app.py

import io
import os
import re
from datetime import datetime, timedelta
import numpy as np
import pandas as pd
import requests
import streamlit as st
from dotenv import load_dotenv
from fuzzywuzzy import fuzz  # Make sure fuzzywuzzy is installed (pip install fuzzywuzzy python-levenshtein)
from groq import Groq
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

# Import database functions directly here.
# These functions should NOT import anything from app.py or user_management.py
# If you don't have database.py, you'll need to create it with these functions.
# For demonstration, I'll assume they exist.
try:
    from database import get_user_history, register_user, user_exists, check_user_credentials, save_user_history
    # Assuming get_user_history, register_user, user_exists, check_user_credentials, save_user_history are in database.py
except ImportError:
    st.error("Could not import database functions. Please ensure database.py exists and contains required functions.")
    # Define dummy functions to allow the app to run without a real database.py for now
    def get_user_history(user_id):
        st.warning("Database function 'get_user_history' not implemented. History will not be persistent.")
        return []
    def register_user(user_id, full_name, dob, email, password):
        st.warning("Database function 'register_user' not implemented. User registration will not be persistent.")
        return True # Simulate success
    def user_exists(user_id):
        st.warning("Database function 'user_exists' not implemented. User existence check will not work.")
        return False # Simulate user not existing
    def check_user_credentials(user_id, password):
        st.warning("Database function 'check_user_credentials' not implemented. Login will not work.")
        return False # Simulate login failure
    def save_user_history(user_id, symptoms, predicted_diseases):
        st.warning("Database function 'save_user_history' not implemented. History saving will not be persistent.")
        pass


# Import user management functions from user_management.py
# These functions will now receive st.session_state as an argument
from user_management import render_user_management_sidebar, save_history_to_db_if_logged_in

# Import utility functions
try:
    from utils import extract_keyword  # Ensure utils.py has the extract_keyword function
except ImportError:
    st.error("Could not import utility functions. Please ensure utils.py exists and contains required functions.")
    def extract_keyword(text, keywords):
        # Dummy implementation if utils.py is missing
        for kw in keywords:
            if kw.lower() in text.lower():
                return kw
        return "Unknown"


# Load environment variables from .env.local for local development.
# On Hugging Face Spaces, st.secrets will be used.
load_dotenv(dotenv_path=".env.local")

# --- Configuration and Initial Setup (MUST BE FIRST) ---
st.set_page_config(page_title="MediBot - Health Assistant", page_icon="🏥", layout="wide")

# Initialize Groq client
groq_client = None
GROQ_AVAILABLE = False
try:
    # Prefer st.secrets for Hugging Face Spaces deployment
    GROQ_API_KEY = st.secrets.get("GROQ_API_KEY")
    if not GROQ_API_KEY:
        # Fallback to environment variable for local development if not in secrets
        GROQ_API_KEY = os.getenv("GROQ_API_KEY")
    if GROQ_API_KEY:
        groq_client = Groq(api_key=GROQ_API_KEY)
        GROQ_AVAILABLE = True
    else:
        st.error("Groq API Key not found. Groq chatbot will not be available.")
except Exception as e:
    st.error(f"Error initializing Groq client: {e}. Groq chatbot will not be available.")

# Initialize Hugging Face Inference API client details for DATEXIS/CORe-clinical-diagnosis-prediction
HF_MODEL_AVAILABLE = False
HF_API_TOKEN = None
try:
    # Assuming 'med_model' is the name of your Hugging Face API key in st.secrets
    HF_API_TOKEN = st.secrets.get("med_model")
    if not HF_API_TOKEN:
        # Fallback to environment variable for local development
        HF_API_TOKEN = os.getenv("MED_MODEL")  # Using MED_MODEL for consistency with environment variables
    if HF_API_TOKEN:
        HF_MODEL_AVAILABLE = True
    else:
        st.warning("Hugging Face 'med_model' API Key not found. Clinical diagnosis assessment will not be available.")
except Exception as e:
    st.warning(f"Error retrieving Hugging Face API key: {e}. Clinical diagnosis assessment will not be available.")

# Initialize session state variables
if "chat_history" not in st.session_state:
    st.session_state.chat_history = []
if "feedback" not in st.session_state:
    st.session_state.feedback = []
if "show_welcome" not in st.session_state:
    st.session_state.show_welcome = True
if "chat_input_value" not in st.session_state:  # To clear the text area after submission
    st.session_state.chat_input_value = ""
if "last_chat_response" not in st.session_state:  # To persist the last chat response
    st.session_state.last_chat_response = ""
if "feedback_input" not in st.session_state:  # For clearing feedback text area
    st.session_state.feedback_input = ""
# Ensure user_id is initialized for saving history
if "user_id" not in st.session_state:
    st.session_state.user_id = None
if "logged_in_user" not in st.session_state: # This will hold the user_id after successful login
    st.session_state.logged_in_user = None

# --- HARDCODED DATA LOADING FROM CSVs ---
@st.cache_data  # Cache this function to avoid reloading data on every rerun
def load_csv_data():
    try:
        # These paths assume the CSVs are directly in the same directory as app.py
        dataset_df = pd.read_csv('dataset.csv').fillna('')  # Fill NaN with empty string
        description_df = pd.read_csv('symptom_Description.csv').fillna('')
        precaution_df = pd.read_csv('symptom_precaution.csv').fillna('')
        severity_df = pd.read_csv('Symptom-severity.csv').fillna('')  # Load symptom severity

        # Prepare data for quick lookup
        # Dataset mapping diseases to their symptoms
        disease_symptoms_map = {}
        for index, row in dataset_df.iterrows():
            disease = row['Disease']
            # Get all symptoms for this disease, filtering out empty strings and 'Disease' column itself
            symptoms = [s.strip().replace('_', ' ') for s in row.values[1:] if s.strip()]
            disease_symptoms_map[disease] = symptoms

        # Disease descriptions map
        disease_description_map = {row['Disease']: row['Description'] for index, row in description_df.iterrows()}

        # Disease precautions map
        disease_precaution_map = {row['Disease']: [p.strip() for p in row.values[1:] if p.strip()] for index, row in precaution_df.iterrows()}

        # Symptom severity map
        # Ensure symptom names are consistent (e.g., lowercase and spaces instead of underscores)
        symptom_severity_map = {row['Symptom'].strip().replace('_', ' ').lower(): row['weight'] for index, row in severity_df.iterrows()}

        # Extract all unique symptoms for the multiselect
        all_unique_symptoms = sorted(list(set(symptom for symptoms_list in disease_symptoms_map.values() for symptom in symptoms_list)))
        return disease_symptoms_map, disease_description_map, disease_precaution_map, all_unique_symptoms, symptom_severity_map
    except FileNotFoundError as e:
        st.error(f"Error: Required CSV file not found. Make sure 'dataset.csv', 'symptom_Description.csv', 'symptom_precaution.csv', and 'Symptom-severity.csv' are in the correct directory. Details: {e}")
        st.stop()  # Stop the app if crucial files are missing
    except Exception as e:
        st.error(f"Error loading CSV data: {e}")
        st.stop()  # Stop the app if data loading fails

disease_symptoms_map, disease_description_map, disease_precaution_map, hardcoded_symptoms, symptom_severity_map = load_csv_data()

# --- Custom CSS for extensive UI improvements ---
st.markdown("""
    <style>
    /* Basic Page Layout & Background */
    .stApp {
        background-color: #f8f9fa; /* Very light grey */
        font-family: 'Arial', sans-serif; /* Modern sans-serif font */
        color: #343a40; /* Darker grey for primary text */
    }
    /* Main Container Styling (for sections like Home, History) */
    /* Streamlit's main content block often has a data-testid="stVerticalBlock" */
    .stApp > header, .stApp > div:first-child > div:first-child > div:first-child {
        /* This targets the container that usually holds the main content in Streamlit */
        padding: 2.5rem; /* Increased padding */
        border-radius: 12px; /* More rounded corners */
        box-shadow: 0 8px 24px rgba(0, 0, 0, 0.08); /* Stronger, softer shadow */
        margin-top: 2rem; /* Space from top elements */
        margin-bottom: 2rem;
        background-color: #ffffff; /* White background */
    }
    /* Headers */
    h1, h2, h3, h4, h5, h6 {
        color: #004d99; /* A professional darker blue */
        font-weight: 700; /* Bold headers */
        margin-top: 1.5em;
        margin-bottom: 0.8em;
    }
    h1 { font-size: 2.8em; text-align: center; color: #003366; } /* Larger, darker blue for main title */
    h2 { font-size: 2.2em; border-bottom: 2px solid #e0e7ee; padding-bottom: 0.5em; margin-bottom: 1em; } /* Subtle line under h2 */
    h3 { font-size: 1.6em; }
    /* Main Tabs Styling (Home, History, Feedback, About, Insights) */
    .stTabs [data-baseweb="tab-list"] {
        gap: 20px; /* More space between tabs */
        margin-bottom: 30px; /* More space below tabs */
        justify-content: center; /* Center the main tabs */
        flex-wrap: wrap; /* Allow tabs to wrap on smaller screens */
    }
    .stTabs [data-baseweb="tab"] {
        height: 60px; /* Taller tabs */
        padding: 15px 30px; /* More padding */
        background-color: #e9f0f6; /* Light blue-grey background for tabs */
        border-radius: 12px 12px 0 0; /* Rounded top corners */
        font-size: 1.25em; /* Larger font size */
        font-weight: 600; /* Semi-bold */
        color: #4a6a8c; /* Muted blue text color */
        border: none; /* Remove default border */
        border-bottom: 4px solid transparent; /* Thicker highlight bottom border */
        transition: all 0.3s ease-in-out; /* Smooth transitions */
        box-shadow: 0 4px 10px rgba(0, 0, 0, 0.05); /* Subtle shadow */
        outline: none !important; /* Explicitly remove outline */
        text-align: center; /* Center text within tab */
        min-width: 120px; /* Ensure a minimum width for tabs on mobile */
    }
    .stTabs [data-baseweb="tab"]:hover {
        background-color: #dbe4ee; /* Slightly darker blue-grey on hover */
        color: #004d99; /* Darker blue text on hover */
        transform: translateY(-2px); /* Slight lift effect */
        outline: none !important; /* Ensure no outline on hover either */
    }
    /* Updated styling for selected main tabs */
    .stTabs [data-baseweb="tab"][aria-selected="true"] {
        background-color: #004d99; /* Sober darker blue for selected tab */
        color: white; /* White text for selected tab */
        border-bottom: 4px solid #004d99; /* Keep the consistent bottom border */
        box-shadow: 0 -4px 15px rgba(0, 0, 0, 0.15); /* More pronounced shadow for selected */
        outline: none !important; /* Ensure no outline when selected */
    }
    /* Ensure no outline on focus for tabs */
    .stTabs [data-baseweb="tab"]:focus {
        outline: none !important;
        box-shadow: 0 0 0 0.25rem rgba(0, 123, 255, 0.25) !important; /* Subtle focus glow if needed */
    }
    /* Nested Tabs Styling (Symptom Checker, Chat with MediBot) */
    /* This targets tabs that are children of other tabs, making them smaller */
    .stTabs [data-baseweb="tab-list"]:has(.stTabs [data-baseweb="tab-list"]) [data-baseweb="tab"],
    .stTabs [data-baseweb="tab-list"] [role="tablist"] [data-baseweb="tab"] { /* More robust selector for nested tabs */
        height: 45px; /* Slightly smaller height for sub-tabs */
        padding: 10px 20px; /* Slightly smaller padding */
        font-size: 1.1em;
        background-color: #f0f5f9; /* Lighter blue-grey for sub-tabs */
        border-radius: 10px; /* Fully rounded corners for sub-tabs */
        border: 1px solid #d8e2ed;
        margin: 0 8px; /* Small margin between sub-tabs */
        box-shadow: none; /* No individual shadow for sub-tabs */
        color: #5f7a96;
        outline: none !important; /* Remove outline on focus */
        min-width: unset; /* Remove min-width for sub-tabs */
    }
    .stTabs [data-baseweb="tab-list"]:has(.stTabs [data-baseweb="tab-list"]) [data-baseweb="tab"]:hover,
    .stTabs [data-baseweb="tab-list"] [role="tablist"] [data-baseweb="tab"]:hover {
        background-color: #e3ecf5;
        color: #004d99;
        transform: none; /* No lift for sub-tabs */
        outline: none !important; /* Ensure no outline on hover either */
    }
    /* Updated styling for selected nested tabs */
    .stTabs [data-baseweb="tab-list"]:has(.stTabs [data-baseweb="tab-list"]) [aria-selected="true"],
    .stTabs [data-baseweb="tab-list"] [role="tablist"] [aria-selected="true"] {
        background-color: #0056b3; /* Slightly darker blue for selected sub-tab */
        color: white;
        border: 1px solid #0056b3;
        box-shadow: 0 2px 8px rgba(0,0,0,0.15); /* Subtle shadow for selected sub-tab */
        outline: none !important; /* Ensure no outline when selected */
    }
    /* General Button Styling */
    .stButton>button {
        background-color: #007bff; /* Primary blue button */
        color: white;
        border-radius: 10px; /* More rounded */
        padding: 12px 28px; /* More padding */
        font-weight: 600; /* Semi-bold */
        border: none;
        cursor: pointer;
        box-shadow: 0 5px 15px rgba(0,0,0,0.1); /* Softer, more diffuse shadow */
        transition: all 0.3s ease-in-out; /* Smooth transitions */
        font-size: 1.05em; /* Slightly larger text */
        outline: none; /* Remove outline on focus */
        width: auto; /* Allow buttons to size naturally, but consider max-width on mobile */
        min-width: 100px; /* Ensure minimum tappable area */
    }
    .stButton>button:hover {
        background-color: #0056b3; /* Darker blue on hover */
        box-shadow: 0 8px 20px rgba(0,0,0,0.15); /* Larger shadow on hover */
        transform: translateY(-3px); /* More pronounced lift */
        outline: none; /* Ensure no outline on hover either */
    }
    /* Full width buttons in sidebar for better mobile experience */
    .sidebar .stButton>button {
        width: 100%; /* Full width buttons in sidebar */
        margin-bottom: 10px;
    }
    /* Input Fields, Selects, etc. */
    .stTextInput>div>div>input,
    .stTextArea>div>div>textarea, /* Target textarea as well */
    .stDateInput>div>div>input,
    .stMultiSelect>div>div {
        border-radius: 10px; /* More rounded */
        border: 1px solid #ced4da; /* Light grey border */
        padding: 10px 15px; /* More padding */
        box-shadow: inset 0 1px 4px rgba(0,0,0,0.05); /* Inner shadow */
        transition: border-color 0.2s ease-in-out, box-shadow 0.2s ease-in-out;
        background-color: #fefefe; /* Slightly off-white background */
        outline: none; /* Remove default outline */
        color: #343a40; /* Explicitly set text color to dark grey */
    }
    .stTextInput>div>div>input:focus,
    .stTextArea>div>div>textarea:focus,
    .stDateInput>div>div>input:focus,
    .stMultiSelect>div>div:focus-within {
        border-color: #007bff; /* Primary blue border on focus */
        box-shadow: 0 0 0 0.25rem rgba(0,123,255,.25); /* Focus glow */
        outline: none; /* Remove default outline */
    }
    /* Specific styling for the multiselect selected items */
    .stMultiSelect div[data-baseweb="tag"] {
        background-color: #e0f2f7 !important; /* Light blue tag background */
        color: #004d99 !important; /* Dark blue tag text */
        border-radius: 5px !important;
        padding: 5px 10px !important;
        margin: 2px !important;
    }
    /* Expander (for disease info) */
    .stExpander {
        border: 1px solid #e0e7ee; /* Lighter grey border */
        border-radius: 12px; /* More rounded */
        margin-bottom: 15px; /* More space below */
        background-color: #ffffff; /* White background */
        box-shadow: 0 4px 12px rgba(0,0,0,0.05); /* Softer shadow */
        overflow: hidden; /* Ensure rounded corners clip content */
    }
    .stExpander > div > div > .streamlit-expanderHeader {
        background-color: #f0f5f9; /* Light blue header */
        padding: 15px 20px;
        font-weight: 600;
        font-size: 1.1em;
        color: #004d99;
        border-bottom: 1px solid #e0e7ee;
        outline: none !important; /* Remove outline on focus */
    }
    .stExpander > div > div > .streamlit-expanderHeader:focus {
        outline: none !important; /* Ensure no outline on focus */
        box-shadow: 0 0 0 0.2rem rgba(0, 123, 255, 0.25) !important; /* Subtle focus ring */
    }
    .stExpander > div > div > .streamlit-expanderContent {
        padding: 20px; /* Increased padding inside */
    }
    /* Sidebar Styling */
    /* Streamlit's sidebar elements are usually inside a div with role="complementary" */
    .st-emotion-cache-vk33as { /* This targets the Streamlit sidebar div with padding */
        background-color: #ffffff; /* White sidebar background */
        padding: 25px;
        border-radius: 12px;
        box-shadow: 0 8px 24px rgba(0,0,0,0.08); /* Consistent shadow */
        margin-top: 2rem;
    }
    .sidebar .stButton>button {
        width: 100%; /* Full width buttons in sidebar */
        margin-bottom: 10px;
    }
    .sidebar h2, .sidebar h3 {
        color: #004d99;
        text-align: center;
        margin-bottom: 1.5em;
    }
    .sidebar .stTextInput, .sidebar .stDateInput, .sidebar .stSelectbox {
        margin-bottom: 1em; /* Space between sidebar inputs */
    }
    /* Alerts */
    .stAlert {
        border-radius: 10px; /* Rounded corners for alerts */
        padding: 15px;
        font-size: 1.05em;
    }
    .stAlert.st-success { background-color: #d4edda; color: #155724; border-color: #c3e6cb; }
    .stAlert.st-info { background-color: #d1ecf1; color: #0c5460; border-color: #bee5eb; }
    .stAlert.st-warning { background-color: #fff3cd; color: #856404; border-color: #ffeeba; }
    .stAlert.st-error { background-color: #f8d7da; color: #721c24; border-color: #f5c6cb; }
    /* Spinners */
    .stSpinner { color: #007bff; } /* Spinner color matching primary button */
    /* Disclaimer Box - using a more reliable target */
    div[data-testid="stVerticalBlock"] > div:first-child > div:has(p > strong:contains("Disclaimer")) {
        background-color: #fff8e1; /* Light yellow for warnings/disclaimers */
        border: 1px solid #ffeeba;
        padding: 1.5rem;
        border-radius: 10px;
        margin-bottom: 2rem;
        color: #856404;
        box-shadow: 0 2px 8px rgba(0,0,0,0.05);
    }
    /* This targets the specific disclaimer block by looking for its content */
    .stAlert[data-testid="stAlert"] p strong:contains("Important Disclaimer") {
        color: #664d03;
    }
    /* General text improvements */
    p {
        line-height: 1.7;
        margin-bottom: 1em;
    }
    ul, ol {
        margin-bottom: 1em;
        padding-left: 25px;
    }
    li {
        margin-bottom: 0.5em;
    }
    /* Increased font size for history expander titles */
    .stExpander > div > div > .streamlit-expanderHeader {
        font-size: 1.2em; /* Increased font size */
    }
    /* Media queries for specific mobile adjustments if needed (example) */
    @media (max-width: 768px) {
        h1 {
            font-size: 2.2em; /* Slightly smaller H1 on mobile */
        }
        h2 {
            font-size: 1.8em; /* Slightly smaller H2 on mobile */
        }
        .stTabs [data-baseweb="tab"] {
            font-size: 1em; /* Smaller tab font size on mobile */
            padding: 10px 15px; /* Reduced padding for tabs on mobile */
            height: auto; /* Allow height to adjust */
            min-width: unset; /* Remove min-width to allow more flexibility */
            flex: 1 1 auto; /* Allow tabs to grow and shrink more flexibly */
        }
        .stTabs [data-baseweb="tab-list"] {
            gap: 10px; /* Smaller gap between tabs on mobile */
        }
        /* Make multiselect items slightly smaller on mobile for better fit */
        .stMultiSelect div[data-baseweb="tag"] {
            font-size: 0.9em !important;
            padding: 3px 8px !important;
        }
    }
    </style>""", unsafe_allow_html=True)

# --- Groq API Response Function (updated system prompt) ---
def get_groq_response(user_query, severity_label="Undetermined Severity", model="llama-3.3-70b-versatile"):
    """
    Function to get a response from Groq API for health questions.
    Augments the system prompt with severity information if available.
    """
    if not GROQ_AVAILABLE or groq_client is None:
        return "AI assistant is not available."
    # Augment the system prompt with severity information from clinical diagnosis model
    # Note: 'severity_label' comes from the symptom checker. If asking a direct question,
    #       it might default to "Undetermined Severity" unless explicitly passed from a prior analysis.
    system_prompt = (
        "You are an experienced physician specialized in diagnosis and clinical decision-making. "
        "Your primary role is to analyze presented symptoms or health queries and provide a differential diagnosis along with evidence-based recommendations for next steps. "
        f"Based on initial analysis, the perceived severity of the user's condition is: {severity_label}. "
        "Adjust your tone and recommendations accordingly, emphasizing urgency if severity is 'High Severity'.\n\n"
        "When a user describes symptoms or asks a health question, you should:\n\n"
        "1.  **Prioritized Differential Diagnosis**: Provide a prioritized list of possible diagnoses based on the information given, indicating their relative likelihood or confidence (e.g., 'most likely', 'possible', 'less likely').\n"
        "2.  **Reasoning**: Briefly explain the clinical reasoning for each diagnosis, referencing common clinical features, pathophysiology, or typical presentations.\n"
        "3.  **Recommended Investigations**: Suggest appropriate next diagnostic tests or investigations to confirm or rule out these conditions.\n\n"
        "4.  **Initial Management/Treatment**: Propose evidence-based initial management or general treatment options (e.g., symptomatic relief, lifestyle changes, over-the-counter suggestions).\n"
        "5.  **Red Flags/Urgency**: Clearly highlight any red flags or warning signs that would require immediate emergency care or urgent specialist referral.\n\n"
        "Always maintain a professional, empathetic, and medically accurate tone. Present information clearly, using bullet points or numbered lists where appropriate. "
        "Crucially, always conclude your response by strongly advising the user to consult a qualified healthcare professional for a definitive diagnosis and personalized treatment plan, "
        "as this AI is for informational purposes only and not a substitute for professional medical advice."
    )
    try:
        chat_completion = groq_client.chat.completions.create(
            messages=[
                {"role": "system", "content": system_prompt},
                {"role": "user", "content": user_query},
            ],
            model=model,
            temperature=0.7,
            max_tokens=800,  # Increased max_tokens to allow for more detailed responses
            top_p=1,
            stop=None,
            stream=False,
        )
        return chat_completion.choices[0].message.content
    except Exception as e:
        st.error(f"Groq API call failed: {e}")
        return "Sorry, I am unable to process that request at the moment due to an AI service error."

# --- Clinical Diagnosis Model Integration (DATEXIS/CORe-clinical-diagnosis-prediction) ---
def get_diagnosis_and_severity_from_model(symptoms_text):
    """
    Function to get diagnosis predictions and infer severity from DATEXIS/CORe-clinical-diagnosis-prediction
    using Hugging Face Inference API.
    """
    if not HF_MODEL_AVAILABLE or not HF_API_TOKEN:
        st.warning("Hugging Face API key not available. Cannot assess severity.")
        return "Severity Assessment Unavailable (API Key Missing)", []
    API_URL = "https://api-inference.huggingface.co/models/DATEXIS/CORe-clinical-diagnosis-prediction"
    headers = {"Authorization": f"Bearer {HF_API_TOKEN}"}
    payload = {"inputs": symptoms_text}
    try:
        response = requests.post(API_URL, headers=headers, json=payload)
        response.raise_for_status()
        result = response.json()
        raw_predicted_diagnoses = []
        threshold = 0.5
        if result and isinstance(result, list) and len(result) > 0 and isinstance(result[0], list):
            for prediction_set in result:
                for item in prediction_set:
                    if item['score'] >= threshold:
                        raw_predicted_diagnoses.append(item['label'])

        filtered_diagnoses = []
        # EXPANDED AND REFINED GENERIC FILTER KEYWORDS
        generic_filter_keywords = [
            'unspecified', 'acute', 'chronic', 'use', 'status', 'other', 'not elsewhere classified',
            'no diagnosis', 'history of', 'finding', 'problem', 'syndrome', 'disease',
            'disorder', 'condition', 'code', 'category', 'episode', 'complication',
            'sequelae', 'factor', 'manifestation', 'procedure', 'examination', 'observation',
            'symptoms', 'sign', 'unconfirmed', 'type', 'group', 'normal', 'unknown', 'level',
            'positive', 'negative', 'patient', 'value', 'test', 'result', 'diagnosis',
            'kidney', 'stage', 'without', 'essential', 'with', 'due to', 'related to', 'of',
            'organ', 'function', 'system', 'body', 'region',
            'clinical', 'consideration', 'presence', 'absence', 'mild', 'moderate', 'severe',
            'manifesting', 'affecting', 'affect', 'area', 'part', 'general', 'specific',
            'diagnosis of', 'history of', 'finding of', 'problem of', 'type of', 'group of',
            'unlikely', 'possible', 'likely', 'primary', 'secondary', 'and', 'or', 'by', 'for', 'in', 'on',
            'symptom', 'sign', 'pain', 'fever', 'cough', 'vomiting', 'nausea', 'rash', 'headache', 'fatigue', 'diarrhea', 'sore throat', 'hemorrhage',
            # Additional common non-diagnostic terms from ICD or general medical language
            'i', 'ii', 'iii', 'iv', 'v', 'vi', 'vii', 'viii', 'ix', 'x', # Roman numerals
            'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', # Single letters
            'longterm', 'shortterm', 'controlled', 'uncontrolled', 'recurrent', 'intermittent', 'persistent',
            'follow-up', 'observation', 'screening', 'encounter', 'admission', 'discharge',
            'acute on chronic', 'other specified', 'not otherwise specified'
        ]

        for diagnosis_label in raw_predicted_diagnoses:
            lower_diag = diagnosis_label.lower().strip()
            is_generic = False

            # Rule 1: Check against expanded generic filter keywords
            for generic_kw in generic_filter_keywords:
                # Use regex for whole word matching to avoid partial matches (e.g., 'use' matching 'house')
                if re.fullmatch(r'\b' + re.escape(generic_kw) + r'\b', lower_diag):
                    is_generic = True
                    break
            if is_generic:
                continue # Skip to next diagnosis if it's a generic keyword

            # Rule 2: Filter out very short numerical or alphanumeric strings (e.g., 'ii', 'a1')
            if len(lower_diag) <= 2 and (lower_diag.replace('.', '').isdigit() or lower_diag.isalnum()):
                is_generic = True
            if is_generic:
                continue

            # Rule 3: Filter out terms that are purely numerical codes (e.g., '250.00', 'E11.9')
            # This is a heuristic, as some numbers might be part of a valid diagnosis
            if re.fullmatch(r'[\d\.]+', lower_diag) and len(lower_diag) < 7: # e.g., "250.00" or "E11.9"
                is_generic = True
            if is_generic:
                continue

            # Rule 4: Filter out terms that are single words and are very common, non-specific symptoms
            # (already covered by generic_filter_keywords, but an explicit check for robustness)
            if len(lower_diag.split()) == 1 and lower_diag in ['pain', 'fever', 'cough', 'vomiting', 'nausea', 'rash', 'headache', 'fatigue', 'diarrhea', 'sore throat', 'hemorrhage']:
                is_generic = True
            if is_generic:
                continue

            # If none of the above rules flagged it as generic, add to filtered list
            filtered_diagnoses.append(diagnosis_label)

        filtered_diagnoses = list(dict.fromkeys(filtered_diagnoses)) # Remove duplicates
        if len(filtered_diagnoses) > 5:
            filtered_diagnoses = filtered_diagnoses[:5] # Limit to top 5

        if not filtered_diagnoses:
            return "Overall Symptom Severity (AI Assessment): Undetermined Severity", []

        severity_map_keywords = {
            "High Severity": ['heart attack', 'stroke', 'failure', 'hemorrhage', 'cancer', 'acute respiratory', 'sepsis', 'cardiac arrest', 'severe', 'malignant', 'emergency', 'rupture', 'infarction', 'coma', 'shock', 'decompensation', 'crisis', 'perforation', 'ischemia', 'embolism', 'aneurysm', 'critical'],
            "Moderate Severity": ['hypertension', 'diabetes', 'pneumonia', 'infection', 'chronic', 'inflammation', 'moderate', 'insufficiency', 'fracture', 'ulcer', 'hepatitis', 'renal', 'vascular', 'disease', 'disorder', 'syndrome', 'acute', 'bronchitis', 'appendicitis', 'gallstones', 'pancreatitis', 'lupus', 'arthritis'],
            "Low Severity": ['headache', 'pain', 'mild', 'allergy', 'fever', 'cough', 'common cold', 'dermatitis', 'arthritis', 'influenza', 'viral', 'sprain', 'strain', 'gastritis', 'sore throat', 'conjunctivitis', 'sinusitis', 'bruise', 'rash', 'minor']
        }

        overall_severity = "Low Severity"
        for diagnosis_label in filtered_diagnoses:
            diag_lower = diagnosis_label.lower()
            if any(keyword in diag_lower for keyword in severity_map_keywords["High Severity"]):
                return "Overall Symptom Severity (AI Assessment): High Severity", filtered_diagnoses
            if any(keyword in diag_lower for keyword in severity_map_keywords["Moderate Severity"]):
                if overall_severity == "Low Severity":
                    overall_severity = "Moderate Severity"
                # Keep looping to see if a High Severity diagnosis is found later in the filtered list
                # Don't return here if a Moderate is found, continue to check for High
        return f"Overall Symptom Severity (AI Assessment): {overall_severity}", filtered_diagnoses
    except requests.exceptions.RequestException as e:
        st.error(f"Network or API Error during clinical diagnosis model call: {e}. Check API key and internet connection.")
        return "Severity Assessment Unavailable (Network Error)", []
    except Exception as e:
        st.error(f"Error processing clinical diagnosis model response: {e}. Unexpected data format or mapping issue.")
        return "Severity Assessment Unavailable (Processing Error)", []

# --- Functions for PDF generation (retained and adjusted for DB history) ---
def generate_pdf_report(history_data):
    buffer = io.BytesIO()
    c = canvas.Canvas(buffer, pagesize=letter)
    width, height = letter
    c.setFont("Helvetica-Bold", 16)
    c.drawString(50, height - 50, "MediBot Health Report")
    c.setFont("Helvetica", 10)
    c.drawString(50, height - 70, f"Report Generated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    y = height - 100
    for entry in history_data:
        # history_data comes as list of tuples: (history_id, symptoms, predicted_diseases, query_timestamp)
        timestamp, symptoms_text, predicted_diseases = entry[3], entry[1], entry[2]
        if y < 100:
            c.showPage()
            c.setFont("Helvetica-Bold", 16)
            c.drawString(50, height - 50, "MediBot Health Report (Continued)")
            c.setFont("Helvetica", 10)
            y = height - 100

        c.setFont("Helvetica-Bold", 10)
        c.drawString(50, y, f"Timestamp: {timestamp.strftime('%Y-%m-%d %H:%M:%S')}")
        y -= 15
        c.setFont("Helvetica", 10)
        symptoms_line = f"Symptoms/Question: {symptoms_text}"
        insight_line = f"Insight/Response: {predicted_diseases}"

        textobject = c.beginText(50, y)
        textobject.setFont("Helvetica", 10)

        # Helper to wrap text within PDF
        def draw_wrapped_text(text_obj, text, max_width):
            nonlocal y
            words = text.split(' ')
            current_line_words = []
            for word_idx, word in enumerate(words):
                temp_line = ' '.join(current_line_words + [word])
                if c.stringWidth(temp_line, "Helvetica", 10) < max_width:
                    current_line_words.append(word)
                else:
                    text_obj.textLine(' '.join(current_line_words))
                    y -= 12  # Line height
                    current_line_words = [word]
                    # Handle very long words that exceed max_width
                    if c.stringWidth(word, "Helvetica", 10) >= max_width:
                        # If a single word is too long, break it
                        chunk_size = 50  # Arbitrary chunk size for breaking long words
                        for i in range(0, len(word), chunk_size):
                            text_obj.textLine(word[i:i + chunk_size])
                            y -= 12
                        current_line_words = []  # Reset after a long word is broken
                        continue
            if current_line_words:  # Draw any remaining words
                text_obj.textLine(' '.join(current_line_words))
                y -= 12  # Line height

        draw_wrapped_text(textobject, symptoms_line, width - 100)
        draw_wrapped_text(textobject, insight_line, width - 100)
        c.drawText(textobject)
        y -= 20
    c.save()
    buffer.seek(0)
    return buffer

# --- Symptom Checker Logic (Now using hardcoded data and severity) ---
def get_disease_info_from_csv(selected_symptoms: list, disease_symptoms_map, disease_description_map, disease_precaution_map, symptom_severity_map) -> list[tuple[str, str, list[str]]]:
    """
    Finds potential diseases, descriptions, and precautions based on selected symptoms
    using the hardcoded CSV data, incorporating symptom severity.
    Returns a list of tuples: (disease_name, description, [precautions])
    """
    matching_diseases_with_scores = {}  # Stores disease -> weighted_score
    # Normalize selected symptoms for consistent matching
    normalized_selected_symptoms = [s.strip().lower() for s in selected_symptoms]

    for disease, symptoms_list in disease_symptoms_map.items():
        # Convert the symptoms_list from map to lowercase for comparison
        normalized_disease_symptoms = [s.lower() for s in symptoms_list]
        weighted_score = 0
        for selected_symptom in normalized_selected_symptoms:
            if selected_symptom in normalized_disease_symptoms:
                # Add severity weight if available, otherwise a default of 1
                # The .get() method is safe if a symptom is in dataset.csv but not in Symptom-severity.csv
                weight = symptom_severity_map.get(selected_symptom, 1)
                weighted_score += weight
        if weighted_score > 0:
            matching_diseases_with_scores[disease] = weighted_score

    # Sort diseases by the weighted score (highest first)
    sorted_matching_diseases = sorted(matching_diseases_with_scores.items(), key=lambda item: item[1], reverse=True)

    results = []
    # Limit to top 5 most matching diseases (or fewer if less than 5 matches)
    for disease_name, _ in sorted_matching_diseases[:5]:
        description = disease_description_map.get(disease_name, "No description available.")
        precautions = disease_precaution_map.get(disease_name, ["No precautions available."])
        results.append((disease_name, description, precautions))
    return results

# --- Function to parse insight text for analytics ---
def parse_insight_text_for_conditions(insight_text: str) -> list[str]:
    """
    Parses the combined insight text from history to extract condition names.
    Expected format: "Severity. Dataset Conditions: Cond1, Cond2; AI Suggestions: AICond1, AIC2"
    or just "Severity. No specific insights found."
    """
    conditions = []
    # Regex to find "Dataset Conditions: ..." and "AI Suggestions: ..." parts
    dataset_match = re.search(r"Dataset Conditions:\s*([^;]+)", insight_text)
    ai_match = re.search(r"AI Suggestions:\s*(.+)", insight_text)

    if dataset_match:
        dataset_str = dataset_match.group(1).strip()
        if dataset_str and dataset_str.lower() != "no specific insights found":
            conditions.extend([c.strip() for c in dataset_str.split(',') if c.strip()])

    if ai_match:
        ai_str = ai_match.group(1).strip()
        if ai_str and ai_str.lower() != "no specific insights found" and ai_str.lower() != "ai assistant is not available.":
            conditions.extend([c.strip() for c in ai_str.split(',') if c.strip()])

    # Remove duplicates and return
    return list(set(conditions))

# --- Main Application Logic ---
# Ensure feedback_input is initialized if not already (redundant if done at start, but harmless)
if "feedback_input" not in st.session_state:
    st.session_state.feedback_input = ""

if st.session_state.show_welcome:
    # A more visually appealing welcome page
    st.markdown("<h1 style='color: #0056b3; font-size: 3.5em; margin-top: 50px; text-shadow: 2px 2px 4px rgba(0,0,0,0.1);'>MediBot - Your Personal Health Assistant 🏥</h1>", unsafe_allow_html=True)
    st.markdown("""
        <div style='background-color: #e6f7ff; padding: 30px; border-radius: 15px; text-align: center; margin-top: 30px; box-shadow: 0 10px 30px rgba(0, 0, 0, 0.1);'>
            <p style='font-size: 1.2em; line-height: 1.8; color: #336699;'>
                Explore possible causes and precautions for your symptoms and get answers to health-related questions using advanced AI.
                Your health journey, simplified and supported.
            </p>
            <ul style='list-style-type: none; padding: 0; margin-top: 25px; display: inline-block; text-align: left;'>
                <li style='font-size: 1.1em; margin-bottom: 10px; color: #2a527a;'>✅ <b>Symptom Checker:</b> Get insights from a comprehensive symptom list.</li>
                <li style='font-size: 1.1em; margin-bottom: 10px; color: #2a527a;'>💬 <b>AI Chatbot:</b> Ask general health questions.</li>
                <li style='font-size: 1.1em; margin-bottom: 10px; color: #2a527a;'>👤 <b>User Management:</b> Save your health history.</li>
                <li style='font-size: 1.1em; margin-bottom: 10px; color: #2a527a;'>📜 <b>Persistent History:</b> View and download past records.</li>
                <li style='font-size: 1.1em; margin-bottom: 10px; color: #2a527a;'>📈 <b>Usage Insights:</b> See trends in conditions.</li>
            </ul>
        </div>
    """, unsafe_allow_html=True)
    st.markdown("<div style='text-align: center; margin-top: 40px;'>", unsafe_allow_html=True)
    if st.button("Get Started", key="welcome_button"):
        st.session_state.show_welcome = False
        st.rerun()  # Force rerun to ensure app reloads to main page
    st.markdown("</div>", unsafe_allow_html=True)
    st.markdown("""
        <div style='background-color: #fff8e1; padding: 20px; border-radius: 10px; margin-top: 50px; text-align: center; color: #8a6d3b; box-shadow: 0 4px 10px rgba(0,0,0,0.05);'>
            <p style='font-size: 0.9em; margin-bottom: 0;'>
                <b>Important Disclaimer:</b> This app provides preliminary health information based on symptoms and AI analysis.
                <b>It is not a substitute for professional medical advice, diagnosis, or treatment.</b> Always consult a qualified healthcare provider for a definitive diagnosis and personalized treatment plan, as this AI is for informational purposes only and not a substitute for professional medical advice.
            </p>
        </div>
    """, unsafe_allow_html=True)
else:
    # Displaying disclaimer at the top of the main app view
    st.markdown("<div class='stContainer' style='background-color: #fff8e1; border: 1px solid #ffeeba;'>"
                "<p style='margin-bottom: 0; font-size: 0.95em; color: #856404;'>"
                "<strong>Disclaimer</strong>: This app provides preliminary health information based on symptoms and AI analysis. "
                "It is not a substitute for professional medical advice, diagnosis, or treatment. Always consult a qualified healthcare provider."
                "</p>"
                "</div>", unsafe_allow_html=True)

    # Sidebar for User Management
    with st.sidebar:
        st.header("User Management")
        # Call the refactored user management function, passing st.session_state
        render_user_management_sidebar(st.session_state)

        st.markdown("---")
        st.header("Navigation")
        # Add a button to clear chat history
        if st.button("Clear Chat History", help="Clears all messages from the current session."):
            st.session_state.chat_history = []
            st.session_state.last_chat_response = ""
            st.session_state.chat_input_value = ""
            st.success("Chat history cleared!")

        # PDF Download Button - available if user is logged in and has history
        if st.session_state.get("user_id"):
            user_history = get_user_history(st.session_state["user_id"]) # Directly call get_user_history
            if user_history:
                pdf_buffer = generate_pdf_report(user_history)
                st.download_button(
                    label="Download Health Report (PDF)",
                    data=pdf_buffer,
                    file_name="medibot_health_report.pdf",
                    mime="application/pdf",
                    help="Download your chat and symptom checker history as a PDF report."
                )
            else:
                st.info("No history to download yet. Interact with MediBot to generate a report.")
        else:
            st.info("Log in to download your health report.")

    st.markdown("<h1 style='text-align: center; color: #0056b3;'>MediBot - Your Health Assistant 🩺</h1>", unsafe_allow_html=True)
    # Top-level tabs: Home, History, Feedback, About, Insights
    # Re-ordered tabs slightly to put Insights closer to History
    main_tab_home, main_tab_history, main_tab_insights, main_tab_feedback, main_tab_about = st.tabs(["Home", "History", "Insights", "Feedback", "About"])

    with main_tab_home:
        st.markdown("<h2>How can I help you today?</h2>", unsafe_allow_html=True)
        # Nested tabs for Symptom Checker and Chat with MediBot
        tab_symptom_checker, tab_chatbot = st.tabs(["Symptom Checker", "Chat with MediBot"])

        with tab_symptom_checker:
            st.markdown("<h3>Select from common symptoms to get insights:</h3>", unsafe_allow_html=True)
            selected_symptoms = st.multiselect(
                "Select your symptoms:",
                options=hardcoded_symptoms,  # Use symptoms derived from CSV
                default=[],
                key="symptom_select",
                help="Choose one or more symptoms you are experiencing."
            )

            if st.button("Get Health Insight", key="diagnose_button"):
                if not selected_symptoms:
                    st.error("Please select at least one symptom.")
                else:
                    with st.spinner("Analyzing symptoms..."):
                        # Get overall severity and predicted diagnoses from the Hugging Face model
                        combined_symptoms_text = ", ".join(selected_symptoms)
                        severity_assessment_text, predicted_diagnoses_from_model = get_diagnosis_and_severity_from_model(combined_symptoms_text)

                        # Get relevant disease info from your CSV datasets
                        diseases_from_csv = get_disease_info_from_csv(selected_symptoms, disease_symptoms_map, disease_description_map, disease_precaution_map, symptom_severity_map)

                        st.markdown(f"**{severity_assessment_text}**", unsafe_allow_html=True)
                        st.markdown("<h2>Possible Conditions and Insights:</h2>", unsafe_allow_html=True)  # Unified Heading

                        # --- Process and display CSV-based diseases first ---
                        if diseases_from_csv:
                            st.markdown("<h4>From our Medical Knowledge Base:</h4>", unsafe_allow_html=True)
                            for disease_name, description, precautions_list in diseases_from_csv:
                                with st.expander(disease_name):
                                    st.write(f"**Description**: {description}")
                                    st.write("**Precautions**:")
                                    if precautions_list:
                                        for precaution in precautions_list:
                                            if precaution:  # Only display non-empty precautions
                                                st.write(f"- {precaution}")
                                    else:
                                        st.write("- No specific precautions listed.")
                                    st.markdown("---")  # Separator for each disease in expander
                        else:
                            st.info("No common conditions found for these symptoms in our dataset. Please try adding more specific symptoms or switch to 'Chat with MediBot' for a general query.")

                        # --- Integrate relevant AI Model diagnoses not covered by CSV ---
                        additional_ai_diagnoses = []
                        # Create a set of normalized disease names from CSV for quick lookup and fuzzy matching
                        csv_disease_names_normalized = {d[0].lower() for d in diseases_from_csv}

                        for model_diag in predicted_diagnoses_from_model:
                            model_diag_normalized = model_diag.lower()
                            is_covered_by_csv = False
                            # Check for strong fuzzy match with CSV diseases
                            for csv_diag_name in csv_disease_names_normalized:
                                # Use token_set_ratio for better matching of multi-word terms, less sensitive to word order
                                if fuzz.token_set_ratio(model_diag_normalized, csv_diag_name) > 85:  # High threshold for a strong match
                                    is_covered_by_csv = True
                                    break
                            if not is_covered_by_csv:
                                additional_ai_diagnoses.append(model_diag)

                        if additional_ai_diagnoses:
                            st.markdown("<h4>Additional AI-Suggested Clinical Considerations:</h4>", unsafe_allow_html=True)
                            st.write("The AI model suggests the following clinical terms based on your symptoms:")
                            for diag in additional_ai_diagnoses:
                                st.write(f"- **{diag}**: This is a medical term that the AI found relevant. Please consult a healthcare professional for more details.")
                            st.info("These are general medical terms and require professional interpretation. They may not have specific descriptions or precautions available in our dataset.")
                        elif not diseases_from_csv:  # Only if no CSV diseases AND no unique AI diagnoses
                             st.info("The AI model could not confidently predict specific or unique diagnoses from the provided symptoms. Try different symptoms or consult a doctor.")

                        st.write("---")  # Final Separator

                        # --- Save to history (adjusting content to reflect unified response) ---
                        history_content_parts = []
                        if diseases_from_csv:
                            history_content_parts.append("Dataset Conditions: " + ", ".join([d[0] for d in diseases_from_csv]))
                        if additional_ai_diagnoses:
                            history_content_parts.append("AI Suggestions: " + ", ".join(additional_ai_diagnoses))

                        # Combine all insight for history
                        predicted_diseases_str_for_history = f"{severity_assessment_text.replace('Overall Symptom Severity (AI Assessment): ', '')}. " + "; ".join(history_content_parts)
                        if not history_content_parts:
                            predicted_diseases_str_for_history = f"{severity_assessment_text.replace('Overall Symptom Severity (AI Assessment): ', '')}. No specific insights found."

                        if st.session_state.get("user_id"):
                            # Call the refactored save history function
                            save_history_to_db_if_logged_in(st.session_state.user_id, ", ".join(selected_symptoms), predicted_diseases_str_for_history)
                            st.success("Analysis saved to your history.")
                        else:
                            st.info("Log in to save this analysis to your history.")

        with tab_chatbot:  # Ask a Health Question (Chatbot)
            st.markdown("<h3>Describe your symptoms or ask a general health question:</h3>", unsafe_allow_html=True)
            # Use st.form without clear_on_submit=True to keep text in the area
            with st.form("chat_form"): # Removed clear_on_submit=True
                user_question = st.text_area(
                    "Input your issue:",
                    value=st.session_state.chat_input_value,  # Use session state for value
                    key="chat_input_widget",  # Unique widget key
                    placeholder="e.g., I am having a severe fever and body aches. Or, what are the causes of high blood pressure?",
                    height=120  # Slightly taller text area
                )
                chat_submit_button = st.form_submit_button("Ask MediBot")

                if chat_submit_button:
                    if user_question:
                        # For the chatbot, if it's a direct question, severity is undetermined
                        # unless passed from a preceding symptom check.
                        # For simplicity, if not from symptom checker, pass "Undetermined Severity".
                        severity_for_groq_prompt = "Undetermined Severity"
                        with st.spinner("MediBot is thinking..."):
                            groq_answer = get_groq_response(user_question, severity_label=severity_for_groq_prompt)
                            st.markdown("**MediBot's Answer:**")
                            st.write(groq_answer)
                            # Save Q&A to chat history (if desired, not necessarily DB)
                            st.session_state.chat_history.append({"user": user_question, "bot": groq_answer})

                            # Save to database history if logged in
                            if st.session_state.get("user_id"):
                                # Prepend "Question: " to the input for history tracking
                                save_history_to_db_if_logged_in(st.session_state.user_id, f"Question: {user_question}", groq_answer)
                                st.success("Your question and answer have been saved to history.")
                            else:
                                st.info("Log in to save this Q&A to your history.")
                    else:
                        st.warning("Please type your question to get an answer.")

    with main_tab_history:
        st.header("Your Health History")
        user_id = st.session_state.get("user_id")
        if user_id:
            st.info("This section shows your saved symptom analyses and health questions.")
            history_data = get_user_history(user_id)  # Fetch history from database
            if history_data:
                st.subheader("Past Interactions:")
                # Display history in reverse chronological order using expanders
                for entry in reversed(history_data):
                    timestamp, symptoms_text, insight_text = entry[3], entry[1], entry[2]
                    # Determine summary title based on the nature of the input
                    summary_title_prefix = ""
                    expander_icon = ""  # Initialize icon here
                    if symptoms_text.startswith("Question: "):
                        keyword = extract_keyword(symptoms_text, hardcoded_symptoms)
                        summary_title_prefix = f"Question: {keyword}" if keyword != "Unknown" else "General Question"
                        expander_icon = "💬"
                    else:  # Symptom checker entry (🩺)
                        summary_conditions = parse_insight_text_for_conditions(insight_text)
                        if summary_conditions:
                            summary_title_prefix = ", ".join(summary_conditions[:3])
                            if len(summary_conditions) > 3:
                                summary_title_prefix += "..."
                        else:
                            # MODIFIED LOGIC: If no conditions identified, try to use input symptoms
                            input_symptoms_match = re.search(r"Symptoms/Question: (.*)", symptoms_text) # Adjusted regex for "Symptoms/Question:"
                            if input_symptoms_match:
                                extracted_input_symptoms = input_symptoms_match.group(1).strip()
                                # Clean up potential extra spaces/commas, take first few if too many
                                clean_symptoms = [s.strip() for s in extracted_input_symptoms.split(',') if s.strip()]
                                if clean_symptoms:
                                    summary_title_prefix = ", ".join(clean_symptoms[:3])
                                    if len(clean_symptoms) > 3:
                                        summary_title_prefix += "..."
                                else:
                                    summary_title_prefix = "No conditions identified"  # Fallback if no symptoms extracted
                            else:
                                summary_title_prefix = "No conditions identified"  # Fallback if input format is unexpected
                        expander_icon = "🩺"

                    # MODIFIED LINE: Use Markdown heading (e.g., ###) for larger font and bolding
                    expander_label = f"### **{timestamp.strftime('%Y-%m-%d %H:%M')}** - {expander_icon} *{summary_title_prefix}*"
                    with st.expander(expander_label):
                        st.write(f"**Your Input:** {symptoms_text}")
                        st.write(f"**MediBot's Insight:** {insight_text}")

                # PDF Download button
                pdf_buffer = generate_pdf_report(history_data)
                st.download_button(
                    label="Download History as PDF",
                    data=pdf_buffer,
                    file_name="MediBot_Health_Report.pdf",
                    mime="application/pdf"
                )
            else:
                st.info("No history found for your account. Start interacting with MediBot!")
        else:
            st.warning("Please log in to view your health history.")

    with main_tab_insights:
        st.header("Your Health Insights")
        user_id = st.session_state.get("user_id")
        if user_id:
            st.info("This section provides insights into the conditions identified in your past interactions.")
            history_data = get_user_history(user_id)
            if history_data:
                # Filter data for the last 30 days
                thirty_days_ago = datetime.now() - timedelta(days=30)
                recent_history = [
                    entry for entry in history_data
                    if entry[3] and entry[3] > thirty_days_ago  # entry[3] is query_timestamp
                ]
                if recent_history:
                    all_conditions = []
                    for entry in recent_history:
                        # entry[2] is predicted_diseases string
                        conditions_from_entry = parse_insight_text_for_conditions(entry[2])
                        all_conditions.extend(conditions_from_entry)

                    if all_conditions:
                        # Count occurrences of each condition
                        condition_counts = pd.Series(all_conditions).value_counts().reset_index()
                        condition_counts.columns = ['Condition', 'Count']
                        st.subheader("Most Frequent Conditions in Last 30 Days:")
                        # Display as a bar chart
                        st.bar_chart(condition_counts, x='Condition', y='Count', use_container_width=True)
                        st.write("This chart shows how many times each condition (from both dataset and AI suggestions) appeared in your analyses over the past 30 days.")
                    else:
                        st.info("No specific conditions were identified in your recent history (last 30 days).")
                else:
                    st.info("You have no health interactions in the last 30 days to generate insights.")
            else:
                st.info("No history found for your account. Start interacting with MediBot to see insights!")
        else:
            st.warning("Please log in to view your health insights.")

    with main_tab_feedback:
        st.header("Share Your Feedback")
        st.write("We appreciate your feedback to improve MediBot.")
        with st.form("feedback_form", clear_on_submit=True):
            feedback_text = st.text_area("Your feedback:", height=150, key="feedback_text_area")
            rating = st.slider("Rate your experience (1-5 stars):", 1, 5, 3, key="feedback_rating")
            feedback_submit_button = st.form_submit_button("Submit Feedback")

            if feedback_submit_button:
                if feedback_text:
                    # In a real app, you would save this to a database
                    st.session_state.feedback.append({"text": feedback_text, "rating": rating, "timestamp": datetime.now()})
                    st.success("Thank you for your feedback! It has been submitted.")
                    st.session_state.feedback_input = ""  # Clear after submission
                else:
                    st.warning("Please enter your feedback before submitting.")

    with main_tab_about:
        st.header("About MediBot")
        st.write("""
            MediBot is a health assistant designed to provide general information based on your symptoms and answer health-related questions.
            It utilizes various AI models and medical datasets to offer insights.

            **Technology Stack:**
            - **Streamlit**: For the interactive web application interface.
            - **Groq API**: Powers the conversational AI for health questions using high-performance language models (e.g., Llama-3), enabling rapid and relevant responses.
            - **Hugging Face Inference API**: Integrates with specialized medical text classification models, specifically `DATEXIS/CORe-clinical-diagnosis-prediction`, to predict possible clinical diagnoses (often mapping to ICD-9 codes) from symptom inputs.
            - **Pandas**: For efficient data handling and processing of local CSV medical datasets (symptoms, descriptions, precautions).
            - **ReportLab**: For generating downloadable PDF reports of your personalized health history.
            - **Database**: PostgreSQL is used for efficient handling of user's data, interaction history and diagnosis record keeping.


            **Datasets Used:**
            - Symptom-to-Disease mapping, Descriptions, and Precautions sourced from:
              "Disease Symptom Prediction" dataset available on Kaggle.
              [https://www.kaggle.com/datasets/itachi9604/disease-symptom-description-dataset](https://www.kaggle.com/datasets/itachi9604/disease-symptom-description-dataset)
              *Credit to Itachi9604 for compiling this valuable dataset.*

            **Important Disclaimer**: This application is for informational purposes only and should not be used as a substitute for professional medical advice, diagnosis, or treatment. Always consult with a qualified healthcare provider for any health concerns or before making any decisions related to your health.
        """)
        st.markdown("[Learn more about Streamlit](https://streamlit.io/)")
        st.markdown("[Learn more about Groq](https://groq.com/)")
        st.markdown("[Learn more about Hugging Face](https://huggingface.co/)")

st.markdown("---")
st.markdown("For professional medical advice, always consult a qualified healthcare provider.")