Update app.py

app.py

@@ -1,74 +1,66 @@
+
 import os
 import streamlit as st
 import asyncio
 import nest_asyncio
 from gpt_researcher import GPTResearcher
+from dotenv import load_dotenv
 
-# Allow async in Streamlit (important for notebooks + event loops)
+# Allow async execution in Streamlit
 nest_asyncio.apply()
+load_dotenv()
 
-# Streamlit page config
-st.set_page_config(page_title="GPT Researcher Async UI", layout="wide")
-st.title("📘 GPT Researcher (Async Streamlit Interface)")
-
-# Sidebar Inputs
-with st.sidebar:
-    st.header("🧠 Research Agent Setup")
-    query = st.text_input("🔍 Research Topic", "Should I invest in Nvidia?")
-    report_type = st.selectbox("📄 Report Type", [
-        "research_report", "summary", "detailed_report"
-    ])
-    run_button = st.button("🚀 Run Research Agent")
+# Inject Tavily API key (used internally by gpt-researcher if configured)
+os.environ["TAVILY_API_KEY"] = "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"
 
-# Async wrapper function
-async def run_gpt_researcher(query: str, report_type: str):
-    researcher = GPTResearcher(query, report_type)
-    
-    # Phase 1: Planning + Research
-    await researcher.conduct_research()
-    
-    # Phase 2: Writing
-    report = await researcher.write_report()
+st.set_page_config(page_title="🧠 Super Deep Research Agent", layout="wide")
+st.title("📚 GPT-Powered Super Deep Research Assistant")
 
-    # Additional context
-    context = researcher.get_research_context()
-    costs = researcher.get_costs()
-    images = researcher.get_research_images()
-    sources = researcher.get_research_sources()
-
-    return report, context, costs, images, sources
+with st.sidebar:
+    st.header("🔍 Setup Research Agent")
+    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"])
+    source_type = st.selectbox("📡 Source Scope", ["web", "arxiv", "semantic-scholar", "hybrid"])
+    output_format = st.selectbox("📝 Output Format", ["markdown", "text"])
+    start = st.button("🚀 Start Deep Research")
 
-# Main Execution
-if run_button and query:
-    st.info("🤖 Autonomous agent is researching... Please wait.")
-    
-    # Run async function in Streamlit
-    report, context, costs, images, sources = asyncio.run(run_gpt_researcher(query, report_type))
+# Async wrapper
+async def run_research(query, report_type, source, tone, fmt):
+    agent = GPTResearcher(
+        query=query,
+        report_type=report_type,
+        report_source=source,
+        report_format=fmt,
+        tone=tone
+    )
+    await agent.conduct_research()
+    report = await agent.write_report()
+    context = agent.get_research_context()
+    sources = agent.get_research_sources()
+    costs = agent.get_costs()
+    images = agent.get_research_images()
+    return report, context, sources, costs, images
 
-    st.success("✅ Research completed!")
+# Run and show results
+if start and query:
+    st.info("🤖 Running super deep research...")
+    report, context, sources, costs, images = asyncio.run(run_research(query, report_type, source_type, tone, output_format))
 
-    # Show final report
+    st.success("✅ Report generation complete!")
     st.subheader("📄 Final Report")
     st.markdown(report, unsafe_allow_html=True)
 
-    # Show sources
-    if sources:
-        st.subheader("📚 Sources Used")
-        for src in sources:
-            title = src.get("title", "Untitled")
-            url = src.get("url", "#")
-            st.markdown(f"- [{title}]({url})")
+    st.subheader("📚 Sources")
+    for s in sources:
+        st.markdown(f"- [{s.get('title', 'Untitled')}]({s.get('url', '#')})")
 
-    # Show research cost
-    if costs:
-        st.subheader("💰 Cost Breakdown")
-        st.json(costs)
+    st.subheader("💰 Token Usage & Cost")
+    st.json(costs)
 
-    # Show related images
     if images:
-        st.subheader("🖼️ Related Images")
+        st.subheader("🖼️ Relevant Images")
         for img in images:
             st.image(img, use_column_width=True)
 
-    # Download button for the report
-    st.download_button("💾 Download Report", data=report, file_name="report.md", mime="text/markdown")
+    st.download_button("💾 Download Report", report, file_name="deep_research.md", mime="text/markdown")