Integrate OpenAI recommendations

HUGGINGFACE_DEPLOYMENT.md

@@ -20,15 +20,17 @@ This guide will help you deploy the Smart Budget Recommendation API to Hugging F
    - **Visibility**: Choose Public or Private
 4. Click "Create Space"
 
-### Step 2: Add MongoDB URI as Secret
+### Step 2: Add secrets (MongoDB and optional OpenAI)
 
 1. In your Space, go to **Settings** (gear icon)
 2. Navigate to **Variables and secrets** section
 3. Click **New secret**
-4. Add:
+4. Add the following secrets:
    - **Name**: `MONGODB_URI`
-   - **Value**: `mongodb://expenseuser:Kem_6o%3F%[email protected]:27017/expense?authSource=admin`
-5. Click **Add secret**
+     - **Value**: `mongodb://expenseuser:Kem_6o%3F%[email protected]:27017/expense?authSource=admin`
+   - **Name**: `OPENAI_API_KEY` *(optional, enables GPT-based recommendations)*
+     - **Value**: `sk-...`
+5. Click **Add secret** after each entry
 
 ### Step 3: Upload Files
 
@@ -110,9 +112,9 @@ print(response.json())
 
 ## Important Notes
 
-1. **Port Configuration**: Hugging Face automatically maps port 8000, so your Dockerfile should expose port 8000 (which it does)
+1. **Port Configuration**: Hugging Face Spaces expect apps to serve on port **7860**, so the Dockerfile exposes and binds to that port.
 
-2. **Environment Variables**: The `MONGODB_URI` secret will be automatically available as an environment variable in your container
+2. **Environment Variables**: Secrets such as `MONGODB_URI` (and optional `OPENAI_API_KEY`) are injected automatically into the container environment.
 
 3. **Cold Starts**: The first request after inactivity may take longer (cold start). Subsequent requests will be faster
 

README.md

@@ -52,9 +52,11 @@ A FastAPI-based service that provides intelligent budget recommendations based o
 pip install -r requirements.txt
 ```
 
-2. Set environment variable:
+2. Set environment variables:
 ```bash
 export MONGODB_URI="mongodb://expenseuser:Kem_6o%3F%[email protected]:27017/expense?authSource=admin"
+# optional
+export OPENAI_API_KEY="your_openai_key"
 ```
 
 3. Run the application:
@@ -73,7 +75,7 @@ docker build -t smart-budget-recommendation .
 
 ### Run Docker Container
 ```bash
-docker run -p 8000:8000 -e MONGODB_URI="your_mongodb_uri" smart-budget-recommendation
+docker run -p 7860:7860 -e MONGODB_URI="your_mongodb_uri" smart-budget-recommendation
 ```
 
 ## Hugging Face Deployment
@@ -85,10 +87,11 @@ docker run -p 8000:8000 -e MONGODB_URI="your_mongodb_uri" smart-budget-recommend
 
 ### Steps
 
-1. **Store MongoDB URI as Secret in Hugging Face**:
+1. **Store secrets in Hugging Face**:
    - Go to your Hugging Face Space settings
    - Navigate to "Variables and secrets"
-   - Add a new secret named `MONGODB_URI` with your MongoDB connection string
+   - Add `MONGODB_URI` with your MongoDB connection string
+   - *(Optional)* Add `OPENAI_API_KEY` if you want GPT-powered recommendations
 
 2. **Create Hugging Face Space**:
    - Create a new Space on Hugging Face
@@ -107,7 +110,7 @@ docker run -p 8000:8000 -e MONGODB_URI="your_mongodb_uri" smart-budget-recommend
 The Dockerfile is configured to:
 - Use Python 3.11
 - Install all dependencies
-- Expose port 8000
+- Expose port 7860 (Hugging Face default)
 - Run the FastAPI application with Uvicorn
 
 Hugging Face will automatically:
@@ -139,10 +142,13 @@ The Smart Budget Recommendation engine:
 4. **Confidence Scoring**: 
    - Based on data quality (months analyzed, transaction count, consistency)
    - Returns score from 0-1
+5. **(Optional) GPT Refinement**:
+   - If `OPENAI_API_KEY` is set, GPT reviews the history and suggests increase/decrease/keep along with a natural-language reason.
 
 ## Environment Variables
 
 - `MONGODB_URI`: MongoDB connection string (required)
+- `OPENAI_API_KEY`: Optional. If set, GPT-based recommendations augment the rule-based engine.
 
 ## License
 

Smart_Budget_Recommendation_API.postman_collection.json

@@ -0,0 +1,384 @@
+{
+	"info": {
+		"_postman_id": "smart-budget-recommendation-api",
+		"name": "Smart Budget Recommendation API",
+		"description": "API collection for Smart Budget Recommendation service deployed on Hugging Face",
+		"schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json"
+	},
+	"item": [
+		{
+			"name": "Health Check",
+			"request": {
+				"method": "GET",
+				"header": [],
+				"url": {
+					"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/health",
+					"protocol": "https",
+					"host": [
+						"logicgoinfotechspaces-smart-budget-recommendation",
+						"hf",
+						"space"
+					],
+					"path": [
+						"health"
+					]
+				},
+				"description": "Check if the API and database are running"
+			}
+		},
+		{
+			"name": "Root Endpoint",
+			"request": {
+				"method": "GET",
+				"header": [],
+				"url": {
+					"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/",
+					"protocol": "https",
+					"host": [
+						"logicgoinfotechspaces-smart-budget-recommendation",
+						"hf",
+						"space"
+					],
+					"path": [
+						""
+					]
+				}
+			}
+		},
+		{
+			"name": "Create Expense",
+			"request": {
+				"method": "POST",
+				"header": [
+					{
+						"key": "Content-Type",
+						"value": "application/json"
+					}
+				],
+				"body": {
+					"mode": "raw",
+					"raw": "{\n    \"user_id\": \"68a834c3f4694b11efedacd2\",\n    \"amount\": 3800,\n    \"category\": \"Groceries\",\n    \"description\": \"Monthly groceries\",\n    \"date\": \"2025-01-15T00:00:00\",\n    \"type\": \"expense\"\n}"
+				},
+				"url": {
+					"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/expenses",
+					"protocol": "https",
+					"host": [
+						"logicgoinfotechspaces-smart-budget-recommendation",
+						"hf",
+						"space"
+					],
+					"path": [
+						"expenses"
+					]
+				},
+				"description": "Create a new expense record"
+			}
+		},
+		{
+			"name": "Get Expenses",
+			"request": {
+				"method": "GET",
+				"header": [],
+				"url": {
+					"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/expenses?user_id=68a834c3f4694b11efedacd2&limit=20",
+					"protocol": "https",
+					"host": [
+						"logicgoinfotechspaces-smart-budget-recommendation",
+						"hf",
+						"space"
+					],
+					"path": [
+						"expenses"
+					],
+					"query": [
+						{
+							"key": "user_id",
+							"value": "68a834c3f4694b11efedacd2",
+							"description": "User identifier"
+						},
+						{
+							"key": "limit",
+							"value": "20",
+							"description": "Maximum number of expenses to return"
+						}
+					]
+				},
+				"description": "Get expenses for a specific user"
+			}
+		},
+		{
+			"name": "Create Budget",
+			"request": {
+				"method": "POST",
+				"header": [
+					{
+						"key": "Content-Type",
+						"value": "application/json"
+					}
+				],
+				"body": {
+					"mode": "raw",
+					"raw": "{\n    \"user_id\": \"68a834c3f4694b11efedacd2\",\n    \"category\": \"Groceries\",\n    \"amount\": 4000,\n    \"period\": \"monthly\",\n    \"start_date\": \"2025-02-01T00:00:00\",\n    \"end_date\": \"2025-02-29T00:00:00\"\n}"
+				},
+				"url": {
+					"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/budgets",
+					"protocol": "https",
+					"host": [
+						"logicgoinfotechspaces-smart-budget-recommendation",
+						"hf",
+						"space"
+					],
+					"path": [
+						"budgets"
+					]
+				},
+				"description": "Create a new budget"
+			}
+		},
+		{
+			"name": "Get Budgets",
+			"request": {
+				"method": "GET",
+				"header": [],
+				"url": {
+					"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/budgets?user_id=68a834c3f4694b11efedacd2",
+					"protocol": "https",
+					"host": [
+						"logicgoinfotechspaces-smart-budget-recommendation",
+						"hf",
+						"space"
+					],
+					"path": [
+						"budgets"
+					],
+					"query": [
+						{
+							"key": "user_id",
+							"value": "68a834c3f4694b11efedacd2"
+						}
+					]
+				},
+				"description": "Get budgets for a specific user"
+			}
+		},
+		{
+			"name": "Get Smart Budget Recommendations",
+			"request": {
+				"method": "GET",
+				"header": [],
+				"url": {
+					"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/recommendations/68a834c3f4694b11efedacd2?month=2&year=2025",
+					"protocol": "https",
+					"host": [
+						"logicgoinfotechspaces-smart-budget-recommendation",
+						"hf",
+						"space"
+					],
+					"path": [
+						"recommendations",
+						"68a834c3f4694b11efedacd2"
+					],
+					"query": [
+						{
+							"key": "month",
+							"value": "2",
+							"description": "Target month (1-12), optional - defaults to next month"
+						},
+						{
+							"key": "year",
+							"value": "2025",
+							"description": "Target year, optional - defaults to next year"
+						}
+					]
+				},
+				"description": "Get smart budget recommendations based on past spending behavior. Requires at least 2-3 months of expense data."
+			}
+		},
+		{
+			"name": "Get Category Expenses",
+			"request": {
+				"method": "GET",
+				"header": [],
+				"url": {
+					"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/category-expenses/68a834c3f4694b11efedacd2?months=3",
+					"protocol": "https",
+					"host": [
+						"logicgoinfotechspaces-smart-budget-recommendation",
+						"hf",
+						"space"
+					],
+					"path": [
+						"category-expenses",
+						"68a834c3f4694b11efedacd2"
+					],
+					"query": [
+						{
+							"key": "months",
+							"value": "3",
+							"description": "Number of months to analyze (default: 3)"
+						}
+					]
+				},
+				"description": "Get average expenses by category for the past N months"
+			}
+		},
+		{
+			"name": "Sample Expenses - Create Multiple",
+			"item": [
+				{
+					"name": "Groceries - Month 1 (Sept 2024)",
+					"request": {
+						"method": "POST",
+						"header": [
+							{
+								"key": "Content-Type",
+								"value": "application/json"
+							}
+						],
+						"body": {
+							"mode": "raw",
+							"raw": "{\n    \"user_id\": \"68a834c3f4694b11efedacd2\",\n    \"amount\": 3500,\n    \"category\": \"Groceries\",\n    \"description\": \"Monthly groceries - September 2024\",\n    \"date\": \"2024-09-15T00:00:00\",\n    \"type\": \"expense\"\n}"
+						},
+						"url": {
+							"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/expenses",
+							"protocol": "https",
+							"host": [
+								"logicgoinfotechspaces-smart-budget-recommendation",
+								"hf",
+								"space"
+							],
+							"path": [
+								"expenses"
+							]
+						}
+					}
+				},
+				{
+					"name": "Groceries - Month 2 (Oct 2024)",
+					"request": {
+						"method": "POST",
+						"header": [
+							{
+								"key": "Content-Type",
+								"value": "application/json"
+							}
+						],
+						"body": {
+							"mode": "raw",
+							"raw": "{\n    \"user_id\": \"68a834c3f4694b11efedacd2\",\n    \"amount\": 3800,\n    \"category\": \"Groceries\",\n    \"description\": \"Monthly groceries - October 2024\",\n    \"date\": \"2024-10-15T00:00:00\",\n    \"type\": \"expense\"\n}"
+						},
+						"url": {
+							"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/expenses",
+							"protocol": "https",
+							"host": [
+								"logicgoinfotechspaces-smart-budget-recommendation",
+								"hf",
+								"space"
+							],
+							"path": [
+								"expenses"
+							]
+						}
+					}
+				},
+				{
+					"name": "Groceries - Month 3 (Nov 2024)",
+					"request": {
+						"method": "POST",
+						"header": [
+							{
+								"key": "Content-Type",
+								"value": "application/json"
+							}
+						],
+						"body": {
+							"mode": "raw",
+							"raw": "{\n    \"user_id\": \"68a834c3f4694b11efedacd2\",\n    \"amount\": 4000,\n    \"category\": \"Groceries\",\n    \"description\": \"Monthly groceries - November 2024\",\n    \"date\": \"2024-11-15T00:00:00\",\n    \"type\": \"expense\"\n}"
+						},
+						"url": {
+							"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/expenses",
+							"protocol": "https",
+							"host": [
+								"logicgoinfotechspaces-smart-budget-recommendation",
+								"hf",
+								"space"
+							],
+							"path": [
+								"expenses"
+							]
+						}
+					}
+				},
+				{
+					"name": "Transport - Month 1 (Sept 2024)",
+					"request": {
+						"method": "POST",
+						"header": [
+							{
+								"key": "Content-Type",
+								"value": "application/json"
+							}
+						],
+						"body": {
+							"mode": "raw",
+							"raw": "{\n    \"user_id\": \"68a834c3f4694b11efedacd2\",\n    \"amount\": 2000,\n    \"category\": \"Transport\",\n    \"description\": \"Monthly transport - September 2024\",\n    \"date\": \"2024-09-20T00:00:00\",\n    \"type\": \"expense\"\n}"
+						},
+						"url": {
+							"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/expenses",
+							"protocol": "https",
+							"host": [
+								"logicgoinfotechspaces-smart-budget-recommendation",
+								"hf",
+								"space"
+							],
+							"path": [
+								"expenses"
+							]
+						}
+					}
+				},
+				{
+					"name": "Transport - Month 2 (Oct 2024)",
+					"request": {
+						"method": "POST",
+						"header": [
+							{
+								"key": "Content-Type",
+								"value": "application/json"
+							}
+						],
+						"body": {
+							"mode": "raw",
+							"raw": "{\n    \"user_id\": \"68a834c3f4694b11efedacd2\",\n    \"amount\": 2200,\n    \"category\": \"Transport\",\n    \"description\": \"Monthly transport - October 2024\",\n    \"date\": \"2024-10-20T00:00:00\",\n    \"type\": \"expense\"\n}"
+						},
+						"url": {
+							"raw": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space/expenses",
+							"protocol": "https",
+							"host": [
+								"logicgoinfotechspaces-smart-budget-recommendation",
+								"hf",
+								"space"
+							],
+							"path": [
+								"expenses"
+							]
+						}
+					}
+				}
+			]
+		}
+	],
+	"variable": [
+		{
+			"key": "base_url",
+			"value": "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space",
+			"type": "string"
+		},
+		{
+			"key": "user_id",
+			"value": "68a834c3f4694b11efedacd2",
+			"type": "string"
+		}
+	]
+}
+

app/models.py

@@ -29,6 +29,10 @@ class BudgetRecommendation(BaseModel):
     recommended_budget: float
     reason: str
     confidence: float = Field(..., ge=0, le=1, description="Confidence score (0-1)")
+    action: Optional[str] = Field(
+        None,
+        description="AI suggestion: increase, decrease, or keep"
+    )
 
 class CategoryExpense(BaseModel):
     category: str

app/smart_recommendation.py

@@ -1,8 +1,18 @@
-from datetime import datetime, timedelta
-from typing import List, Dict
+import json
+import math
+import os
 from collections import defaultdict
+from datetime import datetime, timedelta
+from typing import Dict, List
+
+from dotenv import load_dotenv
+from openai import OpenAI
+
 from app.models import BudgetRecommendation, CategoryExpense
-import math
+
+load_dotenv()
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+openai_client = OpenAI(api_key=OPENAI_API_KEY) if OPENAI_API_KEY else None
 
 class SmartBudgetRecommender:
     """
@@ -14,6 +24,7 @@ class SmartBudgetRecommender:
     
     def __init__(self, db):
         self.db = db
+        self.openai_client = openai_client
     
     def get_recommendations(self, user_id: str, month: int, year: int) -> List[BudgetRecommendation]:
         """
@@ -51,12 +62,21 @@ class SmartBudgetRecommender:
             
             reason = self._generate_reason(category, avg_expense, recommended_budget)
             
+            ai_result = self._get_ai_recommendation(category, data, avg_expense, recommended_budget)
+            if ai_result:
+                recommended_budget = ai_result.get("recommended_budget", recommended_budget)
+                reason = ai_result.get("reason", reason)
+                action = ai_result.get("action")
+            else:
+                action = None
+
             recommendations.append(BudgetRecommendation(
                 category=category,
                 average_expense=round(avg_expense, 2),
                 recommended_budget=round(recommended_budget, 2),
                 reason=reason,
-                confidence=confidence
+                confidence=confidence,
+                action=action
             ))
         
         # Sort by average expense (highest first)
@@ -216,3 +236,41 @@ class SmartBudgetRecommender:
         result.sort(key=lambda x: x.average_monthly_expense, reverse=True)
         return result
 
+    def _get_ai_recommendation(self, category: str, data: Dict, avg_expense: float, fallback_budget: float):
+        """Use OpenAI to refine the budget recommendation."""
+        if not self.openai_client:
+            return None
+
+        history = ", ".join(f"{value:.0f}" for value in data["monthly_values"])
+        summary = (
+            f"Category: {category}\n"
+            f"Monthly totals: [{history}]\n"
+            f"Average spend: {avg_expense:.2f}\n"
+            f"Std deviation: {data['std_dev']:.2f}\n"
+            f"Months observed: {data['months_analyzed']}\n"
+            f"Current suggested budget: {fallback_budget:.2f}\n"
+        )
+
+        prompt = (
+            "You are an Indian personal finance coach. "
+            "Given the user's spending history, decide whether to increase, decrease, "
+            "or keep the upcoming month's budget and provide a short explanation. "
+            "Respond strictly as JSON with the following keys:\n"
+            '{ "recommended_budget": number, "action": "increase|decrease|keep", "reason": "string" }.\n'
+            "Use rupees for all amounts.\n\n"
+            f"{summary}"
+        )
+
+        try:
+            response = self.openai_client.responses.create(
+                model="gpt-4.1-mini",
+                input=prompt,
+                temperature=0.1,
+                response_format={"type": "json_object"},
+            )
+            content = response.output[0].content[0].text
+            return json.loads(content)
+        except Exception as exc:
+            print(f"OpenAI recommendation error for {category}: {exc}")
+            return None
+

requirements.txt

@@ -3,4 +3,6 @@ uvicorn[standard]==0.24.0
 pymongo==4.6.0
 pydantic==2.5.0
 python-multipart==0.0.6
+openai==1.51.0
+python-dotenv==1.0.1
 

test_hf_api.py

@@ -0,0 +1,215 @@
+"""
+Test script for Hugging Face deployed API
+Creates sample expenses and tests recommendations
+"""
+
+import requests
+import json
+from datetime import datetime, timedelta
+
+BASE_URL = "https://logicgoinfotechspaces-smart-budget-recommendation.hf.space"
+USER_ID = "68a834c3f4694b11efedacd2"
+
+def test_health():
+    """Test health endpoint"""
+    print("=" * 60)
+    print("1. Testing Health Endpoint")
+    print("=" * 60)
+    try:
+        response = requests.get(f"{BASE_URL}/health")
+        print(f"Status: {response.status_code}")
+        print(f"Response: {json.dumps(response.json(), indent=2)}")
+        return response.status_code == 200
+    except Exception as e:
+        print(f"Error: {e}")
+        return False
+
+def create_sample_expenses():
+    """Create multiple sample expenses across different months"""
+    print("\n" + "=" * 60)
+    print("2. Creating Sample Expenses")
+    print("=" * 60)
+    
+    # Create expenses for the past 4 months
+    base_date = datetime(2024, 9, 15)  # Start from September 2024
+    expenses = []
+    
+    # Groceries - 4 months
+    for i in range(4):
+        date = base_date + timedelta(days=30 * i)
+        expenses.append({
+            "user_id": USER_ID,
+            "amount": 3500 + (i * 100),  # Varying amounts: 3500, 3600, 3700, 3800
+            "category": "Groceries",
+            "description": f"Monthly groceries - {date.strftime('%B %Y')}",
+            "date": date.isoformat(),
+            "type": "expense"
+        })
+    
+    # Transport - 3 months
+    for i in range(3):
+        date = base_date + timedelta(days=30 * i)
+        expenses.append({
+            "user_id": USER_ID,
+            "amount": 2000 + (i * 50),  # 2000, 2050, 2100
+            "category": "Transport",
+            "description": f"Monthly transport - {date.strftime('%B %Y')}",
+            "date": date.isoformat(),
+            "type": "expense"
+        })
+    
+    # Utilities - 2 months
+    for i in range(2):
+        date = base_date + timedelta(days=30 * i)
+        expenses.append({
+            "user_id": USER_ID,
+            "amount": 1500 + (i * 100),  # 1500, 1600
+            "category": "Utilities",
+            "description": f"Monthly utilities - {date.strftime('%B %Y')}",
+            "date": date.isoformat(),
+            "type": "expense"
+        })
+    
+    created_count = 0
+    for expense in expenses:
+        try:
+            response = requests.post(
+                f"{BASE_URL}/expenses",
+                json=expense,
+                headers={"Content-Type": "application/json"}
+            )
+            if response.status_code == 200:
+                print(f"[OK] Created: {expense['category']} - Rs.{expense['amount']} ({expense['date'][:10]})")
+                created_count += 1
+            else:
+                print(f"[FAIL] Failed: {expense['category']} - {response.text}")
+        except Exception as e:
+            print(f"[ERROR] Error creating expense: {e}")
+    
+    print(f"\nTotal expenses created: {created_count}/{len(expenses)}")
+    return created_count > 0
+
+def get_expenses():
+    """Get all expenses for the user"""
+    print("\n" + "=" * 60)
+    print("3. Getting All Expenses")
+    print("=" * 60)
+    try:
+        response = requests.get(
+            f"{BASE_URL}/expenses",
+            params={"user_id": USER_ID, "limit": 100}
+        )
+        if response.status_code == 200:
+            expenses = response.json()
+            print(f"Found {len(expenses)} expenses:\n")
+            for exp in expenses:
+                print(f"  - {exp['category']}: Rs.{exp['amount']} ({exp['date'][:10]})")
+            return True
+        else:
+            print(f"Error: {response.status_code} - {response.text}")
+            return False
+    except Exception as e:
+        print(f"Error: {e}")
+        return False
+
+def test_recommendations():
+    """Test getting budget recommendations"""
+    print("\n" + "=" * 60)
+    print("4. Testing Smart Budget Recommendations")
+    print("=" * 60)
+    try:
+        # Get recommendations for next month
+        next_month = datetime.now().month + 1
+        next_year = datetime.now().year
+        if next_month > 12:
+            next_month = 1
+            next_year += 1
+        
+        response = requests.get(
+            f"{BASE_URL}/recommendations/{USER_ID}",
+            params={"month": next_month, "year": next_year}
+        )
+        
+        if response.status_code == 200:
+            recommendations = response.json()
+            print(f"\nFound {len(recommendations)} recommendations:\n")
+            
+            if len(recommendations) == 0:
+                print("[WARNING] No recommendations yet. Need more expense data (at least 2-3 months).")
+            else:
+                for rec in recommendations:
+                    print(f"Category: {rec['category']}")
+                    print(f"  Average Expense: Rs.{rec['average_expense']:,.0f}")
+                    print(f"  Recommended Budget: Rs.{rec['recommended_budget']:,.0f}")
+                    print(f"  Confidence: {rec['confidence']*100:.0f}%")
+                    print(f"  Reason: {rec['reason']}")
+                    print()
+            return True
+        else:
+            print(f"Error: {response.status_code} - {response.text}")
+            return False
+    except Exception as e:
+        print(f"Error: {e}")
+        return False
+
+def test_category_expenses():
+    """Test getting category expense averages"""
+    print("\n" + "=" * 60)
+    print("5. Testing Category Expense Averages")
+    print("=" * 60)
+    try:
+        response = requests.get(
+            f"{BASE_URL}/category-expenses/{USER_ID}",
+            params={"months": 6}
+        )
+        
+        if response.status_code == 200:
+            categories = response.json()
+            print(f"\nFound {len(categories)} categories:\n")
+            
+            for cat in categories:
+                print(f"{cat['category']}:")
+                print(f"  Average Monthly: Rs.{cat['average_monthly_expense']:,.0f}")
+                print(f"  Total Transactions: {cat['total_expenses']}")
+                print(f"  Months Analyzed: {cat['months_analyzed']}")
+                print()
+            return True
+        else:
+            print(f"Error: {response.status_code} - {response.text}")
+            return False
+    except Exception as e:
+        print(f"Error: {e}")
+        return False
+
+if __name__ == "__main__":
+    print("\n" + "=" * 60)
+    print("Smart Budget Recommendation API - Hugging Face Test")
+    print("=" * 60)
+    print(f"\nBase URL: {BASE_URL}")
+    print(f"User ID: {USER_ID}\n")
+    
+    results = []
+    
+    # Run tests
+    results.append(("Health Check", test_health()))
+    results.append(("Create Expenses", create_sample_expenses()))
+    results.append(("Get Expenses", get_expenses()))
+    results.append(("Get Recommendations", test_recommendations()))
+    results.append(("Category Averages", test_category_expenses()))
+    
+    # Summary
+    print("\n" + "=" * 60)
+    print("Test Summary")
+    print("=" * 60)
+    for test_name, passed in results:
+        status = "[PASS]" if passed else "[FAIL]"
+        print(f"{status} - {test_name}")
+    
+    passed_count = sum(1 for _, passed in results if passed)
+    print(f"\nTotal: {passed_count}/{len(results)} tests passed")
+    
+    print("\n" + "=" * 60)
+    print("API Documentation:")
+    print(f"  Swagger UI: {BASE_URL}/docs")
+    print("=" * 60)
+