Update app.py

app.py

@@ -106,11 +106,19 @@ def generate_pdf(text):
     pdf = FPDF()
     pdf.add_page()
     pdf.set_auto_page_break(auto=True, margin=15)
-    pdf.set_font("Arial", size=12)
-    for line in text.split('\n'):
-        pdf.multi_cell(0, 10, line)
-    pdf_output = BytesIO()
-    pdf.output(pdf_output)
+    lines = text.split('\n')
+    for line in lines:
+        if line.startswith("# "):
+            pdf.set_font("Arial", style="B", size=16)
+            pdf.multi_cell(0, 10, line[2:])
+        elif line.startswith("## "):
+            pdf.set_font("Arial", style="B", size=14)
+            pdf.multi_cell(0, 10, line[3:])
+        else:
+            pdf.set_font("Arial", size=12)
+            pdf.multi_cell(0, 8, line)
+    pdf_bytes = pdf.output(dest='S').encode('latin-1')
+    pdf_output = BytesIO(pdf_bytes)
     pdf_output.seek(0)
     return pdf_output
 
@@ -132,138 +140,3 @@ def download_image_as_bytes(url):
     if response.status_code == 200:
         return BytesIO(response.content)
     return None
-
-# --- Streamlit UI ---
-st.set_page_config("Deep Research Bot", layout="wide")
-
-with st.sidebar:
-    st.title("Deep Research Assistant")
-    topic = st.text_input("Topic to research")
-    report_type = st.selectbox("Type of report", [
-        "Summary - Short and fast (~2 min)",
-        "Detailed Report (~5 min)",
-        "Thorough Academic Research (~10 min)"
-    ])
-    tone = st.selectbox("Tone of the report", [
-        "Objective - Impartial and unbiased presentation of facts and findings",
-        "Persuasive - Advocating a specific point of view",
-        "Narrative - Storytelling tone for layperson readers"
-    ])
-    source_type = st.selectbox("Sources to include", ["Web Only", "Academic Only", "Hybrid"])
-    custom_domains = st.text_input("Query Domains (Optional)", placeholder="techcrunch.com, forbes.com")
-    research_button = st.button("Research")
-
-st.title("Research Output")
-
-if research_button and topic:
-    try:
-        with st.status("Gathering data..."):
-            st.info("Fetching from sources...")
-
-            all_sources = []
-            citations = []
-
-            if source_type in ["Web Only", "Hybrid"]:
-                web_data = get_sources(topic, custom_domains)
-                for item in web_data:
-                    all_sources.append(item | {"source": "web"})
-
-            if source_type in ["Academic Only", "Hybrid"]:
-                arxiv_data = get_arxiv_papers(topic)
-                for item in arxiv_data:
-                    all_sources.append(item | {"source": "arxiv"})
-                semantic_data = get_semantic_papers(topic)
-                for item in semantic_data:
-                    all_sources.append(item | {"source": "semantic"})
-
-            merged = merge_duplicates(all_sources)
-            combined_text = ""
-            for m in merged:
-                combined_text += f"- [{m['title']}]({m['url']})\n> {m.get('snippet', m.get('summary', ''))[:300]}...\n\n"
-                citations.append(generate_apa_citation(m['title'], m['url'], m['source']))
-
-        with st.spinner("Synthesizing report..."):
-            if "Summary" in report_type:
-                prompt = f"""
-# Topic Overview: {topic}
-Tone: {tone}
-Sources:
-{combined_text}
-Write a brief summary that introduces the topic, key findings, and general importance. Use markdown.
-                """
-            elif "Detailed Report" in report_type:
-                prompt = f"""
-# Research Topic: {topic}
-Tone: {tone}
-Sources:
-{combined_text}
-Write a structured report in markdown including:
-1. Introduction
-2. Research Gap
-3. Novel Insight
-4. Path Forward to Bridge the Research Gap
-5. Citations
-                """
-            else:
-                prompt = f"""
-# Thorough Academic Research Paper
-Topic: {topic}
-Tone: {tone}
-Sources:
-{combined_text}
-Write a detailed research paper in academic markdown with these sections:
-1. Abstract
-2. Introduction
-3. Literature Review
-4. Research Gap
-5. Proposed Methodology or Novel Insight
-6. Applications and Implications
-7. Conclusion
-8. References in APA format
-Also, suggest 1-2 relevant open-license images and include their links.
-                """
-
-            final_output = call_llm([{"role": "user", "content": prompt}])
-
-        st.markdown(f"### {report_type}")
-        st.markdown(final_output, unsafe_allow_html=True)
-
-        with st.spinner("Preparing PDF and LaTeX..."):
-            pdf_file = generate_pdf(final_output)
-            latex_file = generate_latex(final_output)
-            st.markdown(generate_download_button(pdf_file, "Research_Report.pdf", "application/pdf"), unsafe_allow_html=True)
-            st.markdown(generate_download_button(latex_file, "Research_Report.tex", "application/x-latex"), unsafe_allow_html=True)
-
-        st.markdown("### Citations (APA Format)")
-        for cite in citations:
-            st.markdown(f"- {cite}")
-
-        st.markdown("### Topic-Related Images")
-        images = get_images(topic)
-        if images:
-            cols = st.columns(len(images))
-            for i, img in enumerate(images):
-                with cols[i]:
-                    try:
-                        image_bytes = requests.get(img["url"]).content
-                        st.image(image_bytes, caption=img.get("title", "Related Image"), use_column_width=True)
-                        image_data = download_image_as_bytes(img["url"])
-                        if image_data:
-                            b64_img = base64.b64encode(image_data.read()).decode()
-                            href = f'<a href="data:image/jpeg;base64,{b64_img}" download="image_{i+1}.jpg">Download</a>'
-                            st.markdown(href, unsafe_allow_html=True)
-                    except Exception as e:
-                        st.warning(f"Could not load image: {e}")
-        else:
-            st.info("No related images found.")
-
-        overlaps = check_plagiarism(final_output, topic)
-        if overlaps:
-            st.warning("Potential overlaps detected:")
-            for hit in overlaps:
-                st.markdown(f"- [{hit['title']}]({hit['url']})")
-        else:
-            st.success("No major overlaps found.")
-
-    except Exception as e:
-        st.error(f"Error: {e}")