]['generated_text']
+            output = nlp(prompt, max_new_tokens=250, do_sample=True, temperature=0.5)[0]['generated_text']
 
-            # Clean up response
             if '[/INST]' in output:
                 answer = output.split('[/INST]')[-1].strip()
             else: