Update app.py

app.py

@@ -3,8 +3,6 @@ import pandas as pd
 import sqlite3
 import os
 import json
-import tempfile
-from fpdf import FPDF
 from pathlib import Path
 import plotly.express as px
 from datetime import datetime, timezone
@@ -80,20 +78,10 @@ elif input_option == "Upload CSV File":
         except Exception as e:
             st.error(f"Error loading file: {e}")
 
-# Helper Functions for Download
-def save_as_txt(content, filename):
-    with open(filename, "w") as f:
-        f.write(content)
-    return filename
-
-def save_as_pdf(content, filename):
-    pdf = FPDF()
-    pdf.add_page()
-    pdf.set_font("Arial", size=12)
-    for line in content.split('\n'):
-        pdf.multi_cell(0, 10, line)
-    pdf.output(filename)
-    return filename
+# Show Dataset Preview Only After Loading
+if st.session_state.df is not None and st.session_state.show_preview:
+    st.subheader("📂 Dataset Preview")
+    st.dataframe(st.session_state.df.head())
 
 # SQL-RAG Analysis
 if st.session_state.df is not None:
@@ -168,20 +156,21 @@ if st.session_state.df is not None:
     )
 
     write_report = Task(
-        description="Write the analysis report with Introduction, Key Insights, and Analysis. DO NOT include any Conclusion or Summary.",
+        description="Write the analysis report with  Introduction, Key Insights, and Analysis. DO NOT include any Conclusion or Summary.",
         expected_output="Markdown-formatted report excluding Conclusion.",
         agent=report_writer,
         context=[analyze_data],
     )
 
     write_conclusion = Task(
-        description="Write a brief and impactful 3-5 line Conclusion summarizing only the most important insights/findings. Include the max, min, and average salary and highlight the most impactful insights.",
+        description="Write a brief and impactful 3-5 line Conclusion summarizing only the most important insights/findings. Include the max, min, and average salary"
+            "and highlight the most impactful insights.",
         expected_output="Markdown-formatted Conclusion/Summary section with key insights and statistics.",
         agent=conclusion_writer,
         context=[analyze_data],
     )
 
-    # Crews for report and conclusion
+    # Separate Crews for report and conclusion
     crew_report = Crew(
         agents=[sql_dev, data_analyst, report_writer],
         tasks=[extract_data, analyze_data, write_report],
@@ -204,58 +193,71 @@ if st.session_state.df is not None:
         query = st.text_area("Enter Query:", value="Provide insights into the salary of a Principal Data Scientist.")
         if st.button("Submit Query"):
             with st.spinner("Processing query..."):
-                report_result = crew_report.kickoff(inputs={"query": query + " Provide detailed analysis but DO NOT include Conclusion."})
-                conclusion_result = crew_conclusion.kickoff(inputs={"query": query + " Provide ONLY the most important insights in 3-5 concise lines."})
+                # Step 1: Generate the analysis report
+                report_inputs = {"query": query + " Provide detailed analysis but DO NOT include Conclusion."}
+                report_result = crew_report.kickoff(inputs=report_inputs)
+
+                # Step 2: Generate only the concise conclusion
+                conclusion_inputs = {"query": query + " Provide ONLY the most important insights in 3-5 concise lines."}
+                conclusion_result = crew_conclusion.kickoff(inputs=conclusion_inputs)
+
+                # Step 3: Display the report
+                #st.markdown("### Analysis Report:")
+                st.markdown(report_result if report_result else "⚠️ No Report Generated.")
+
+                # Step 4: Generate Visualizations
+                visualizations = []
+
+                fig_salary = px.box(st.session_state.df, x="job_title", y="salary_in_usd",
+                                    title="Salary Distribution by Job Title")
+                visualizations.append(fig_salary)
 
-                st.markdown(str(report_result) if report_result else "⚠️ No Report Generated.")
+                fig_experience = px.bar(
+                    st.session_state.df.groupby("experience_level")["salary_in_usd"].mean().reset_index(),
+                    x="experience_level", y="salary_in_usd",
+                    title="Average Salary by Experience Level"
+                )
+                visualizations.append(fig_experience)
 
-                fig_salary = px.box(st.session_state.df, x="job_title", y="salary_in_usd", title="Salary Distribution by Job Title")
-                st.plotly_chart(fig_salary, use_container_width=True, key="fig_salary")
-                st.caption("📊 Salary distribution across different job titles.")
+                fig_employment = px.box(st.session_state.df, x="employment_type", y="salary_in_usd",
+                                        title="Salary Distribution by Employment Type")
+                visualizations.append(fig_employment)
 
-                fig_experience = px.bar(st.session_state.df.groupby("experience_level")["salary_in_usd"].mean().reset_index(),
-                                        x="experience_level", y="salary_in_usd", title="Average Salary by Experience Level")
-                st.plotly_chart(fig_experience, use_container_width=True, key="fig_experience")
-                st.caption("📊 Average salary by experience level.")
+                # Step 5: Insert Visual Insights
+                st.markdown("#### 5. Visual Insights")
+                for fig in visualizations:
+                    st.plotly_chart(fig, use_container_width=True)
 
-                fig_employment = px.box(st.session_state.df, x="employment_type", y="salary_in_usd", title="Salary Distribution by Employment Type")
-                st.plotly_chart(fig_employment, use_container_width=True, key="fig_employment")
-                st.caption("📊 Salary distribution across employment types.")
+                # Step 6: Display Concise Conclusion
+                #st.markdown("#### 6. Conclusion")
+                st.markdown(conclusion_result if conclusion_result else "⚠️ No Conclusion Generated.")
 
     # Full Data Visualization Tab
     with tab2:
         st.subheader("📊 Comprehensive Data Visualizations")
 
         fig1 = px.histogram(st.session_state.df, x="job_title", title="Job Title Frequency")
-        st.plotly_chart(fig1, key="fig1")
-        st.caption("📊 Frequency of each job title in the dataset.")
+        st.plotly_chart(fig1)
 
-        fig2 = px.bar(st.session_state.df.groupby("experience_level")["salary_in_usd"].mean().reset_index(),
-                      x="experience_level", y="salary_in_usd", title="Average Salary by Experience Level")
-        st.plotly_chart(fig2, key="fig2")
-        st.caption("📊 Average salary for each experience level.")
+        fig2 = px.bar(
+            st.session_state.df.groupby("experience_level")["salary_in_usd"].mean().reset_index(),
+            x="experience_level", y="salary_in_usd",
+            title="Average Salary by Experience Level"
+        )
+        st.plotly_chart(fig2)
 
-        fig3 = px.box(st.session_state.df, x="employment_type", y="salary_in_usd", title="Salary Distribution by Employment Type")
-        st.plotly_chart(fig3, key="fig3")
-        st.caption("📊 Salary distribution across employment types.")
-
-        # Restored Summary for Tab 2
-        tab2_content = "Comprehensive Data Visualizations:\n"
-        tab2_content += "- Job Title Frequency\n"
-        tab2_content += "- Average Salary by Experience Level\n"
-        tab2_content += "- Salary Distribution by Employment Type\n"
-
-        tab2_txt = save_as_txt(tab2_content, "Tab2_Visualizations.txt")
-        tab2_pdf = save_as_pdf(tab2_content, "Tab2_Visualizations.pdf")
-        st.download_button("📥 Download Tab 2 Summary as TXT", open(tab2_txt, "rb"), file_name="Tab2_Visualizations.txt")
-        st.download_button("📥 Download Tab 2 Summary as PDF", open(tab2_pdf, "rb"), file_name="Tab2_Visualizations.pdf")
+        fig3 = px.box(st.session_state.df, x="employment_type", y="salary_in_usd",
+                      title="Salary Distribution by Employment Type")
+        st.plotly_chart(fig3)
 
     temp_dir.cleanup()
 else:
     st.info("Please load a dataset to proceed.")
 
+
 # Sidebar Reference
 with st.sidebar:
     st.header("📚 Reference:")
     st.markdown("[SQL Agents w CrewAI & Llama 3 - Plaban Nayak](https://github.com/plaban1981/Agents/blob/main/SQL_Agents_with_CrewAI_and_Llama_3.ipynb)")
 
+