I like this Ui now, add all these functionlaities to it

You are an expert full-stack engineer tasked with building an AI-Powered Rental Property Analysis Tool. The system will have a Next.js (React) frontend and a Node.js backend (with Express). Please follow these instructions and code structure requirements in your output:

============================================================

1. PROJECT OVERVIEW ============================================================

• We want a web application that allows users to input rental property details (address, price, interest rate, loan duration, estimated expenses, etc.) and receive:

  • Financial insights (e.g., monthly cash flow, ROI, cap rate).
  • Predictive analytics (e.g., estimated rent, property appreciation, market trends).
  • Textual market insights generated by a GenAI model.

• The application architecture includes:

  • Frontend: Next.js + React, using Chart.js or D3.js for visualizations, TailwindCSS or Material-UI for styling.
  • Backend: Node.js + Express, Redis for caching, and a relational database (e.g., PostgreSQL) to store data.
  • Data Pipeline (ETL): Uses external APIs (Zillow, Redfin, etc.) and an Airflow-based data pipeline or simple scheduling for regular updates.
  • Model Training & Inference: XGBoost or Scikit-learn for predictive models; an optional large language model (like GPT) for generating insights.
  • CI/CD: Automated deployments using Docker, GitHub Actions, or AWS services.

============================================================ 2. REPOSITORY STRUCTURE AND FILE ORGANIZATION

Please generate code stubs and file structures for both the frontend and backend. The structure should look like this:

my-rental-app/ ├── README.md ├── .gitignore ├── frontend/ │ ├── package.json │ ├── next.config.js │ ├── pages/ │ │ ├── index.js │ │ ├── analyze.js │ │ └── api/ │ ├── components/ │ │ ├── Layout.js │ │ ├── PropertyForm.js │ │ └── ... (other reusable components) │ ├── styles/ │ │ └── globals.css │ ├── public/ │ └── ... ├── backend/ │ ├── package.json │ ├── src/ │ │ ├── index.js │ │ ├── config/ │ │ │ ├── db.js │ │ │ └── redis.js │ │ ├── routes/ │ │ │ ├── analysisRoutes.js │ │ │ ├── insightsRoutes.js │ │ │ └── predictionRoutes.js │ │ ├── controllers/ │ │ │ ├── analysisController.js │ │ │ ├── insightsController.js │ │ │ └── predictionController.js │ │ ├── models/ │ │ │ └── Property.js │ │ └── ... │ └── ... ├── docker-compose.yml ├── Dockerfile-frontend ├── Dockerfile-backend └── ...

============================================================ 3. FRONTEND REQUIREMENTS

3.1 Technology Stack

• Next.js for SSR and routing.
• React for interactive components.
• TailwindCSS or Material-UI for quick UI styling.
• Chart.js or D3.js for financial data visualizations.

3.2 Features

1. Home Page (/):

   • A brief overview of the tool with a call-to-action to analyze a property.
   • Possibly some marketing content about the benefits.

2. Analyze Page (/analyze):

   • PropertyForm component for user input (purchase price, down payment, mortgage rate, property tax, insurance, etc.).
   • Submit Button to trigger an API call to the backend.
   • Results Section:
     • Monthly cash flow, ROI, cap rate.
     • Predicted rent and property appreciation (retrieved from backend).
     • Graphs showing cash flow over time, potential long-term ROI, etc.

3. Insights (Optional Page or Modal):

   • Displays text-based market insights generated by the GenAI model (e.g., “This neighborhood has a strong rental demand...”).

4. Global Components:

   • Layout: Nav bar, footer, consistent styling.
   • Loader/Spinner: Indicate when analysis is running.

5. Design Requirements:

   • Responsive layout (mobile, tablet, desktop).
   • Consistent color scheme.
   • Accessible form elements (labels, placeholders, error messages).

3.3 Example Code Requirements

• In pages/analyze.js, create the form elements.
• In components/PropertyForm.js, handle form state and validations.
• Use fetch or Axios to call the backend (/api/analyze) and render results.
• Include skeleton or placeholder states while fetching data.
• Provide minimal CSS examples or Tailwind class usage.

============================================================ 4. BACKEND REQUIREMENTS

4.1 Technology Stack

• Node.js + Express for building RESTful APIs.
• Redis for caching frequent queries (e.g., repeated property analysis in the same region).
• PostgreSQL (or MySQL) to store property data and user inputs. Use an ORM like Sequelize or Prisma.

4.2 Core API Endpoints

1. POST /api/analyze

   • Purpose: Calculate cash flow, ROI, cap rate.
   • Request: JSON body with property details (price, interest rate, annual taxes, etc.).
   • Response: JSON with monthly cash flow, ROI, breakdown of monthly expenses.

2. POST /api/predict

   • Purpose: Predict monthly rent and property appreciation using ML model.
   • Request: JSON with property features.
   • Response: JSON with predicted rent, annual appreciation rate, confidence intervals.

3. GET /api/insights

   • Purpose: Return AI-generated textual insights about the property or market.
   • Response: JSON with a string containing the generated insight.

4.3 Database Schema (Example)

• Property Table:
  • id (primary key)
  • address (string)
  • city (string)
  • state (string)
  • zip (string)
  • purchasePrice (float)
  • ... (other relevant columns)

4.4 Caching Logic

• For repeated queries in the same location, store results in Redis for quick retrieval.
• Implement a simple caching middleware in Express (e.g., cache.js) that checks Redis before hitting the controllers.

4.5 Example Code Requirements

• index.js: Set up the Express app, connect to database, configure Redis, mount routes.
• analysisRoutes.js & analysisController.js: Business logic for computing cash flow and ROI.
• predictionRoutes.js & predictionController.js: Integrate or stub ML predictions (real or mock).
• insightsRoutes.js & insightsController.js: Return either static or GPT-generated market insights.

============================================================ 5. DATA PIPELINE & MODEL INTEGRATION (STUBS)

• ETL: (Not fully coded, but provide stubs or placeholders for how we’d pull data from Zillow/Redfin).
• Model:
  • Provide a placeholder function (e.g., predictRent(propertyDetails)) in predictionController.js.
  • Optionally show how we’d call a Hugging Face or OpenAI API for text-based insights.

============================================================ 6. CI/CD AND DEPLOYMENT

• Dockerfiles for both frontend and backend:
  • Dockerfile-frontend: Next.js build steps.
  • Dockerfile-backend: Node.js + Express setup, plus Redis in docker-compose if needed.
• docker-compose.yml:
  • Orchestrates the containers (frontend, backend, Redis, and possibly PostgreSQL).
• GitHub Actions:
  • Basic YAML config for continuous integration (e.g., run linter, run tests, build Docker images).
• Provide minimal or commented placeholders if a full pipeline is out of scope.

============================================================ 7. OTHER REQUIREMENTS

• Testing: Basic unit tests for both frontend (React Testing Library/Jest) and backend (Jest/Supertest).
• Documentation: Provide a short README for each major folder (frontend and backend) explaining setup and running instructions.

============================================================ 8. OUTPUT FORMAT

• Please return your answer in the form of a well-organized code base outline, including (where possible) sample code snippets or placeholders.
• Use triple backticks ``` to separate code blocks for clarity.
• Write any additional notes, setup steps, or environment variable instructions (e.g., .env usage).

============================================================ 9. FINAL REQUEST

Generate all necessary files for a working minimal MVP of the AI-Powered Rental Property Analysis Tool, including:

• Sample Next.js pages
• Minimal Express APIs
• A mocked or placeholder predictive model call
• Redis-based caching logic
• Docker artifacts (Dockerfiles, docker-compose)
• Basic testing stubs
• Documentation comments

Ensure that the code is clean, follows best practices, and is ready to be extended with real ETL and ML code later.