Update app.py

app.py

@@ -1,23 +1,23 @@
 #!/usr/bin/env python3
-"""MedGenesis AI — CPU-only, dual-LLM (OpenAI / Gemini)"""
+# MedGenesis AI · CPU-only Streamlit app (OpenAI / Gemini)
 
-# ────────────── FIX: create a writable Streamlit data dir ──────────────
+# ── Streamlit telemetry dir fix ───────────────────────────────────────
 import os, pathlib
-os.environ["STREAMLIT_DATA_DIR"]                = "/tmp/.streamlit"
-os.environ["XDG_STATE_HOME"]                    = "/tmp"
+os.environ["STREAMLIT_DATA_DIR"] = "/tmp/.streamlit"
+os.environ["XDG_STATE_HOME"] = "/tmp"
 os.environ["STREAMLIT_BROWSER_GATHERUSAGESTATS"] = "false"
 pathlib.Path("/tmp/.streamlit").mkdir(parents=True, exist_ok=True)
-# ───────────────────────────────────────────────────────────────────────
 
+# ── Std-lib / third-party imports ────────────────────────────────────
 import asyncio, re
 from pathlib import Path
-
 import streamlit as st
 import pandas as pd
 import plotly.express as px
-from fpdf import FPDF
+from fpdf import FPDF          # classic FPDF → Latin-1 only
 from streamlit_agraph import agraph
 
+# ── Internal helpers ────────────────────────────────────────────────
 from mcp.orchestrator    import orchestrate_search, answer_ai_question
 from mcp.workspace       import get_workspace, save_query
 from mcp.knowledge_graph import build_agraph
@@ -27,19 +27,35 @@ from mcp.alerts          import check_alerts
 ROOT = Path(__file__).parent
 LOGO = ROOT / "assets" / "logo.png"
 
-# ──────────────── small helpers ─────────────────
+# ── PDF export helper (UTF-8 → Latin-1 “safe”) ──────────────────────
+def _latin1_safe(txt: str) -> str:
+    """Return text that FPDF(latin-1) can embed; replace unknown chars."""
+    return txt.encode("latin-1", "replace").decode("latin-1")
+
 def _pdf(papers):
-    pdf = FPDF(); pdf.add_page(); pdf.set_font("Arial", size=11)
-    pdf.cell(200, 8, "MedGenesis AI – Results", ln=True, align="C"); pdf.ln(3)
+    pdf = FPDF()
+    pdf.set_auto_page_break(auto=True, margin=15)
+    pdf.add_page()
+    pdf.set_font("Helvetica", size=11)
+    pdf.cell(200, 8, _latin1_safe("MedGenesis AI – Results"),  ln=True, align="C")
+    pdf.ln(3)
+
     for i, p in enumerate(papers, 1):
-        pdf.set_font("Arial", "B", 11)
-        pdf.multi_cell(0, 7, f"{i}. {p['title']}")
-        pdf.set_font("Arial", "", 9)
-        pdf.multi_cell(0, 6, f"{p['authors']}\n{p['summary']}\n{p['link']}\n")
+        pdf.set_font("Helvetica", "B", 11)
+        pdf.multi_cell(0, 7, _latin1_safe(f"{i}. {p['title']}"))
+        pdf.set_font("Helvetica", "", 9)
+        body = (
+            f"{p['authors']}\n"
+            f"{p['summary']}\n"
+            f"{p['link']}\n"
+        )
+        pdf.multi_cell(0, 6, _latin1_safe(body))
         pdf.ln(1)
-    return pdf.output(dest="S").encode("latin-1")
 
-def _sidebar_workspace():
+    return pdf.output(dest="S").encode("latin-1", "replace")
+
+# ── Sidebar workspace ───────────────────────────────────────────────
+def _workspace_sidebar():
     with st.sidebar:
         st.header("🗂️ Workspace")
         ws = get_workspace()
@@ -50,12 +66,12 @@ def _sidebar_workspace():
             with st.expander(f"{i}. {item['query']}"):
                 st.write(item["result"]["ai_summary"])
 
-# ──────────────── Streamlit UI ──────────────────
+# ── Main UI ─────────────────────────────────────────────────────────
 def render_ui():
     st.set_page_config("MedGenesis AI", layout="wide")
-    _sidebar_workspace()
+    _workspace_sidebar()
 
-    # header
+    # Header
     c1, c2 = st.columns([0.15, 0.85])
     with c1:
         if LOGO.exists():
@@ -64,21 +80,23 @@ def render_ui():
         st.markdown("## 🧬 **MedGenesis AI**")
         st.caption("Multi-source biomedical assistant · OpenAI / Gemini")
 
-    llm = st.radio("LLM engine", ["openai", "gemini"], horizontal=True)
+    llm   = st.radio("LLM engine", ["openai", "gemini"], horizontal=True)
     query = st.text_input("Enter biomedical question",
                           placeholder="e.g. CRISPR glioblastoma therapy")
 
-    # alert check
+    # Alert check
     if get_workspace():
         try:
             news = asyncio.run(check_alerts([w["query"] for w in get_workspace()]))
             if news:
-                st.sidebar.subheader("🔔 New papers")
-                for q, lst in news.items():
-                    st.sidebar.write(f"**{q}** – {len(lst)} new")
-        except Exception as e:
-            st.sidebar.warning(f"Alert check failed: {e}")
-
+                with st.sidebar:
+                    st.subheader("🔔 New papers")
+                    for q, lnks in news.items():
+                        st.write(f"**{q}** – {len(lnks)} new")
+        except Exception:
+            pass
+
+    # Run search
     if st.button("Run Search 🚀") and query:
         with st.spinner("Collecting literature & biomedical data …"):
             res = asyncio.run(orchestrate_search(query, llm=llm))
@@ -87,7 +105,7 @@ def render_ui():
         tabs = st.tabs(["Results", "Genes", "Trials", "Graph",
                         "Metrics", "Visuals"])
 
-        # Results -----------------------------------------------------
+        # Results
         with tabs[0]:
             for i, p in enumerate(res["papers"], 1):
                 st.markdown(f"**{i}. [{p['title']}]({p['link']})**  *{p['authors']}*")
@@ -118,7 +136,7 @@ def render_ui():
             st.subheader("AI summary")
             st.info(res["ai_summary"])
 
-        # Genes -------------------------------------------------------
+        # Genes
         with tabs[1]:
             st.header("Gene / Variant signals")
             for g in res["genes"]:
@@ -133,17 +151,17 @@ def render_ui():
                     if d:
                         st.write("-", d)
 
-        # Trials ------------------------------------------------------
+        # Trials
         with tabs[2]:
             st.header("Clinical trials")
             if not res["clinical_trials"]:
                 st.info("No trials (rate-limited or none found).")
             for t in res["clinical_trials"]:
                 st.markdown(f"**{t['NCTId'][0]}** – {t['BriefTitle'][0]}")
-                st.write(f"Phase {t.get('Phase', [''])[0]} | "
-                         f"Status {t['OverallStatus'][0]}")
+                st.write(f"Phase {t.get('Phase', [''])[0]} "
+                         f"| Status {t['OverallStatus'][0]}")
 
-        # Graph -------------------------------------------------------
+        # Graph
         with tabs[3]:
             nodes, edges, cfg = build_agraph(res["papers"],
                                              res["umls"],
@@ -155,7 +173,7 @@ def render_ui():
                     n.color = "#f1c40f" if pat.search(n.label) else "#d3d3d3"
             agraph(nodes, edges, cfg)
 
-        # Metrics -----------------------------------------------------
+        # Metrics
         with tabs[4]:
             G = build_nx([n.__dict__ for n in nodes],
                          [e.__dict__ for e in edges])
@@ -165,13 +183,14 @@ def render_ui():
                 lab = next((n.label for n in nodes if n.id == nid), nid)
                 st.write(f"- {lab}  {sc:.3f}")
 
-        # Visuals -----------------------------------------------------
+        # Visuals
         with tabs[5]:
             years = [p["published"] for p in res["papers"] if p.get("published")]
             if years:
                 st.plotly_chart(px.histogram(years, nbins=12,
                                              title="Publication Year"))
 
+        # Follow-up Q-A
         st.markdown("---")
         follow = st.text_input("Ask follow-up:")
         if st.button("Ask AI"):