Update app.py

app.py

@@ -1,12 +1,18 @@
 import streamlit as st
 import pandas as pd
-import os
 import numpy as np
-import google.generativeai as genai
-from datetime import datetime
+import os
 import hashlib
+import requests
+from datetime import datetime
 from PIL import Image
+from fpdf import FPDF
 import plotly.graph_objects as go
+import google.generativeai as genai
+import folium
+from streamlit_folium import st_folium
+from streamlit_geolocation import streamlit_geolocation
+from groq import Groq
 
 # --- 1. CORE SYSTEM CONFIG ---
 GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
@@ -21,35 +27,40 @@ vision_model = genai.GenerativeModel('gemini-2.0-flash')
 
 st.set_page_config(page_title="IntelliCare Portal | Hassan Naseer", layout="wide", page_icon="🏥")
 
-# --- 2. THEME ENGINE (HIGH CONTRAST) ---
+# --- 2. THEME & PDF GENERATOR ---
 if "theme" not in st.session_state: st.session_state.theme = "Light"
 
+def generate_medical_pdf(chat_history, username):
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_font("Arial", 'B', 16)
+    pdf.cell(200, 10, txt="IntelliCare Portal - Clinical Summary", ln=True, align='C')
+    pdf.set_font("Arial", size=10)
+    pdf.cell(200, 10, txt=f"Patient: {username} | Date: {datetime.now().strftime('%Y-%m-%d %H:%M')}", ln=True, align='C')
+    pdf.ln(10)
+    for msg in chat_history:
+        role = "PATIENT" if msg["role"] == "user" else "CLINICAL AI"
+        pdf.set_font("Arial", 'B', 10); pdf.cell(0, 10, txt=f"{role}:", ln=True)
+        pdf.set_font("Arial", size=10); pdf.multi_cell(0, 8, txt=msg["content"]); pdf.ln(4)
+    return pdf.output(dest='S').encode('latin-1')
+
 def inject_theme():
     bg = "#000000" if st.session_state.theme == "Dark" else "#FFFFFF"
     txt = "#FFFFFF" if st.session_state.theme == "Dark" else "#000000"
     card = "#111111" if st.session_state.theme == "Dark" else "#F0F2F6"
     brd = "#FFFFFF" if st.session_state.theme == "Dark" else "#000000"
-    
-    st.markdown(f"""
-    <style>
+    st.markdown(f"""<style>
     .stApp {{ background-color: {bg} !important; color: {txt} !important; }}
-    div[data-baseweb="input"], div[data-baseweb="textarea"], select {{
-        border: 2px solid {brd} !important; border-radius: 10px !important;
-    }}
     .chat-bubble {{ padding: 15px; border-radius: 15px; margin-bottom: 10px; border: 1px solid {brd}; }}
     .user-msg {{ background-color: rgba(59, 130, 246, 0.1); border-left: 5px solid #3b82f6; }}
     .ai-msg {{ background-color: rgba(16, 185, 129, 0.1); border-left: 5px solid #10b981; }}
     .clinical-card {{ background-color: {card}; border: 2px solid {brd}; padding: 25px; border-radius: 15px; color: {txt}; }}
-    [data-testid="stSidebar"] * {{ color: {txt} !important; }}
-    </style>
-    """, unsafe_allow_html=True)
+    </style>""", unsafe_allow_html=True)
 
 inject_theme()
 
 # --- 3. DATA PERSISTENCE ---
-USER_DB = "users_secure.csv"
-HISTORY_DB = "clinical_history.csv"
-
+USER_DB, HISTORY_DB = "users_secure.csv", "clinical_history.csv"
 def hash_pass(pwd): return hashlib.sha256(str.encode(pwd)).hexdigest()
 def load_db(file, cols):
     if os.path.exists(file): return pd.read_csv(file)
@@ -64,18 +75,17 @@ def get_vector_db():
     signal = client.get_or_create_collection(name="signals_targeted", embedding_function=emb_fn)
     return main, signal
 
-# --- 4. AUTHENTICATION GATE ---
+# --- 4. AUTHENTICATION ---
 if "logged_in" not in st.session_state: st.session_state.logged_in = False
 if "last_processed_audio" not in st.session_state: st.session_state.last_processed_audio = None
 
 if not st.session_state.logged_in:
     st.markdown("<h1 style='text-align: center;'>🏥 IntelliCare Portal</h1>", unsafe_allow_html=True)
-    c1, c2, c3 = st.columns([1, 2, 1])
+    c2 = st.columns([1, 2, 1])[1]
     with c2:
-        tab1, tab2 = st.tabs(["🔐 Login", "📝 Create Account"])
-        with tab1:
-            u = st.text_input("Username", key="l_u")
-            p = st.text_input("Password", type="password", key="l_p")
+        t1, t2 = st.tabs(["🔐 Login", "📝 Create Account"])
+        with t1:
+            u, p = st.text_input("Username", key="l_u"), st.text_input("Password", type="password", key="l_p")
             if st.button("Sign In"):
                 users = load_db(USER_DB, ["username", "password", "role"])
                 match = users[(users['username'] == u) & (users['password'] == hash_pass(p))]
@@ -83,121 +93,106 @@ if not st.session_state.logged_in:
                     st.session_state.logged_in, st.session_state.username = True, u
                     st.session_state.role, st.session_state.msgs = match.iloc[0]['role'], []
                     st.rerun()
-                else: st.error("Invalid Login")
-        with tab2:
-            nu = st.text_input("New Username", key="r_u")
-            np = st.text_input("New Password", type="password", key="r_p")
-            nr = st.selectbox("Role", ["Patient", "Doctor"], key="r_r")
+        with t2:
+            nu, np, nr = st.text_input("New User"), st.text_input("New Pass", type="password"), st.selectbox("Role", ["Patient", "Doctor"])
             if st.button("Register"):
                 df = load_db(USER_DB, ["username", "password", "role"])
-                if nu and np:
-                    if nu not in df['username'].values:
-                        pd.concat([df, pd.DataFrame([{"username": nu, "password": hash_pass(np), "role": nr}])]).to_csv(USER_DB, index=False)
-                        st.success("✅ Account Created! Now go to Login.")
-                    else: st.error("User exists.")
+                if nu not in df['username'].values:
+                    pd.concat([df, pd.DataFrame([{"username": nu, "password": hash_pass(np), "role": nr}])]).to_csv(USER_DB, index=False)
+                    st.success("✅ Registered!")
     st.stop()
 
 # --- 5. NAVIGATION ---
 with st.sidebar:
-    st.markdown(f"### 👤 {st.session_state.username} ({st.session_state.role})")
+    st.markdown(f"### 👤 {st.session_state.username}")
     if st.button("Logout"): st.session_state.logged_in = False; st.rerun()
     st.divider()
-    if st.session_state.role == "Patient":
-        nav = st.radio("Menu", ["💬 AI Chat", "🧪 Health Lab", "📍 Nearby Hospitals", "📸 Vision Scanner", "📞 Video Call", "📜 My Records"])
-    else:
-        nav = st.radio("Menu", ["🖥️ Consultation Desk", "📋 Patient Records Archive"])
-
-# --- 6. PATIENT PORTAL ---
-if st.session_state.role == "Patient":
-    if nav == "💬 AI Chat":
-        st.markdown('<div class="clinical-card"><h3>💬 Clinical AI Assistant</h3></div>', unsafe_allow_html=True)
-        for m in st.session_state.msgs:
-            bubble = "user-msg" if m["role"] == "user" else "ai-msg"
-            st.markdown(f'<div class="chat-bubble {bubble}"><b>{m["role"].upper()}:</b><br>{m["content"]}</div>', unsafe_allow_html=True)
-        
-        q = st.chat_input("Explain symptoms...")
-        c1, c2, c3 = st.columns(3)
-        with c1: v = st.audio_input("🎤 Voice", key=f"v_{len(st.session_state.msgs)}")
-        with c2: up_pdf = st.file_uploader("📄 PDF Report", type=['pdf'], key=f"p_{len(st.session_state.msgs)}")
-        with c3: up_img = st.file_uploader("📸 Image Scan", type=['png', 'jpg'], key=f"i_{len(st.session_state.msgs)}")
-        
-        final_q = q if q else None
-        if up_pdf:
-            import pdfplumber
-            with pdfplumber.open(up_pdf) as f: final_q = "PDF: " + " ".join([p.extract_text() for p in f.pages if p.extract_text()])
-        elif up_img:
-            res = vision_model.generate_content(["Extract clinical text:", Image.open(up_img)])
-            final_q = "Image Scan: " + res.text
-        elif v:
-            v_hash = hashlib.md5(v.getvalue()).hexdigest()
-            if v_hash != st.session_state.last_processed_audio:
-                from groq import Groq
-                trans = Groq(api_key=GROQ_API_KEY).audio.transcriptions.create(file=("a.wav", v.getvalue()), model="whisper-large-v3", response_format="text")
-                final_q = trans
-                st.session_state.last_processed_audio = v_hash
-
-        if final_q:
-            st.session_state.msgs.append({"role": "user", "content": final_q})
-            from groq import Groq
-            main_col, _ = get_vector_db()
-            res = main_col.query(query_texts=[final_q], n_results=1)
-            ctx = res['documents'][0][0] if (res.get('documents') and len(res['documents'][0]) > 0) else "N/A"
-            ans = Groq(api_key=GROQ_API_KEY).chat.completions.create(model="llama-3.3-70b-versatile", messages=[{"role": "system", "content": f"Context: {ctx}"}] + st.session_state.msgs)
-            st.session_state.msgs.append({"role": "assistant", "content": ans.choices[0].message.content})
-            st.rerun()
-
-    elif nav == "🧪 Health Lab":
-        st.markdown('<div class="clinical-card"><h3>🧪 Advanced Analytics</h3></div>', unsafe_allow_html=True)
-        hr = st.slider("Heart Rate (BPM)", 40, 180, 72)
-        # ECG Waveform simulation
-        t = np.linspace(0, 2, 100)
-        y = np.sin(2 * np.pi * (hr/60) * t) + 0.5 * np.sin(4 * np.pi * (hr/60) * t)
-        fig = go.Figure(data=go.Scatter(y=y, mode='lines', line=dict(color='#ff4b4b', width=3)))
-        fig.update_layout(height=250, margin=dict(l=0,r=0,t=0,b=0), paper_bgcolor='rgba(0,0,0,0)', plot_bgcolor='rgba(0,0,0,0)')
-        st.plotly_chart(fig, use_container_width=True)
-        st.metric("Pulse Status", f"{hr} BPM", delta="Normal" if 60<=hr<=100 else "Alert")
-        
-
-    elif nav == "📍 Nearby Hospitals":
-        st.markdown('<div class="clinical-card"><h3>📍 Rawalpindi Hospital Intel</h3></div>', unsafe_allow_html=True)
-        h_data = [{"Hospital": "Maryam Memorial", "Rating": "4.5", "Area": "Peshawar Rd"}, {"Hospital": "Medway Medical", "Rating": "4.6", "Area": "Satellite Town"}]
-        st.table(pd.DataFrame(h_data))
-
-    elif nav == "📞 Video Call":
-        st.markdown('<div class="clinical-card"><h3>📞 Request a Specialist</h3></div>', unsafe_allow_html=True)
-        users = load_db(USER_DB, ["username", "password", "role"])
-        docs = users[users['role'] == 'Doctor']['username'].tolist()
-        sel = st.selectbox("Search/Select Doctor", docs)
-        if st.button("Initiate Connection"):
-            room = f"IntelliCare-{st.session_state.username}-{sel}"
-            _, signal_col = get_vector_db()
-            signal_col.upsert(documents=[f"CALL|{sel}|{room}|{st.session_state.username}"], ids=["latest"])
-            st.session_state.active_room = room
-        if "active_room" in st.session_state:
-            st.components.v1.html(f'<iframe src="https://meet.jit.si/{st.session_state.active_room}" width="100%" height="550px"></iframe>', height=600)
-
-    elif nav == "📜 My Records":
-        st.table(load_db(HISTORY_DB, ["Time", "Patient", "Doctor", "Status"]))
-
-# --- 7. DOCTOR PORTAL ---
-elif st.session_state.role == "Doctor":
-    if nav == "🖥️ Consultation Desk":
-        st.markdown('<div class="clinical-card"><h3>🖥️ Consultation Desk</h3></div>', unsafe_allow_html=True)
+    nav = st.radio("Menu", ["💬 AI Chat", "🧪 Health Lab", "📍 Nearby Hospitals", "📞 Video Call", "📜 History"]) if st.session_state.role == "Patient" else st.radio("Menu", ["🖥️ Consultation Desk", "📋 Patient Records"])
+
+# --- 6. UNIFIED AI CHAT (GEMINI STYLE) ---
+if st.session_state.role == "Patient" and nav == "💬 AI Chat":
+    st.markdown('<div class="clinical-card"><h3>💬 Clinical Assistant</h3></div>', unsafe_allow_html=True)
+    for m in st.session_state.msgs:
+        bubble = "user-msg" if m["role"] == "user" else "ai-msg"
+        st.markdown(f'<div class="chat-bubble {bubble}">{m["content"]}</div>', unsafe_allow_html=True)
+
+    # UNIFIED INPUT BAR
+    st.divider()
+    input_col1, input_col2, input_col3 = st.columns([0.6, 0.6, 8])
+    with input_col1:
+        v = st.audio_input("🎤", label_visibility="collapsed", key=f"v_{len(st.session_state.msgs)}")
+    with input_col2:
+        with st.popover("➕"):
+            up_pdf = st.file_uploader("Upload PDF", type=['pdf'])
+            up_img = st.file_uploader("Scan Medicine", type=['png', 'jpg'])
+    with input_col3:
+        q = st.chat_input("Ask a medical question...")
+
+    final_q = q if q else None
+    if up_pdf:
+        import pdfplumber
+        with pdfplumber.open(up_pdf) as f: final_q = "Analyze PDF: " + " ".join([p.extract_text() for p in f.pages if p.extract_text()])
+    elif up_img:
+        res = vision_model.generate_content(["Extract medical text:", Image.open(up_img)])
+        final_q = "Image Scan: " + res.text
+    elif v:
+        v_hash = hashlib.md5(v.getvalue()).hexdigest()
+        if v_hash != st.session_state.last_processed_audio:
+            final_q = Groq(api_key=GROQ_API_KEY).audio.transcriptions.create(file=("a.wav", v.getvalue()), model="whisper-large-v3", response_format="text")
+            st.session_state.last_processed_audio = v_hash
+
+    if final_q:
+        st.session_state.msgs.append({"role": "user", "content": final_q})
+        sys_p = "You are a Clinical AI. Only answer medical questions. Politely decline others. Use provided context."
+        main_col, _ = get_vector_db()
+        res = main_col.query(query_texts=[final_q], n_results=1)
+        ctx = res['documents'][0][0] if (res.get('documents') and len(res['documents'][0]) > 0) else "N/A"
+        ans = Groq(api_key=GROQ_API_KEY).chat.completions.create(model="llama-3.3-70b-versatile", messages=[{"role": "system", "content": sys_p}, {"role": "system", "content": f"Context: {ctx}"}] + st.session_state.msgs)
+        st.session_state.msgs.append({"role": "assistant", "content": ans.choices[0].message.content})
+        st.rerun()
+
+    if st.session_state.msgs:
+        st.download_button("📥 Download PDF Summary", generate_medical_pdf(st.session_state.msgs, st.session_state.username), "Summary.pdf", "application/pdf")
+
+# --- 7. OTHER SECTIONS (LAB & MAP) ---
+elif nav == "🧪 Health Lab":
+    st.markdown('<div class="clinical-card"><h3>🧪 Clinical Diagnostics</h3></div>', unsafe_allow_html=True)
+    w, h = st.number_input("Weight (kg)", 30, 200, 70), st.number_input("Height (cm)", 100, 250, 175)
+    bmi = round(w / ((h/100)**2), 1)
+    st.plotly_chart(go.Figure(go.Indicator(mode="gauge+number", value=bmi, domain={'x': [0, 1], 'y': [0, 1]}, gauge={'axis': {'range': [10, 40]}, 'bar': {'color': "#10b981"}, 'steps': [{'range': [10, 18.5], 'color': "lightblue"}, {'range': [25, 40], 'color': "orange"}]})), use_container_width=True)
+
+elif nav == "📍 Nearby Hospitals":
+    loc = streamlit_geolocation()
+    if loc and loc.get("latitude"):
+        lat, lon = loc["latitude"], loc["longitude"]
+        query = f'[out:json];node["amenity"~"hospital|clinic"](around:5000,{lat},{lon});out body;'
+        data = requests.get("http://overpass-api.de/api/interpreter", params={'data': query}).json()
+        m = folium.Map(location=[lat, lon], zoom_start=14)
+        for e in data.get('elements', []): folium.Marker([e['lat'], e['lon']], popup=e.get('tags', {}).get('name', 'Clinic'), icon=folium.Icon(color="red")).add_to(m)
+        st_folium(m, width=1200, height=500)
+
+elif nav == "📞 Video Call":
+    docs = load_db(USER_DB, ["username", "role"])
+    sel = st.selectbox("Search Doctor", docs[docs['role'] == 'Doctor']['username'].tolist())
+    if st.button("Request Connection"):
+        room = f"IntelliCare-{st.session_state.username}-{sel}"
         _, signal_col = get_vector_db()
-        res = signal_col.get(ids=["latest"])
-        if res.get('documents'):
-            parts = res['documents'][0].split("|")
-            if parts[1] == st.session_state.username:
-                st.warning(f"🔔 {parts[3]} is requesting a call.")
-                if st.button("✅ Join Call"): st.session_state.active_call = parts[2]
-                if "active_call" in st.session_state:
-                    st.components.v1.html(f'<iframe src="https://meet.jit.si/{parts[2]}" width="100%" height="600px"></iframe>', height=650)
-                    if st.button("🔴 Archive & Log"):
-                        df = load_db(HISTORY_DB, ["Time", "Patient", "Doctor", "Status"])
-                        log = pd.DataFrame([{"Time": datetime.now().strftime("%Y-%m-%d %H:%M"), "Patient": parts[3], "Doctor": st.session_state.username, "Status": "Completed"}])
-                        pd.concat([df, log]).to_csv(HISTORY_DB, index=False)
-                        signal_col.delete(ids=["latest"]); del st.session_state.active_call; st.rerun()
-        else: st.info("Waiting for patient requests...")
-
-    elif nav == "📋 Patient Records Archive":
-        st.table(load_db(HISTORY_DB, ["Time", "Patient", "Doctor", "Status"]))
+        signal_col.upsert(documents=[f"CALL|{sel}|{room}|{st.session_state.username}"], ids=["latest"])
+        st.session_state.active_room = room
+    if "active_room" in st.session_state:
+        st.components.v1.html(f'<iframe src="https://meet.jit.si/{st.session_state.active_room}" width="100%" height="550px"></iframe>', height=600)
+
+elif nav == "🖥️ Consultation Desk":
+    _, signal_col = get_vector_db()
+    res = signal_col.get(ids=["latest"])
+    if res.get('documents'):
+        parts = res['documents'][0].split("|")
+        if parts[1] == st.session_state.username:
+            st.warning(f"🔔 {parts[3]} is requesting a call.")
+            if st.button("✅ Join"): st.session_state.active_call = parts[2]
+            if "active_call" in st.session_state:
+                st.components.v1.html(f'<iframe src="https://meet.jit.si/{parts[2]}" width="100%" height="600px"></iframe>', height=650)
+                if st.button("🔴 Archive"):
+                    df = load_db(HISTORY_DB, ["Time", "Patient", "Doctor", "Status"])
+                    pd.concat([df, pd.DataFrame([{"Time": datetime.now().strftime("%Y-%m-%d %H:%M"), "Patient": parts[3], "Doctor": st.session_state.username, "Status": "Completed"}])]).to_csv(HISTORY_DB, index=False)
+                    signal_col.delete(ids=["latest"]); del st.session_state.active_call; st.rerun()