Upload 13 files

Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.10-slim
+
+# Prevent Python from writing pyc files
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+# Install system dependencies (required for sklearn / xgboost)
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    gcc \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy and install dependencies first (better caching)
+COPY requirements.txt .
+RUN pip install --no-cache-dir --upgrade pip \
+    && pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Hugging Face expects port 7860
+EXPOSE 7860
+
+# Start FastAPI
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,119 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel, Field
+from typing import Annotated, Literal
+from prediction_helper import predict
+from one_shot_bot import generate_advice
+from chatbot_advisor import ask_chatbot
+
+class ModelInput(BaseModel):
+    gender: Annotated[Literal["male", "female"], Field(description="Enter your gender")]
+    marital_status: Annotated[Literal["married", "unmarried"], Field(description="Enter your marital status")]
+    age: Annotated[int, Field(gt=0, lt=110, description="Enter your age")]
+    number_of_dependants: Annotated[int, Field(gt=0, lt=8)]
+    income_lakhs: Annotated[float, Field(gt=0,description="Enter your annual income in lakhs")]
+    genetical_risk: Annotated[int, Field(gt=0, lt=6)]
+    insurance_plan: Annotated[Literal['Bronze', 'Silver', 'Gold'], Field(description="Choose one of the given plans")]
+    employment_status: Annotated[Literal['Salaried', 'Self-Employed', 'Freelancer'], Field()]
+    bmi_category: Annotated[Literal['Normal', 'Obesity', 'Overweight', 'Underweight'], Field()]
+    smoking_status: Annotated[Literal['No Smoking', 'Regular', 'Occasional'], Field()]
+    region: Annotated[Literal['Northwest', 'Southeast', 'Northeast', 'Southwest'], Field()]
+    medical_history: Annotated[
+        Literal[
+            'No Disease', 'Diabetes', 'High blood pressure', 'Diabetes & High blood pressure',
+            'Thyroid', 'Heart disease', 'High blood pressure & Heart disease',
+            'Diabetes & Thyroid', 'Diabetes & Heart disease'
+        ],
+        Field()
+    ]
+
+class ModelOutput(BaseModel):
+    yearly : float
+    monthly : float
+    advice : str
+
+class ChatMessage(BaseModel):
+    thread_id : str
+    message : str
+    yearly_cost : float
+    monthly_cost : float
+    ai_summary : str
+
+app = FastAPI()
+
+@app.get("/plans")
+def plans():
+    return {
+        "Bronze": "Basic coverage, low premium.",
+        "Silver": "Balance of premium and coverage.",
+        "Gold": "Premium cost with highest benefits."
+    }
+
+
+@app.get("/home")
+def home():
+    return {"message": "Welcome! The API is live"}
+
+@app.post("/predict", response_model=ModelOutput)
+def predict_output(input_data: ModelInput):
+    try:
+        data = input_data.model_dump()
+
+        converted_data = {
+            "Gender": data["gender"].title(),
+            "Marital Status": data["marital_status"].title(),
+            "Age": data["age"],
+            "Number of Dependants": data["number_of_dependants"],
+            "Income in Lakhs": data["income_lakhs"],
+            "Genetical Risk": data["genetical_risk"],
+            "Insurance Plan": data["insurance_plan"].title(),
+            "Employment Status": data["employment_status"],
+            "BMI Category": data["bmi_category"],
+            "Smoking Status": data["smoking_status"],
+            "Region": data["region"],
+            "Medical History": data["medical_history"]
+        }
+
+        yearly_prediction = float(predict(converted_data))
+        monthly = round(yearly_prediction / 12, 2)
+
+        advice = generate_advice(
+            yearly_premium=yearly_prediction,
+            monthly_premium=monthly,
+            age=input_data.age,
+            gender=input_data.gender,
+            marital_status=input_data.marital_status,
+            dependents=input_data.number_of_dependants,
+            bmi_category=input_data.bmi_category,
+            smoking_status=input_data.smoking_status,
+            medical_history=input_data.medical_history,
+            genetic_risk=input_data.genetical_risk,
+            region=input_data.region,
+            income_lakhs=input_data.income_lakhs,
+            employment_status=input_data.employment_status,
+            insurance_plan=input_data.insurance_plan
+        )
+
+        return ModelOutput(yearly=yearly_prediction, monthly=monthly, advice=advice)
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Prediction Failed: {str(e)}")
+
+
+@app.post('/chat')
+def chat(input_data : ChatMessage):
+    try:
+        yearly_cost = input_data.yearly_cost
+        monthly_cost = input_data.monthly_cost
+        ai_summary = input_data.ai_summary
+
+        response = ask_chatbot(
+            yearly_cost=yearly_cost,
+            monthly_cost=monthly_cost,
+            ai_summary=ai_summary,
+            user_message=input_data.message,
+            thread_id=input_data.thread_id
+        )
+        return {"response": response}
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

chatbot_advisor.py

@@ -0,0 +1,103 @@
+from langgraph.graph import StateGraph, START, END
+from typing import TypedDict,Annotated
+from langchain_core.messages import HumanMessage, BaseMessage, AIMessage, SystemMessage
+from langchain_groq import ChatGroq
+from langgraph.checkpoint.memory import MemorySaver
+from dotenv import load_dotenv
+from langgraph.graph.message import add_messages
+import os
+load_dotenv()
+
+class ChatState(TypedDict):
+    messages : Annotated[list[BaseMessage], add_messages]
+
+llm = ChatGroq(model="openai/gpt-oss-20b", api_key=os.getenv("GROQ_API_KEY"), streaming=True)
+
+SYSTEM_MESSAGE = SystemMessage(
+    content=(
+    """You are CareWise AI, a helpful health insurance guidance assistant designed to help users understand their estimated insurance premium and explore suitable coverage options based on the information they provide.
+
+Your role is to:
+- Explain premium estimates in a simple and friendly way
+- Help users make sense of the key factors influencing cost
+- Offer useful and relevant recommendations on insurance plans, budgeting, and coverage fit
+- Provide supportive guidance without making guarantees or medical claims
+
+Your response style should be:
+
+- Clear, conversational, and human-like (avoid robotic tone)
+- Short and structured rather than long or overwhelming
+- Warm, encouraging, and professional
+- Empathetic and respectful, especially when discussing health-related factors
+- Neutral and non-judgmental (never shame lifestyle or medical conditions)
+
+When responding:
+
+- Reference user context when helpful (age, plan type, lifestyle factors, etc.)
+- Focus on the most meaningful cost drivers rather than listing everything
+- Provide actionable suggestions (example: exploring plan tiers, budgeting tips, preventive care habits, lifestyle improvements, or coverage add-ons)
+- Keep explanations simple and avoid technical insurance language unless useful and easy to explain
+- Avoid long paragraphs; use short sentences or small chunks for clarity
+
+Safety Rules:
+
+- Do NOT give medical advice, diagnoses, treatment recommendations, or anything that could be interpreted as professional health guidance
+- Do NOT make financial guarantees or legal statements
+- You may suggest healthy habits only in general, non-medical wording (e.g., "staying active may help overall well-being")
+- Never promise that a specific plan or behavior will reduce premiums
+
+If the user asks a question outside your scope, gently redirect them to a licensed insurance advisor or healthcare professional.
+
+Your priority is helping users feel informed, confident, and supported while exploring insurance costs and coverage options.
+"""
+    )
+)
+
+def chat_node(state : ChatState):
+    user_query = state['messages']
+    query = [SYSTEM_MESSAGE]+user_query
+    response = llm.invoke(query)
+    return {'messages': [response]}
+
+checkpointer = MemorySaver()
+graph = StateGraph(ChatState)
+graph.add_node("chat_node", chat_node)
+graph.add_edge(START, 'chat_node')
+graph.add_edge('chat_node', END)
+
+insurance_chatbot = graph.compile(checkpointer=checkpointer)
+
+thread_id='1'
+config = {'configurable' : {'thread_id' : thread_id}}
+
+def format_chat_input(yearly_cost, monthly_cost, ai_summary, user_message):
+    return f"""
+Below is the most recent health insurance evaluation. Use this information while responding.
+
+INSURANCE ESTIMATE
+------------------
+• Yearly Premium: ₹{yearly_cost:,.2f}
+• Monthly Cost: ₹{monthly_cost:,.2f}
+
+AI PLAN SUMMARY
+---------------
+{ai_summary}
+
+USER QUESTION
+-------------
+{user_message}
+
+Respond as CareWise AI using a warm, clear, and supportive tone. Make your answer helpful and easy to understand.
+"""
+
+def ask_chatbot(yearly_cost, monthly_cost, ai_summary, user_message, thread_id):
+    formatted_msg = format_chat_input(yearly_cost, monthly_cost, ai_summary, user_message)
+
+    initial_state = {
+        "messages": [HumanMessage(content=formatted_msg)]
+    }
+
+    config = {"configurable": {"thread_id": thread_id}}
+
+    response = insurance_chatbot.invoke(initial_state, config=config)
+    return response["messages"][-1].content

data_segmentation.ipynb

@@ -0,0 +1,433 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "35b7f880",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Age</th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Region</th>\n",
+       "      <th>Marital_status</th>\n",
+       "      <th>Number Of Dependants</th>\n",
+       "      <th>BMI_Category</th>\n",
+       "      <th>Smoking_Status</th>\n",
+       "      <th>Employment_Status</th>\n",
+       "      <th>Income_Level</th>\n",
+       "      <th>Income_Lakhs</th>\n",
+       "      <th>Medical History</th>\n",
+       "      <th>Insurance_Plan</th>\n",
+       "      <th>Annual_Premium_Amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>26</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>Northwest</td>\n",
+       "      <td>Unmarried</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Normal</td>\n",
+       "      <td>No Smoking</td>\n",
+       "      <td>Salaried</td>\n",
+       "      <td>&lt;10L</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Diabetes</td>\n",
+       "      <td>Bronze</td>\n",
+       "      <td>9053</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>29</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Southeast</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Obesity</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>Salaried</td>\n",
+       "      <td>&lt;10L</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Diabetes</td>\n",
+       "      <td>Bronze</td>\n",
+       "      <td>16339</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>49</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Northeast</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Normal</td>\n",
+       "      <td>No Smoking</td>\n",
+       "      <td>Self-Employed</td>\n",
+       "      <td>10L - 25L</td>\n",
+       "      <td>20</td>\n",
+       "      <td>High blood pressure</td>\n",
+       "      <td>Silver</td>\n",
+       "      <td>18164</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>30</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Southeast</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Normal</td>\n",
+       "      <td>No Smoking</td>\n",
+       "      <td>Salaried</td>\n",
+       "      <td>&gt; 40L</td>\n",
+       "      <td>77</td>\n",
+       "      <td>No Disease</td>\n",
+       "      <td>Gold</td>\n",
+       "      <td>20303</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>18</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>Northeast</td>\n",
+       "      <td>Unmarried</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Overweight</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>Self-Employed</td>\n",
+       "      <td>&gt; 40L</td>\n",
+       "      <td>99</td>\n",
+       "      <td>High blood pressure</td>\n",
+       "      <td>Silver</td>\n",
+       "      <td>13365</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Age  Gender     Region Marital_status  Number Of Dependants BMI_Category  \\\n",
+       "0   26    Male  Northwest      Unmarried                     0       Normal   \n",
+       "1   29  Female  Southeast        Married                     2      Obesity   \n",
+       "2   49  Female  Northeast        Married                     2       Normal   \n",
+       "3   30  Female  Southeast        Married                     3       Normal   \n",
+       "4   18    Male  Northeast      Unmarried                     0   Overweight   \n",
+       "\n",
+       "  Smoking_Status Employment_Status Income_Level  Income_Lakhs  \\\n",
+       "0     No Smoking          Salaried         <10L             6   \n",
+       "1        Regular          Salaried         <10L             6   \n",
+       "2     No Smoking     Self-Employed    10L - 25L            20   \n",
+       "3     No Smoking          Salaried        > 40L            77   \n",
+       "4        Regular     Self-Employed        > 40L            99   \n",
+       "\n",
+       "       Medical History Insurance_Plan  Annual_Premium_Amount  \n",
+       "0             Diabetes         Bronze                   9053  \n",
+       "1             Diabetes         Bronze                  16339  \n",
+       "2  High blood pressure         Silver                  18164  \n",
+       "3           No Disease           Gold                  20303  \n",
+       "4  High blood pressure         Silver                  13365  "
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "df = pd.read_excel(\"premiums.xlsx\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "2b820232",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(50000, 13)"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "206a3cdb",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count    50000.000000\n",
+       "mean        34.593480\n",
+       "std         15.000437\n",
+       "min         18.000000\n",
+       "25%         22.000000\n",
+       "50%         31.000000\n",
+       "75%         45.000000\n",
+       "max        356.000000\n",
+       "Name: Age, dtype: float64"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.Age.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "8b905a77",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_young = df[df.Age<=25]\n",
+    "df_rest = df[df.Age>25]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f1d671ec",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((20096, 13), (29904, 13))"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_young.shape, df_rest.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "f566ae1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_young.to_excel(\"premiums_young.xlsx\", index=False)\n",
+    "df_rest.to_excel(\"premiums_rest.xlsx\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ebcc0f68",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "469c45f4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Age</th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Region</th>\n",
+       "      <th>Marital_status</th>\n",
+       "      <th>Number Of Dependants</th>\n",
+       "      <th>BMI_Category</th>\n",
+       "      <th>Smoking_Status</th>\n",
+       "      <th>Employment_Status</th>\n",
+       "      <th>Income_Level</th>\n",
+       "      <th>Income_Lakhs</th>\n",
+       "      <th>Medical History</th>\n",
+       "      <th>Insurance_Plan</th>\n",
+       "      <th>Annual_Premium_Amount</th>\n",
+       "      <th>Genetical_Risk</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>26</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>Northwest</td>\n",
+       "      <td>Unmarried</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Normal</td>\n",
+       "      <td>No Smoking</td>\n",
+       "      <td>Salaried</td>\n",
+       "      <td>&lt;10L</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Diabetes</td>\n",
+       "      <td>Bronze</td>\n",
+       "      <td>9053</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>29</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Southeast</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Obesity</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>Salaried</td>\n",
+       "      <td>&lt;10L</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Diabetes</td>\n",
+       "      <td>Bronze</td>\n",
+       "      <td>16339</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Age  Gender     Region Marital_status  Number Of Dependants BMI_Category  \\\n",
+       "0   26    Male  Northwest      Unmarried                     0       Normal   \n",
+       "1   29  Female  Southeast        Married                     2      Obesity   \n",
+       "\n",
+       "  Smoking_Status Employment_Status Income_Level  Income_Lakhs Medical History  \\\n",
+       "0     No Smoking          Salaried         <10L             6        Diabetes   \n",
+       "1        Regular          Salaried         <10L             6        Diabetes   \n",
+       "\n",
+       "  Insurance_Plan  Annual_Premium_Amount  Genetical_Risk  \n",
+       "0         Bronze                   9053               5  \n",
+       "1         Bronze                  16339               0  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "df = pd.read_excel(\"premiums_with_gr.xlsx\")\n",
+    "df.head(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "48104400",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((20096, 14), (29904, 14))"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_young = df[df.Age<=25]\n",
+    "df_rest = df[df.Age>25]\n",
+    "\n",
+    "df_young.shape, df_rest.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "18a2d9ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_young.to_excel(\"premiums_young_with_gr.xlsx\", index=False)\n",
+    "df_rest.to_excel(\"premiums_rest_with_gr.xlsx\", index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

main.py

@@ -0,0 +1,488 @@
+import streamlit as st
+import requests
+import uuid
+
+# Page configuration
+st.set_page_config(
+    page_title="HealthGuard AI: Insurance Cost Predictor",
+    page_icon="🏥",
+    layout="wide"
+)
+
+# Initialize session storage
+if "chat_history" not in st.session_state:
+    st.session_state.chat_history = []
+if "thread_id" not in st.session_state:
+    st.session_state.thread_id = str(uuid.uuid4())
+if "analysis_done" not in st.session_state:
+    st.session_state.analysis_done = False
+if "show_info" not in st.session_state:
+    st.session_state.show_info = False
+
+# ========================= ENHANCED UI STYLING =========================
+st.markdown("""
+<style>
+@import url('https://fonts.googleapis.com/css2?family=Montserrat:wght@400;600;700&display=swap');
+* {
+    font-family: 'Montserrat', 'Inter', sans-serif;
+}
+.main {
+    background: linear-gradient(135deg, #212d3b 0%, #223a57 100%);
+    padding: 2rem 0;
+}
+.header-container {
+    background: linear-gradient(135deg, #243b55 0%, #141e30 100%);
+    padding: 2rem;
+    border-radius: 16px;
+    box-shadow: 0 8px 32px rgba(36, 59, 85,0.13);
+    margin-bottom: 2rem;
+    text-align: center;
+}
+.header-title {
+    color: white;
+    font-size: 2.5rem;
+    font-weight: 700;
+    margin: 0;
+    text-shadow: 2px 2px 6px rgba(20,30,48,0.2);
+    font-family: 'Montserrat', sans-serif;
+}
+.header-subtitle {
+    color: #aab3cf;
+    font-size: 1.1rem;
+    margin-top: 0.5rem;
+    font-family: 'Montserrat', sans-serif;
+}
+.section-card {
+    background: #25304b;
+    padding: 1.5rem;
+    border-radius: 12px;
+    box-shadow: 0 4px 8px rgba(36, 59, 85,0.12);
+    margin-bottom: 1.5rem;
+    border-left: 4px solid #27ae60;
+    color: #f3f4fa;
+}
+.section-title {
+    color: #f1f7fc;
+    font-size: 1.3rem;
+    font-weight: 700;
+    margin-bottom: 1rem;
+    display: flex;
+    align-items: center;
+    gap: 0.5rem;
+    font-family: 'Montserrat', sans-serif;
+}
+.info-box {
+    background: linear-gradient(135deg, #344667 0%, #27ae60 100%);
+    color: #f1f7fc;
+    padding: 1rem;
+    border-radius: 10px;
+    margin: 1rem 0;
+    border-left: 4px solid #18aad5;
+    animation: slideIn 0.5s ease-out;
+}
+@keyframes slideIn {
+    from { opacity: 0; transform: translateY(-10px); }
+    to { opacity: 1; transform: translateY(0); }
+}
+.metric-card {
+    background: linear-gradient(135deg, #27ae60 0%, #243b55 100%);
+    padding: 1.2rem;
+    border-radius: 12px;
+    color: #f3f4fa;
+    text-align: center;
+    box-shadow: 0 4px 15px rgba(39, 174, 96, 0.2);
+    transition: transform 0.3s ease;
+}
+.metric-card:hover {
+    transform: translateY(-5px);
+}
+.metric-value {
+    font-size: 2rem;
+    font-weight: 700;
+    margin: 0.5rem 0;
+    font-family: 'Montserrat', sans-serif;
+}
+.metric-label {
+    font-size: 0.9rem;
+    opacity: 0.92;
+}
+.result-card {
+    background: linear-gradient(135deg, #27ae60 0%, #2d375b 100%);
+    padding: 2rem;
+    border-radius: 16px;
+    color: #f4f8ff;
+    box-shadow: 0 8px 32px rgba(39, 174, 96, 0.10);
+    margin: 1.5rem 0;
+}
+.result-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
+    gap: 1.5rem;
+    margin-top: 1rem;
+}
+.result-item {
+    background: rgba(25,40,65,0.2);
+    padding: 1.5rem;
+    border-radius: 12px;
+    backdrop-filter: blur(10px);
+}
+.result-item-label {
+    font-size: 0.9rem;
+    opacity: 0.9;
+    margin-bottom: 0.5rem;
+}
+.result-item-value {
+    font-size: 1.8rem;
+    font-weight: 700;
+}
+.advisor-box {
+    background: linear-gradient(135deg, #27ae60 0%, #243b55 100%);
+    color: #f5f5fa;
+    padding: 1.5rem;
+    border-radius: 12px;
+    margin-top: 1.5rem;
+    border-left: 4px solid #18aad5;
+    box-shadow: 0 4px 15px rgba(39, 174, 96, 0.1);
+}
+.advisor-box h4 {
+    color: #f1f7fc;
+    margin-top: 0;
+}
+.chat-container {
+    background: #24304e;
+    color: #fff;
+    padding: 1.5rem;
+    border-radius: 12px;
+    box-shadow: 0 4px 6px rgba(36, 48, 78,0.12);
+    max-height: 400px;
+    overflow-y: auto;
+    margin-bottom: 1rem;
+}
+.chat-bubble-user {
+    background: linear-gradient(135deg, #27ae60 0%, #243b55 100%);
+    color: white;
+    padding: 12px 18px;
+    border-radius: 18px 18px 4px 18px;
+    margin: 8px 0 8px auto;
+    max-width: 70%;
+    text-align: right;
+    box-shadow: 0 2px 8px rgba(39, 174, 96, 0.13);
+    animation: slideInRight 0.3s ease-out;
+    font-family: 'Montserrat', sans-serif;
+}
+.chat-bubble-bot {
+    background: #20293b;
+    border: 2px solid #2a3d6a;
+    color: #ebf2f8;
+    padding: 12px 18px;
+    border-radius: 18px 18px 18px 4px;
+    margin: 8px auto 8px 0;
+    max-width: 70%;
+    box-shadow: 0 2px 8px rgba(0,0,0,0.1);
+    animation: slideInLeft 0.3s ease-out;
+    font-family: 'Montserrat', sans-serif;
+}
+@keyframes slideInRight {
+    from { opacity: 0; transform: translateX(20px); }
+    to { opacity: 1; transform: translateX(0); }
+}
+@keyframes slideInLeft {
+    from { opacity: 0; transform: translateX(-20px); }
+    to { opacity: 1; transform: translateX(0); }
+}
+.stButton>button {
+    width: 100%;
+    background: linear-gradient(135deg, #27ae60 0%, #223a57 100%);
+    color: white;
+    font-weight: 600;
+    border: none;
+    border-radius: 10px;
+    padding: 0.8rem;
+    font-size: 1rem;
+    font-family: 'Montserrat', sans-serif;
+    transition: all 0.3s ease;
+    box-shadow: 0 4px 15px rgba(39, 174, 96, 0.13);
+}
+.stButton>button:hover {
+    transform: translateY(-2px);
+    box-shadow: 0 6px 20px rgba(39, 174, 96, 0.20);
+}
+.stNumberInput>div>div>input,
+.stSelectbox>div>div>select,
+.stTextInput>div>div>input {
+    border-radius: 8px;
+    border: 2px solid #233269;
+    padding: 0.5rem;
+    transition: border-color 0.3s ease;
+    background: #2d375b;
+    color: #e9ecfa;
+    font-family: 'Montserrat', sans-serif;
+}
+.stNumberInput>div>div>input:focus,
+.stSelectbox>div>div>select:focus,
+.stTextInput>div>div>input:focus {
+    border-color: #27ae60;
+    box-shadow: 0 0 0 3px rgba(39, 174, 96, 0.1);
+}
+.alert-banner {
+    background: linear-gradient(135deg, #233269 0%, #27ae60 100%);
+    color: #fff;
+    padding: 1rem;
+    border-radius: 10px;
+    margin: 1rem 0;
+    border-left: 4px solid #18aad5;
+    display: flex;
+    align-items: center;
+    gap: 0.5rem;
+}
+.chat-container::-webkit-scrollbar {
+    width: 8px;
+}
+.chat-container::-webkit-scrollbar-track {
+    background: #1a2336;
+    border-radius: 10px;
+}
+.chat-container::-webkit-scrollbar-thumb {
+    background: #27ae60;
+    border-radius: 10px;
+}
+.chat-container::-webkit-scrollbar-thumb:hover {
+    background: #229954;
+}
+</style>
+""", unsafe_allow_html=True)
+
+# ========================= HEADER =========================
+st.markdown("""
+<div class="header-container">
+    <h1 class="header-title">🏥 HealthGuard AI</h1>
+    <p class="header-subtitle">AI-Powered Health Insurance Cost Prediction Platform</p>
+</div>
+""", unsafe_allow_html=True)
+
+# Alert Banner
+st.markdown("""
+<div class="alert-banner">
+    ⚠️ <strong>Note:</strong> First request may take up to 20 seconds (API cold start).
+</div>
+""", unsafe_allow_html=True)
+
+# Info Toggle
+if st.button("ℹ️ How It Works"):
+    st.session_state.show_info = not st.session_state.show_info
+
+if st.session_state.show_info:
+    st.markdown("""
+    <div class="info-box">
+        <h4>📊 About HealthGuard AI</h4>
+        <p><strong>What we analyze:</strong></p>
+        <ul>
+            <li>Personal demographics and health profile</li>
+            <li>Lifestyle factors (smoking, BMI category)</li>
+            <li>Medical history and genetic risk factors</li>
+            <li>Financial capacity and employment status</li>
+        </ul>
+        <p><strong>Our AI provides:</strong></p>
+        <ul>
+            <li>Accurate annual premium predictions</li>
+            <li>Monthly payment breakdowns</li>
+            <li>Personalized health insurance advice</li>
+            <li>Interactive Q&A with AI health advisor</li>
+        </ul>
+    </div>
+    """, unsafe_allow_html=True)
+
+# Categorical options
+categorical_options = {
+    'Gender': ['Male', 'Female'],
+    'Marital Status': ['Unmarried', 'Married'],
+    'BMI Category': ['Normal', 'Obesity', 'Overweight', 'Underweight'],
+    'Smoking Status': ['No Smoking', 'Regular', 'Occasional'],
+    'Employment Status': ['Salaried', 'Self-Employed', 'Freelancer'],
+    'Region': ['Northwest', 'Southeast', 'Northeast', 'Southwest'],
+    'Medical History': [
+        'No Disease', 'Diabetes', 'High blood pressure', 'Diabetes & High blood pressure',
+        'Thyroid', 'Heart disease', 'High blood pressure & Heart disease',
+        'Diabetes & Thyroid', 'Diabetes & Heart disease'
+    ],
+    'Insurance Plan': ['Bronze', 'Silver', 'Gold']
+}
+
+# ========================= INPUT FORM =========================
+col_left, col_right = st.columns([1, 1], gap="large")
+
+with col_left:
+    st.markdown('<div class="section-card">', unsafe_allow_html=True)
+    st.markdown('<div class="section-title">👤 Personal Information</div>', unsafe_allow_html=True)
+    
+    age = st.number_input('Age', min_value=18, max_value=100, value=30, step=1)
+    gender = st.selectbox('Gender', categorical_options['Gender'])
+    marital_status = st.selectbox('Marital Status', categorical_options['Marital Status'])
+    number_of_dependants = st.number_input('Number of Dependants', min_value=0, max_value=7, value=2, step=1)
+    region = st.selectbox('Region', categorical_options['Region'])
+    
+    st.markdown('</div>', unsafe_allow_html=True)
+    
+    st.markdown('<div class="section-card">', unsafe_allow_html=True)
+    st.markdown('<div class="section-title">💼 Financial Details</div>', unsafe_allow_html=True)
+    
+    income_lakhs = st.number_input('Annual Income (Lakhs)', min_value=1, max_value=200, value=10, step=1)
+    employment_status = st.selectbox('Employment Status', categorical_options['Employment Status'])
+    insurance_plan = st.selectbox('Insurance Plan', categorical_options['Insurance Plan'])
+    
+    st.markdown('</div>', unsafe_allow_html=True)
+
+with col_right:
+    st.markdown('<div class="section-card">', unsafe_allow_html=True)
+    st.markdown('<div class="section-title">🏥 Health Information</div>', unsafe_allow_html=True)
+    
+    bmi_category = st.selectbox('BMI Category', categorical_options['BMI Category'])
+    smoking_status = st.selectbox('Smoking Status', categorical_options['Smoking Status'])
+    medical_history = st.selectbox('Medical History', categorical_options['Medical History'])
+    genetical_risk = st.number_input('Genetical Risk (1-5)', min_value=1, max_value=5, value=3, step=1)
+    
+    st.markdown('</div>', unsafe_allow_html=True)
+    
+    # Risk indicator
+    risk_color = "#e74c3c" if genetical_risk >= 4 else "#f39c12" if genetical_risk == 3 else "#27ae60"
+    st.markdown(f"""
+    <div class="metric-card" style="background: linear-gradient(135deg, {risk_color} 0%, #243b55 100%);">
+        <div class="metric-label">Genetic Risk Level</div>
+        <div class="metric-value">{genetical_risk}/5</div>
+    </div>
+    """, unsafe_allow_html=True)
+
+# Prepare input dictionary
+input_dict = {
+    'age': age,
+    'number_of_dependants': number_of_dependants,
+    'income_lakhs': income_lakhs,
+    'genetical_risk': genetical_risk,
+    'insurance_plan': insurance_plan,
+    'employment_status': employment_status,
+    'gender': gender.lower(),
+    'marital_status': marital_status.lower(),
+    'bmi_category': bmi_category,
+    'smoking_status': smoking_status,
+    'region': region,
+    'medical_history': medical_history
+}
+
+# ========================= PREDICTION BUTTON =========================
+st.markdown("<br>", unsafe_allow_html=True)
+
+if st.button("💰 Calculate Insurance Premium", use_container_width=True):
+    API_URL = st.secrets["API_URL"]
+    
+    with st.spinner('🤖 Calculating your premium...'):
+        try:
+            response = requests.post(API_URL, json=input_dict, timeout=30)
+            
+            if response.status_code == 200:
+                result = response.json()
+                yearly = result['yearly']
+                monthly = result['monthly']
+                advice = result['advice']
+                
+                # Display Results
+                st.markdown('<div class="result-card">', unsafe_allow_html=True)
+                st.markdown('<h3 style="margin-top:0; color:white;">📊 Premium Calculation Results</h3>', unsafe_allow_html=True)
+                st.markdown(f"""
+                <div class="result-grid">
+                    <div class="result-item">
+                        <div class="result-item-label">Annual Premium</div>
+                        <div class="result-item-value">₹ {yearly:,.2f}</div>
+                    </div>
+                    <div class="result-item">
+                        <div class="result-item-label">Monthly Premium</div>
+                        <div class="result-item-value">₹ {monthly:,.2f}</div>
+                    </div>
+                    <div class="result-item">
+                        <div class="result-item-label">Insurance Plan</div>
+                        <div class="result-item-value">{insurance_plan}</div>
+                    </div>
+                </div>
+                """, unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
+                
+                # Display advice
+                st.markdown(f"""
+                <div class="advisor-box">
+                    <h4>💡 AI Health Advisor Insights</h4>
+                    <p>{advice}</p>
+                </div>
+                """, unsafe_allow_html=True)
+                
+                # Store results in session state
+                st.session_state.yearly_cost = yearly
+                st.session_state.monthly_cost = monthly
+                st.session_state.ai_summary = advice
+                st.session_state.analysis_done = True
+                
+                st.success("✅ Calculation complete! You can now chat with our AI assistant below.")
+            else:
+                st.error(f"❌ API Error: {response.status_code}")
+                
+        except requests.exceptions.Timeout:
+            st.error("⏱️ Request timed out. Please try again.")
+        except Exception as e:
+            st.error(f"❌ Connection error: {str(e)}")
+
+# ========================= CHATBOT =========================
+if st.session_state.analysis_done:
+    st.markdown("<br><br>", unsafe_allow_html=True)
+    st.markdown('<div class="section-card">', unsafe_allow_html=True)
+    st.markdown('<div class="section-title">💬 Interactive Health Insurance Assistant</div>', unsafe_allow_html=True)
+    
+    if st.session_state.chat_history:
+        st.markdown('<div class="chat-container">', unsafe_allow_html=True)
+        for role, msg in st.session_state.chat_history:
+            bubble = "chat-bubble-user" if role == "user" else "chat-bubble-bot"
+            prefix = "You: " if role == "user" else "🤖 Assistant: "
+            st.markdown(f"<div class='{bubble}'><strong>{prefix}</strong>{msg}</div>", unsafe_allow_html=True)
+        st.markdown('</div>', unsafe_allow_html=True)
+    
+    user_query = st.text_input("Ask a question about your insurance:", placeholder="e.g., How can I reduce my premium costs?")
+    
+    col_send, col_clear = st.columns([3, 1])
+    with col_send:
+        send_button = st.button("📤 Send Message", use_container_width=True)
+    with col_clear:
+        if st.button("🗑️ Clear Chat", use_container_width=True):
+            st.session_state.chat_history = []
+            st.session_state.thread_id = str(uuid.uuid4())
+            st.experimental_rerun()
+    
+    if send_button and user_query.strip():
+        CHAT_URL = st.secrets["CHAT_URL"]
+        payload = {
+            "thread_id": st.session_state.thread_id,
+            "message": user_query,
+            "yearly_cost": st.session_state.yearly_cost,
+            "monthly_cost": st.session_state.monthly_cost,
+            "ai_summary": st.session_state.ai_summary
+        }
+        
+        with st.spinner("🤖 Thinking..."):
+            try:
+                r = requests.post(CHAT_URL, json=payload, timeout=30)
+                if r.status_code == 200:
+                    reply = r.json()["response"]
+                    st.session_state.chat_history.append(("user", user_query))
+                    st.session_state.chat_history.append(("bot", reply))
+                    st.experimental_rerun()
+                else:
+                    st.error(f"❌ Chat server error: {r.status_code}")
+            except Exception as e:
+                st.error(f"❌ Chat failed: {e}")
+    
+    st.markdown('</div>', unsafe_allow_html=True)
+
+# Footer
+st.markdown("<br><br>", unsafe_allow_html=True)
+st.markdown("""
+<div style='text-align: center; color: #7f8c8d; font-size: 0.9rem;'>
+    <p>🏥 HealthGuard AI © 2025 | Powered by Advanced Machine Learning</p>
+    <p style='font-size: 0.8rem;'>For demonstration purposes only. Not medical or financial advice.</p>
+</div>
+""", unsafe_allow_html=True)

one_shot_bot.py

@@ -0,0 +1,75 @@
+from langchain_groq import ChatGroq
+from langchain_core.prompts import PromptTemplate
+import os
+from dotenv import load_dotenv
+load_dotenv()
+
+llm = ChatGroq(model="openai/gpt-oss-20b", api_key=os.getenv("GROQ_API_KEY"), streaming=True)
+
+prompt = PromptTemplate.from_template("""
+You are a friendly but professional insurance assistant.
+
+Write a short, conversational explanation of the premium. 
+Keep it human, warm, and simple — avoid sounding like a report or policy document.
+
+Response Format:
+1) One-line casual greeting.
+2) State the premium clearly.
+3) A short, natural explanation (2–4 sentences max) of why the cost is what it is, based on the user's data. Mention only the most meaningful factors, not a full list.
+4) Give 1–2 helpful suggestions (upgrade recommendation, lifestyle tip, or policy fit).
+5) End with a short invitation to continue with the chatbot, like know more about healthcare insourence planes and their cost
+
+Tone rules:
+- No long paragraphs.
+- No medical diagnosis or guarantees.
+- Avoid corporate insurance jargon.
+- Keep under 10 total sentences.
+
+User + Model Data:
+yearly_premium: ₹{yearly_premium}
+monthly_premium : ₹{monthly_premium} 
+Age: {age}, Gender: {gender}, Marital Status: {marital_status}, Dependents: {dependents}
+BMI: {bmi_category}, Smoking: {smoking_status}, Medical History: {medical_history}, Genetics: Risk {genetic_risk}
+Region: {region}, Income: {income_lakhs} lakhs, Employment: {employment_status}, Plan: {insurance_plan}
+
+Now generate the response.
+
+
+""")
+
+def generate_advice(yearly_premium, monthly_premium, age, gender, marital_status, dependents, bmi_category, smoking_status,
+                    medical_history, genetic_risk, region, income_lakhs, employment_status, insurance_plan):
+    formatted_prompt = prompt.format(
+        yearly_premium=yearly_premium,
+        monthly_premium=monthly_premium,
+        age=age,
+        gender=gender,
+        marital_status=marital_status,
+        dependents=dependents,
+        bmi_category=bmi_category,
+        smoking_status=smoking_status,
+        medical_history=medical_history,
+        genetic_risk=genetic_risk,
+        region=region,
+        income_lakhs=income_lakhs,
+        employment_status=employment_status,
+        insurance_plan=insurance_plan
+        )
+
+    result = llm.invoke(formatted_prompt)
+    return result.content
+
+"""print(generate_advice(
+    predicted_premium=7621,
+    age=30,
+    gender="Male",
+    marital_status="Unmarried",
+    dependents=2,
+    bmi_category="Normal",
+    smoking_status="No Smoking",
+    medical_history="No Disease",
+    genetic_risk=3,
+    region="Northwest",
+    income_lakhs=10,
+    employment_status="Salaried",
+    insurance_plan="Bronze"))"""

prediction_helper.py

@@ -0,0 +1,110 @@
+import pandas as pd
+import joblib
+
+model_young = joblib.load("artifacts/model_young.joblib")
+model_rest = joblib.load("artifacts/model_rest.joblib")
+scaler_young = joblib.load("artifacts/scaler_young.joblib")
+scaler_rest = joblib.load("artifacts/scaler_rest.joblib")
+
+def calculate_normalized_risk(medical_history):
+    risk_scores = {
+        "diabetes": 6,
+        "heart disease": 8,
+        "high blood pressure": 6,
+        "thyroid": 5,
+        "no disease": 0,
+        "none": 0
+    }
+    diseases = medical_history.lower().split(" & ")
+    total_risk_score = sum(risk_scores.get(disease, 0) for disease in diseases)  
+
+    max_score = 14 
+    min_score = 0 
+    normalized_risk_score = (total_risk_score - min_score) / (max_score - min_score)
+    return normalized_risk_score
+def preprocess_input(input_dict):
+
+    expected_columns = [
+        'age', 'number_of_dependants', 'income_lakhs', 'insurance_plan', 'genetical_risk', 'normalized_risk_score',
+        'gender_Male', 'region_Northwest', 'region_Southeast', 'region_Southwest', 'marital_status_Unmarried',
+        'bmi_category_Obesity', 'bmi_category_Overweight', 'bmi_category_Underweight', 'smoking_status_Occasional',
+        'smoking_status_Regular', 'employment_status_Salaried', 'employment_status_Self-Employed'
+    ]
+
+    insurance_plan_encoding = {'Bronze': 1, 'Silver': 2, 'Gold': 3}
+
+    df = pd.DataFrame(0, columns=expected_columns, index=[0])
+
+
+    for key, value in input_dict.items():
+        if key == 'Gender' and value == 'Male':
+            df['gender_Male'] = 1
+        elif key == 'Region':
+            if value == 'Northwest':
+                df['region_Northwest'] = 1
+            elif value == 'Southeast':
+                df['region_Southeast'] = 1
+            elif value == 'Southwest':
+                df['region_Southwest'] = 1
+        elif key == 'Marital Status' and value == 'Unmarried':
+            df['marital_status_Unmarried'] = 1
+        elif key == 'BMI Category':
+            if value == 'Obesity':
+                df['bmi_category_Obesity'] = 1
+            elif value == 'Overweight':
+                df['bmi_category_Overweight'] = 1
+            elif value == 'Underweight':
+                df['bmi_category_Underweight'] = 1
+        elif key == 'Smoking Status':
+            if value == 'Occasional':
+                df['smoking_status_Occasional'] = 1
+            elif value == 'Regular':
+                df['smoking_status_Regular'] = 1
+        elif key == 'Employment Status':
+            if value == 'Salaried':
+                df['employment_status_Salaried'] = 1
+            elif value == 'Self-Employed':
+                df['employment_status_Self-Employed'] = 1
+        elif key == 'Insurance Plan':  
+            df['insurance_plan'] = insurance_plan_encoding.get(value, 1)
+        elif key == 'Age': 
+            df['age'] = value
+        elif key == 'Number of Dependants': 
+            df['number_of_dependants'] = value
+        elif key == 'Income in Lakhs': 
+            df['income_lakhs'] = value
+        elif key == "Genetical Risk":
+            df['genetical_risk'] = value
+
+   
+    df['normalized_risk_score'] = calculate_normalized_risk(input_dict['Medical History'])
+    df = handle_scaling(input_dict['Age'], df)
+
+    return df
+
+def handle_scaling(age, df):
+   
+    if age <= 25:
+        scaler_object = scaler_young
+    else:
+        scaler_object = scaler_rest
+
+    cols_to_scale = scaler_object['cols_to_scale']
+    scaler = scaler_object['scaler']
+
+    df['income_level'] = None 
+    df[cols_to_scale] = scaler.transform(df[cols_to_scale])
+
+    df.drop('income_level', axis='columns', inplace=True)
+
+    return df
+
+def predict(input_dict):
+    input_df = preprocess_input(input_dict)
+
+    if input_dict['Age'] <= 25:
+        prediction = model_young.predict(input_df)
+    else:
+        prediction = model_rest.predict(input_df)
+
+    return int(prediction[0])

requirements.txt

@@ -0,0 +1,14 @@
+joblib==1.3.2
+pandas==2.0.2
+streamlit==1.22.0
+numpy==1.25.0
+scikit-learn==1.3.0
+xgboost==2.0.3
+fastapi
+uvicorn
+pydantic
+langchain
+langchain-community
+langchain-groq
+langgraph
+