Update app.py

app.py

@@ -1,4 +1,3 @@
-
 import os
 import streamlit as st
 import asyncio
@@ -6,18 +5,20 @@ import nest_asyncio
 from gpt_researcher import GPTResearcher
 from dotenv import load_dotenv
 
+# Apply for async event loop (required for Streamlit + asyncio)
 nest_asyncio.apply()
 load_dotenv()
 
-# Inject Tavily API key
+# Set the Tavily API key (used internally by gpt-researcher)
 os.environ["TAVILY_API_KEY"] = "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"
 
+# Streamlit UI config
 st.set_page_config(page_title="🧠 Super Deep Research Agent", layout="wide")
 st.title("📚 GPT-Powered Super Deep Research Assistant")
 
-# --- Sidebar UI ---
+# Sidebar configuration
 with st.sidebar:
-    st.header("🔍 Setup Research Agent")
+    st.header("🔍 Research Configuration")
     query = st.text_input("📌 Research Topic", "Is AI a threat to creative jobs?")
     report_type = st.selectbox("📄 Report Type", ["research_report", "summary", "detailed_report"])
     tone = st.selectbox("🗣️ Tone", ["objective", "persuasive", "informative"])
@@ -25,7 +26,7 @@ with st.sidebar:
     output_format = st.selectbox("📝 Output Format", ["markdown", "text"])
     start = st.button("🚀 Start Deep Research")
 
-# Async wrapper
+# Async logic
 async def run_research_with_logs(query, report_type, source, tone, fmt, log_callback):
     agent = GPTResearcher(
         query=query,
@@ -42,34 +43,51 @@ async def run_research_with_logs(query, report_type, source, tone, fmt, log_call
     images = agent.get_research_images()
     return report, context, sources, images
 
-# --- Main Run ---
+# Main research execution
 if start and query:
-    st.info("🤖 Running super deep research...")
-
+    st.info("🤖 Running super deep research agent...")
     log_placeholder = st.empty()
-    log_text = ""
 
-    def stream_log(msg):
-        nonlocal log_text
-        log_text += f"🟢 {msg}\n"
-        log_placeholder.code(log_text, language="text")
+    # Enclosing function to use nonlocal log_text
+    def run_loggable_research():
+        log_text = ""
 
-    report, context, sources, images = asyncio.run(
-        run_research_with_logs(query, report_type, source_type, tone, output_format, log_callback=stream_log)
-    )
+        def stream_log(msg):
+            nonlocal log_text
+            log_text += f"🟢 {msg}\n"
+            log_placeholder.code(log_text, language="text")
+
+        return asyncio.run(
+            run_research_with_logs(
+                query,
+                report_type,
+                source_type,
+                tone,
+                output_format,
+                log_callback=stream_log
+            )
+        )
+
+    # Run it
+    report, context, sources, images = run_loggable_research()
 
-    st.success("✅ Report generation complete!")
+    st.success("✅ Research Complete!")
 
+    # Display report
     st.subheader("📄 Final Report")
     st.markdown(report, unsafe_allow_html=True)
 
-    st.subheader("📚 Sources")
-    for s in sources:
-        st.markdown(f"- [{s.get('title', 'Untitled')}]({s.get('url', '#')})")
+    # Display sources
+    if sources:
+        st.subheader("📚 Sources")
+        for s in sources:
+            st.markdown(f"- [{s.get('title', 'Untitled')}]({s.get('url', '#')})")
 
+    # Display images
     if images:
-        st.subheader("🖼️ Relevant Images")
+        st.subheader("🖼️ Related Images")
         for img in images:
             st.image(img, use_column_width=True)
 
+    # Download button
     st.download_button("💾 Download Report", report, file_name="deep_research.md", mime="text/markdown")