Update app.py

app.py

@@ -98,6 +98,24 @@ 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())
 
+import tempfile
+from fpdf import FPDF
+
+# 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
+
 # SQL-RAG Analysis
 if st.session_state.df is not None:
     temp_dir = tempfile.TemporaryDirectory()
@@ -171,21 +189,20 @@ 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],
     )
 
-    # Separate Crews for report and conclusion
+    # Crews for report and conclusion
     crew_report = Crew(
         agents=[sql_dev, data_analyst, report_writer],
         tasks=[extract_data, analyze_data, write_report],
@@ -208,43 +225,33 @@ 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..."):
-                # 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 = []
+                if report_result:
+                    tab1_txt = save_as_txt(report_result, "Tab1_Report.txt")
+                    tab1_pdf = save_as_pdf(report_result, "Tab1_Report.pdf")
+                    st.download_button("Download Tab 1 Report as TXT", open(tab1_txt, "rb"), file_name="Tab1_Report.txt")
+                    st.download_button("Download Tab 1 Report as PDF", open(tab1_pdf, "rb"), file_name="Tab1_Report.pdf")
 
-                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)
+                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)
+                st.caption("📊 Salary distribution across different job titles.")
 
-                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_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)
+                st.caption("📊 Average salary based on experience level.")
 
-                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_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)
+                st.caption("📊 Salary distribution across employment types.")
 
-                # Step 5: Insert Visual Insights
-                st.markdown("#### 5. Visual Insights")
-                for fig in visualizations:
-                    st.plotly_chart(fig, use_container_width=True)
-
-                # Step 6: Display Concise Conclusion
-                #st.markdown("#### 6. Conclusion")
                 st.markdown(conclusion_result if conclusion_result else "⚠️ No Conclusion Generated.")
 
     # Full Data Visualization Tab
@@ -253,23 +260,30 @@ if st.session_state.df is not None:
 
         fig1 = px.histogram(st.session_state.df, x="job_title", title="Job Title Frequency")
         st.plotly_chart(fig1)
+        st.caption("📊 Frequency of each job title in the dataset.")
 
-        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"
-        )
+        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)
+        st.caption("📊 Average salary for each experience level.")
 
-        fig3 = px.box(st.session_state.df, x="employment_type", y="salary_in_usd",
-                      title="Salary Distribution by Employment Type")
+        fig3 = px.box(st.session_state.df, x="employment_type", y="salary_in_usd", title="Salary Distribution by Employment Type")
         st.plotly_chart(fig3)
+        st.caption("📊 Salary distribution for each employment type.")
+
+        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")
 
     temp_dir.cleanup()
 else:
     st.info("Please load a dataset to proceed.")
-
-
 # Sidebar Reference
 with st.sidebar:
     st.header("📚 Reference:")