Update app.py

app.py

@@ -2,38 +2,41 @@ import os
 import streamlit as st
 import asyncio
 import nest_asyncio
+import datetime
+import tempfile
+import base64
 from gpt_researcher import GPTResearcher
 from dotenv import load_dotenv
 
-# Enable async for Streamlit
 nest_asyncio.apply()
 load_dotenv()
 
-# Set your Tavily API key
+# Inject Tavily API key
 os.environ["TAVILY_API_KEY"] = "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"
 
-# App UI setup
 st.set_page_config(page_title="🧠 Super Deep Research Agent", layout="wide")
 st.title("📚 GPT-Powered Super Deep Research Assistant")
 
-# Sidebar UI
+# --- Sidebar UI ---
 with st.sidebar:
-    st.header("🔍 Research Setup")
+    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"])
+    source_type = st.selectbox("📡 Source Scope", ["web", "arxiv", "semantic-scholar", "hybrid"])
     output_format = st.selectbox("📝 Output Format", ["markdown", "text"])
-    start = st.button("🚀 Start Research")
+    export_format = st.selectbox("📤 Export As", ["Markdown", "LaTeX", "PDF"])
+    start = st.button("🚀 Start Deep Research")
 
-# Async agent runner
-async def run_research(query, report_type, source, tone, fmt):
+# Async wrapper
+async def run_research_with_logs(query, report_type, source, tone, fmt, log_callback):
     agent = GPTResearcher(
         query=query,
         report_type=report_type,
         report_source=source,
         report_format=fmt,
-        tone=tone
+        tone=tone,
+        log_fn=log_callback
     )
     await agent.conduct_research()
     report = await agent.write_report()
@@ -42,37 +45,67 @@ async def run_research(query, report_type, source, tone, fmt):
     images = agent.get_research_images()
     return report, context, sources, images
 
-# Run on click
+# Export Utility
+def export_file(content, export_format):
+    filename_base = f"deep_research_{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}"
+
+    if export_format == "Markdown":
+        return content, f"{filename_base}.md", "text/markdown"
+
+    elif export_format == "LaTeX":
+        latex_content = f"\\documentclass{{article}}\n\\begin{{document}}\n{content}\n\\end{{document}}"
+        return latex_content, f"{filename_base}.tex", "application/x-tex"
+
+    elif export_format == "PDF":
+        try:
+            from fpdf import FPDF
+        except ImportError:
+            st.error("Please install `fpdf` to export PDF: `pip install fpdf`")
+            return None, None, None
+
+        pdf = FPDF()
+        pdf.add_page()
+        pdf.set_auto_page_break(auto=True, margin=15)
+        pdf.set_font("Arial", size=12)
+        for line in content.split('\n'):
+            pdf.multi_cell(0, 10, line)
+        temp_path = tempfile.mktemp(suffix=".pdf")
+        pdf.output(temp_path)
+        with open(temp_path, "rb") as f:
+            return f.read(), f"{filename_base}.pdf", "application/pdf"
+
+    return None, None, None
+
+# --- Main Run ---
 if start and query:
-    st.info("⏳ Running research agent...")
+    st.info("🤖 Running super deep research...")
 
-    # Spinner with placeholder log
-    with st.spinner("Thinking..."):
-        # Optional: log collector using mutable container (if future logging is needed)
-        logs = []
+    log_placeholder = st.empty()
+    log_text = [""]  # mutable container
 
-        # Run agent
-        report, context, sources, images = asyncio.run(
-            run_research(query, report_type, source_type, tone, output_format)
-        )
+    def stream_log(msg):
+        log_text[0] += f"🟢 {msg}\n"
+        log_placeholder.code(log_text[0], language="text")
+
+    report, context, sources, images = asyncio.run(
+        run_research_with_logs(query, report_type, source_type, tone, output_format, log_callback=stream_log)
+    )
 
-    st.success("✅ Research Completed!")
+    st.success("✅ Report generation complete!")
 
-    # Display report
     st.subheader("📄 Final Report")
     st.markdown(report, unsafe_allow_html=True)
 
-    # Display sources
-    if sources:
-        st.subheader("📚 Sources")
-        for s in sources:
-            st.markdown(f"- [{s.get('title', 'Untitled')}]({s.get('url', '#')})")
+    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")
         for img in images:
             st.image(img, use_column_width=True)
 
-    # Download report
-    st.download_button("💾 Download Markdown", report, file_name="deep_research.md", mime="text/markdown")
+    # Export Section
+    file_data, filename, mime_type = export_file(report, export_format)
+    if file_data and filename:
+        st.download_button(f"💾 Download as {export_format}", data=file_data, file_name=filename, mime=mime_type)