Implementing AI Assistants with Python

---
description: Guidelines for developing AI-powered virtual assistants using Python, focusing on natural language processing and user interaction.
globs: ["**/*.py"]
tags: [python, ai, virtual-assistant, nlp, user-interaction]
priority: 1
version: 1.0.0
---

# Implementing AI Assistants with Python

## Context
- Applicable when developing AI-powered virtual assistants in Python.
- Focuses on natural language processing (NLP) and user interaction components.

## Requirements

- **Code Structure and Organization**
  - Follow a modular and organized file structure.
  - Separate templates into reusable components.
  - Divide logic into small, reusable modules and use ES6+ syntax.
  - Follow PEP 8 standards and divide large scripts into smaller functions/classes.

- **Coding Standards**
  - Use Python with strict types for each variable.
  - Write down types of function results like `-> ...`.
  - Use Pydantic models for data structures instead of TypedDict or other solutions.
  - Try to avoid type `Any`.
  - Do not use `@staticmethod`.
  - Always prefer functional programming over OOP when possible.

- **Style Guidelines**
  - Use 4 spaces for indentation.
  - Follow PEP 8 naming conventions:
    - Module names: all lowercase, separate words with underscores if necessary.
    - Variable and function names: lowercase words separated by underscores.
    - Class names: CapWords convention.

- **Best Practices**
  - Write clear, optimized code that balances efficiency with readability.
  - Break functionality into self-contained, reusable components.
  - Implement multiple testing levels including unit, integration, and end-to-end tests.
  - Implement security best practices.
  - Write self-documenting code with clear comments.
  - Optimize for performance and resource usage.
  - Include robust error handling and logging.
  - Support CI/CD practices.
  - Design for scalability.
  - Follow API design best practices when applicable.

- **Documentation**
  - Use JSDoc comments for all functions and components.
  - Keep README.md up-to-date with project setup and contribution guidelines.

## Examples

# Good example: Using Pydantic for data validation
from pydantic import BaseModel

class UserInput(BaseModel):
    name: str
    age: int
    email: str

def process_input(user_input: UserInput) -> str:
    return f"Processing input for {user_input.name}"
# Bad example: Using untyped dictionaries
def process_input(user_input: dict) -> str:
    return f"Processing input for {user_input['name']}"