debugging for analysis tables

app.py

@@ -1,12 +1,13 @@
 import os
 import sys
 import tempfile
-import time
 import streamlit as st
 import pandas as pd
 import requests
 import openai
+import pdfkit
 
+# Add 'src' to Python path
 sys.path.append(os.path.join(os.path.dirname(__file__), 'src'))
 from main import run_pipeline
 
@@ -51,7 +52,6 @@ if submitted:
             df.to_csv(tmp_csv.name, index=False)
             csv_path = tmp_csv.name
 
-        spinner_box = st.empty()
         log_box = st.empty()
         logs = []
 
@@ -60,9 +60,8 @@ if submitted:
             log_box.code("\n".join(logs))
 
         try:
-            spinner_box.markdown("⏳ Checking API keys...")
-
-            # === Check OpenAI Key ===
+            # === Check API Keys ===
+            st.info("🔑 **Checking API Keys...**")
             try:
                 client = openai.OpenAI(api_key=openai_api_key)
                 client.models.list()
@@ -71,7 +70,6 @@ if submitted:
                 log(f"❌ OpenAI API Key Error: {e}")
                 st.stop()
 
-            # === Check Tavily Key ===
             try:
                 response = requests.post(
                     "https://api.tavily.com/search",
@@ -87,9 +85,11 @@ if submitted:
                 log(f"❌ Tavily API Key Error: {e}")
                 st.stop()
 
-            spinner_box.markdown("⏳ Running analysis pipeline...")
-            html_paths, articles_df, insights_df = run_pipeline(csv_path, tavily_api_key, progress_callback=log)
-            spinner_box.success("✅ Analysis complete!")
+            # === Run Analysis with Spinner ===
+            with st.spinner("⏳ **Analyzing topics, please wait...**"):
+                html_paths, articles_df, insights_df = run_pipeline(csv_path, tavily_api_key, progress_callback=log)
+
+            st.success("✅ Analysis complete!")
 
             # === Report Tab ===
             with tab_report:
@@ -98,6 +98,20 @@ if submitted:
                         with open(path, 'r', encoding='utf-8') as f:
                             html_content = f.read()
                             st.components.v1.html(html_content, height=600, scrolling=True)
+
+                            # Generate PDF from HTML
+                            pdf_path = path.replace(".html", ".pdf")
+                            try:
+                                pdfkit.from_string(html_content, pdf_path)
+                                with open(pdf_path, "rb") as pdf_file:
+                                    st.download_button(
+                                        label="⬇️ Download Report (PDF)",
+                                        data=pdf_file,
+                                        file_name=os.path.basename(pdf_path),
+                                        mime="application/pdf"
+                                    )
+                            except Exception as e:
+                                st.error(f"PDF generation failed: {e}")
                 else:
                     st.error("❌ No reports were generated.")
 
@@ -105,8 +119,10 @@ if submitted:
             with tab_articles:
                 st.subheader("📋 Articles Table")
                 if not articles_df.empty:
-                    st.dataframe(articles_df[["Title", "URL", "Summary", "Priority", "Sentiment", "Confidence", "Signal", "Date"]],
-                                 use_container_width=True)
+                    st.dataframe(
+                        articles_df[["Title", "URL", "Summary", "Priority", "Sentiment", "Confidence", "Signal", "Date"]],
+                        use_container_width=True
+                    )
                     st.download_button(
                         label="⬇️ Download Articles CSV",
                         data=articles_df.to_csv(index=False).encode("utf-8"),
@@ -136,17 +152,19 @@ if submitted:
                 st.code("\n".join(logs) if logs else "No logs yet.")
 
         except Exception as e:
-            spinner_box.error("❌ Failed.")
+            st.error("❌ Failed.")
             log_box.error(f"❌ Error: {e}")
 
 
 # import os
 # import sys
 # import tempfile
+# import time
 # import streamlit as st
 # import pandas as pd
+# import requests
+# import openai
 
-# # Add 'src' to Python path so we can import main.py
 # sys.path.append(os.path.join(os.path.dirname(__file__), 'src'))
 # from main import run_pipeline
 
@@ -163,7 +181,6 @@ if submitted:
 # topics_data = []
 # with st.form("topics_form"):
 #     topic_count = st.number_input("How many topics?", min_value=1, max_value=10, value=1, step=1)
-
 #     for i in range(topic_count):
 #         col1, col2 = st.columns(2)
 #         with col1:
@@ -171,20 +188,19 @@ if submitted:
 #         with col2:
 #             days = st.number_input(f"Timespan (days)", min_value=1, max_value=30, value=7, key=f"days_{i}")
 #         topics_data.append({"topic": topic, "timespan_days": days})
-
 #     submitted = st.form_submit_button("Run Analysis")
 
 # # === Tabs Setup ===
-# tab_report, tab_articles, tab_insights = st.tabs(["📝 Report", "📋 Articles", "📊 Insights"])
-# articles_df = pd.DataFrame()
-# insights_df = pd.DataFrame()
-# html_paths = []
+# tab_report, tab_articles, tab_insights, tab_debug = st.tabs(["📝 Report", "📋 Articles", "📊 Insights", "🛠 Debug"])
 
-# # === Submission logic ===
 # if submitted:
 #     if not openai_api_key or not tavily_api_key or not all([td['topic'] for td in topics_data]):
 #         st.warning("Please fill in all fields.")
 #     else:
+#         articles_df = pd.DataFrame()
+#         insights_df = pd.DataFrame()
+#         html_paths = []
+
 #         os.environ["OPENAI_API_KEY"] = openai_api_key
 #         os.environ["TAVILY_API_KEY"] = tavily_api_key
 
@@ -202,14 +218,38 @@ if submitted:
 #             log_box.code("\n".join(logs))
 
 #         try:
-#             spinner_box.markdown("⏳ Running analysis pipeline...")
+#             spinner_box.markdown("⏳ Checking API keys...")
+
+#             # === Check OpenAI Key ===
+#             try:
+#                 client = openai.OpenAI(api_key=openai_api_key)
+#                 client.models.list()
+#                 log("✅ OpenAI API key is valid.")
+#             except Exception as e:
+#                 log(f"❌ OpenAI API Key Error: {e}")
+#                 st.stop()
+
+#             # === Check Tavily Key ===
+#             try:
+#                 response = requests.post(
+#                     "https://api.tavily.com/search",
+#                     headers={"Authorization": f"Bearer {tavily_api_key}"},
+#                     json={"query": "test", "days": 1, "max_results": 1}
+#                 )
+#                 if response.status_code == 200:
+#                     log("✅ Tavily API key is valid.")
+#                 else:
+#                     log(f"❌ Tavily Key Error: {response.status_code} {response.text}")
+#                     st.stop()
+#             except Exception as e:
+#                 log(f"❌ Tavily API Key Error: {e}")
+#                 st.stop()
 
-#             # Run the full pipeline
+#             spinner_box.markdown("⏳ Running analysis pipeline...")
 #             html_paths, articles_df, insights_df = run_pipeline(csv_path, tavily_api_key, progress_callback=log)
-
 #             spinner_box.success("✅ Analysis complete!")
 
-#             # --- Report Tab ---
+#             # === Report Tab ===
 #             with tab_report:
 #                 if html_paths:
 #                     for path in html_paths:
@@ -219,20 +259,40 @@ if submitted:
 #                 else:
 #                     st.error("❌ No reports were generated.")
 
-#             # --- Articles Tab ---
+#             # === Articles Tab ===
 #             with tab_articles:
+#                 st.subheader("📋 Articles Table")
 #                 if not articles_df.empty:
-#                     st.dataframe(articles_df, use_container_width=True)
+#                     st.dataframe(articles_df[["Title", "URL", "Summary", "Priority", "Sentiment", "Confidence", "Signal", "Date"]],
+#                                  use_container_width=True)
+#                     st.download_button(
+#                         label="⬇️ Download Articles CSV",
+#                         data=articles_df.to_csv(index=False).encode("utf-8"),
+#                         file_name="articles.csv",
+#                         mime="text/csv"
+#                     )
 #                 else:
 #                     st.info("No articles available.")
 
-#             # --- Insights Tab ---
+#             # === Insights Tab ===
 #             with tab_insights:
+#                 st.subheader("📊 Top Investment Insights")
 #                 if not insights_df.empty:
 #                     st.dataframe(insights_df, use_container_width=True)
+#                     st.download_button(
+#                         label="⬇️ Download Insights CSV",
+#                         data=insights_df.to_csv(index=False).encode("utf-8"),
+#                         file_name="insights.csv",
+#                         mime="text/csv"
+#                     )
 #                 else:
 #                     st.info("No insights available.")
 
+#             # === Debug Tab ===
+#             with tab_debug:
+#                 st.subheader("🛠 Debug Log")
+#                 st.code("\n".join(logs) if logs else "No logs yet.")
+
 #         except Exception as e:
 #             spinner_box.error("❌ Failed.")
 #             log_box.error(f"❌ Error: {e}")

requirements.txt

@@ -87,3 +87,4 @@ urllib3==2.5.0
 zipp==3.23.0
 zstandard==0.23.0
 xhtml2pdf
+pdfkit