Real Python

The Real Python Podcast – Episode #296: Managing Polars Schema Issues & Profiling GitHub Users

2026-05-22T12:00:00+00:00

How can you avoid schema problems in your Polars data pipeline when adding new columns? How can you quickly examine a GitHub user's profile to decide how much to invest in their contributions? Christopher Trudeau is back on the show this week with another batch of PyCoder's Weekly articles and projects.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: Build a Tic-Tac-Toe Game With Python and Tkinter

2026-05-22T12:00:00+00:00

In this quiz, you’ll test your understanding of Build a Tic-Tac-Toe Game With Python and Tkinter.

By working through this quiz, you’ll revisit how to design game logic with Python classes, lay out and update Tkinter widgets, and wire up button clicks to a handler through the event loop.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: Context Managers and Using Python's with Statement

2026-05-21T12:00:00+00:00

In this quiz, you’ll test what you learned in the video course Context Managers and Using Python’s with Statement.

By working through this quiz, you’ll revisit how the with statement runs setup and teardown for you, how to use standard-library context managers like open(), and how to write your own context managers as classes or with the @contextmanager decorator.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

How to Use the Claude API in Python

2026-05-20T14:00:00+00:00

The fastest way to use the Claude API in Python is to install anthropic, set your API key, and call client.messages.create(). You’ll have a working response in under a minute:

Claude is Anthropic’s large language model, accessible via a clean REST API with an official Python SDK. Unlike heavier AI frameworks that require you to wire up multiple components before you see any output, the anthropic package gets you to a working response in a handful of lines.

In the following steps, you’ll install the anthropic SDK, call Claude from Python, shape Claude’s behavior with a system prompt, and then return structured JSON output using a schema or Pydantic.

Note: Claude’s responses are non-deterministic, so the same prompt produces different output each time, which is expected for a large language model. Also, API calls cost money based on the number of tokens processed. Keep an eye on your usage in the Claude Console as you follow along.

Each step builds on the last, and the final script is short enough to read in one sitting but complete enough to extend into a real application of your own.

Get Your Code: Click here to download the free sample code that shows you how to use the Claude API in Python.

Take the Quiz: Test your knowledge with our interactive “How to Use the Claude API in Python” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

How to Use the Claude API in Python

Test your understanding of using the Claude API in Python. Send prompts, set system instructions, and return structured JSON with a schema.

Prerequisites

Before diving in, make sure you have the following in place:

Python knowledge: You should be comfortable with Python basics, like defining functions, running scripts from the terminal, and working with virtual environments. If virtual environments are new to you, Python Virtual Environments: A Primer has you covered before you continue.
Python 3.9 or higher: The anthropic SDK requires Python 3.9 as a minimum. If you’re not sure which version you have, run python --version in your terminal. If you need to install or upgrade, follow the steps in the guide on installing Python.
An Anthropic account: You’ll need an Anthropic account to generate an API key in the Claude Console. Step 1 will show you how to find and secure your key once you’re in.

Don’t worry if you’ve never worked with an API before. This tutorial will walk you through authentication and help you make your first request from scratch.

Step 1: Set Up the Claude API in Python

Before you can call Claude from Python, you need an API key and the anthropic package installed. By the end of this step, you’ll have both, and Claude will be responding to your first prompt.

Get Your API Key and Install `anthropic`

Log in to the Claude Console or create a new account. If you’re starting fresh, you can begin using the API after adding $5 of credits.

Then navigate to the API Keys section. Click Create Key, give it a descriptive name like real-python-tutorial, and copy it immediately. You won’t see it again after you close the dialog.

Note: Never paste your API key directly into your code. Instead, store it as an environment variable. The anthropic SDK automatically reads it from ANTHROPIC_API_KEY at runtime, so you never need to reference it explicitly in your scripts.

Storing your key as an environment variable means it never touches your source code or version control history. The exact command depends on your operating system:

PS> $env:ANTHROPIC_API_KEY="your-api-key-here"

$ export ANTHROPIC_API_KEY="your-api-key-here"

With your API key stored safely, you’re ready to install the SDK. Create a fresh virtual environment and activate it before installing anything. This isolation prevents the anthropic package from conflicting with your system-level tools.

PS> python -m venv venv
PS> venv\Scripts\activate
(venv) PS> python -m pip install anthropic

$ python -m venv venv/
$ source venv/bin/activate
(venv) $ python -m pip install anthropic

Send Your First Prompt

Read the full article at https://realpython.com/claude-api-python/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: How to Use the Claude API in Python

2026-05-20T12:00:00+00:00

In this quiz, you’ll test your knowledge of How to Use the Claude API in Python.

By working through this quiz, you’ll revisit how to install the anthropic SDK, send prompts to Claude with client.messages.create(), shape responses with a system parameter, and return structured JSON output using a schema or Pydantic.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Tapping Into the Zen of Python

2026-05-19T14:00:00+00:00

The Zen of Python is a collection of 19 aphorisms that capture the guiding principles behind Python’s design. You can display them anytime by running import this in a Python REPL. Tim Peters wrote them in 1999 as a joke, but they became an iconic part of Python culture that was even formalized as PEP 20.

By the end of this video course, you’ll understand:

The Zen of Python is a humorous poem of 19 aphorisms describing Python’s design philosophy
Running import this in a Python interpreter displays the complete text of the Zen of Python
Tim Peters wrote the Zen of Python in 1999 as a tongue-in-cheek comment on a mailing list
The aphorisms are guidelines, not strict rules, and some intentionally contradict each other
The principles promote readability, simplicity, and explicitness while acknowledging that practicality matters

Experienced Pythonistas often refer to the Zen of Python as a source of wisdom and guidance, especially when they want to settle an argument about certain design decisions in a piece of code. In this video course, you’ll explore the origins of the Zen of Python, learn how to interpret its mysterious aphorisms, and discover the Easter eggs hidden within it.

You don’t need to be a Python master to understand the Zen of Python! But you do need to answer an important question: What exactly is the Zen of Python?

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: Tapping Into the Zen of Python

2026-05-19T12:00:00+00:00

In this quiz, you’ll test your understanding of Tapping Into the Zen of Python.

By working through this quiz, you’ll revisit the origins of the poem, the meaning of several aphorisms, and the inside jokes hidden throughout.

The questions explore how the principles apply in practice and when it’s okay to bend the rules in the name of practicality.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: Absolute vs Relative Imports in Python

2026-05-19T12:00:00+00:00

In this quiz, you’ll test your understanding of Absolute vs Relative Imports in Python.

By working through this quiz, you’ll revisit how Python’s import system resolves modules, the differences between absolute and relative imports, and the PEP 8 conventions for styling import statements.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Python Built-in Functions: A Complete Guide

2026-05-18T14:00:00+00:00

Python’s built-in functions are predefined functions you can use anywhere in your code without any imports. They handle common tasks across math, data type creation, iterable processing, and input and output. Knowing which ones to reach for makes your code shorter and more Pythonic.

In this tutorial, you’ll:

Recognize Python’s built-in functions and the built-in scope they live in
Use the right built-in for math, data types, iterables, and I/O tasks
Tell apart true functions and classes that look like functions
Apply built-ins to solve practical problems without reinventing the wheel

To get the most out of this tutorial, you’ll need to be familiar with Python programming, including topics like working with built-in data types, functions, classes, decorators, scopes, and the import system.

Get Your Code: Click here to download the free sample code that shows you how to use Python’s built-in functions.

Get the PDF Guide: Click here to download a free PDF guide that gives you a complete overview of Python’s built-in functions and how to use them.

Take the Quiz: Test your knowledge with our interactive “Python Built-in Functions: A Complete Guide” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

Python Built-in Functions: A Complete Guide

Test your understanding of Python's built-in functions for math, data types, iterables, and I/O—and when to reach for each one.

Built-in Functions in Python

Python has several functions available for you to use directly from anywhere in your code. These functions are known as built-in functions and they cover many common programming problems, from mathematical computations to Python-specific features.

Note: All these functions live in the builtins module, which Python loads at startup and exposes through the built-in scope, so you can use them anywhere without importing the module. Importing the module explicitly is useful if you know that you’ll shadow a built-in name with one of your own variables or functions. Doing so keeps the original within reach as builtins.name.

Among these built-ins, you’ll also find classes with function-style names like str, tuple, list, and dict, which define built-in data types. These classes are listed in the Python documentation as built-in functions, so they’re covered in this tutorial too.

In this tutorial, you’ll learn the basics of Python’s built-in functions. By the end, you’ll know what their use cases are and how they work. You’ll start with the built-in functions for math computations.

In Python, you’ll find a few built-in functions that take care of common math operations, like computing the absolute value of a number, calculating powers, and more. Here’s a summary of the math-related built-in functions in Python:

Function	Description
`abs()`	Calculates the absolute value of a number
`divmod()`	Computes the quotient and remainder of integer division
`max()`	Finds the largest of the given arguments or items in an iterable
`min()`	Finds the smallest of the given arguments or items in an iterable
`pow()`	Raises a number to a power
`round()`	Rounds a floating-point value
`sum()`	Sums the values in an iterable

In the following sections, you’ll learn how these functions work and how to use them in your Python code.

Getting the Absolute Value of a Number: `abs()`

The absolute value or modulus of a real number is its non-negative value. In other words, the absolute value is the number without its sign. For example, the absolute value of -5 is 5, and the absolute value of 5 is also 5.

Note: To learn more about abs(), check out the How to Find an Absolute Value in Python tutorial.

Python’s built-in abs() function allows you to quickly compute the absolute value of a number. Here’s its signature:

abs(number)

The number argument can be any numeric value, including integers, floating-point numbers, complex numbers, fractions, and decimals. Take a look at a few examples:

>>> from decimal import Decimal
>>> from fractions import Fraction

>>> abs(-42)
42
>>> abs(42)
42

>>> abs(-42.42)
42.42
>>> abs(42.42)
42.42

>>> abs(complex("-2+3j"))
3.605551275463989
>>> abs(complex("2+3j"))
3.605551275463989

>>> abs(Fraction("-1/2"))
Fraction(1, 2)
>>> abs(Fraction("1/2"))
Fraction(1, 2)

>>> abs(Decimal("-0.5"))
Decimal('0.5')
>>> abs(Decimal("0.5"))
Decimal('0.5')

In these examples, you compute the absolute value of different numeric types using the abs() function. First, you use integer numbers, then floating-point and complex numbers, and finally, fractional and decimal numbers. In all cases, when you call the function with a negative value, the final result removes the sign.

For a practical example, say that you need to compute the total profits and losses of your company from a month’s transactions:

>>> transactions = [-200, 300, -100, 500]

>>> incomes = sum(income for income in transactions if income > 0)
>>> expenses = abs(
...     sum(expense for expense in transactions if expense < 0)
... )

>>> print(f"Total incomes: ${incomes}")
Total incomes: $800
>>> print(f"Total expenses: ${expenses}")
Total expenses: $300
>>> print(f"Total profit: ${incomes - expenses}")
Total profit: $500

Read the full article at https://realpython.com/python-built-in-functions/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #295: Agentic Architecture: Why Files Aren't Always Enough

2026-05-15T12:00:00+00:00

What are the limitations of using a file-based agent workflow? Why do massive context windows tend to collapse? This week on the show, Mikiko Bazeley from MongoDB joins us to discuss agentic architecture and context engineering.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: Python's Array: Working With Numeric Data Efficiently

2026-05-15T12:00:00+00:00

In this quiz, you’ll test your understanding of Python’s Array: Working With Numeric Data Efficiently.

By working through this quiz, you’ll revisit the differences between Python’s array module and the built-in list, the meaning of type codes, how to create and manipulate arrays as mutable sequences, and the performance trade-offs of using a low-level numeric container.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: Cursor vs Windsurf: Which AI Code Editor Is Best for Python?

2026-05-14T12:00:00+00:00

In this quiz, you’ll test your understanding of Cursor vs Windsurf: Which AI Code Editor Is Best for Python?

By working through these questions, you’ll revisit how the two editors differ across code completion, agentic multi-file editing, and debugging.

You’ll also reconnect with the audit points worth applying whenever an AI agent writes Python on your behalf.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: Python Metaclasses

2026-05-14T12:00:00+00:00

In this quiz, you’ll test your understanding of Python Metaclasses.

Metaclasses sit behind every class you write in Python, and they’re one of the language’s deeper object-oriented concepts. By working through this quiz, you’ll revisit how classes are themselves objects, how type creates them, and how a custom metaclass lets you customize class creation.

You’ll also reflect on when a custom metaclass is actually the right tool and when a simpler technique does the job better.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

How to Use OpenCode for AI-Assisted Python Coding

2026-05-13T14:00:00+00:00

OpenCode is an open-source AI coding agent that runs in your terminal and lets you analyze and refactor a Python project through conversational commands. In this guide, you’ll install it on your system, set it up with a free Google Gemini API key, and learn the basics of how to use it in your daily programming work.

Here’s what OpenCode’s main interface looks like:

OpenCode works as a conversational assistant you explicitly direct. Ask it to analyze functions, refactor code, or explain issues. Press Enter to send your query, and you’ll get a response with full awareness of your project context. It supports more than seventy-five AI providers, including Anthropic, OpenAI, and Google Gemini.

If you’re a Python developer who prefers working in the terminal, OpenCode offers deliberate, context-aware assistance and a customizable AGENTS.md configuration file.

Take the Quiz: Test your knowledge with our interactive “How to Use OpenCode for AI-Assisted Python Coding” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

How to Use OpenCode for AI-Assisted Python Coding

Quiz yourself on OpenCode: install it, connect an AI provider, and use it to analyze and refactor Python from your terminal.

Prerequisites

Before you start working with OpenCode, you’ll need to fulfill the following prerequisites regarding your current system and working environment:

Python 3.11 or higher for the sample project
A modern terminal emulator

You also need an AI provider account. In this guide, you’ll use Google AI Studio to get a free Gemini API key. The free Gemini tier lets you follow along without any additional costs. However, you can also use Anthropic, OpenAI, or GitHub Copilot if you already have subscriptions to those services.

This guide uses a sample project consisting of a dice-rolling script. You’ll find the full source code in a collapsible block at the start of Step 2. The download below includes the starting script and the final refactored version so you can compare your work when you’re done:

Get Your Code: Click here to download the free sample code you’ll use to learn about AI-assisted Python coding with OpenCode.

You’ll also need some background knowledge of Python programming and basic experience with your operating system’s terminal or command line.

Step 1: Install and Set Up OpenCode

It’s time to install OpenCode and get it talking to a model. You’ll install the tool on your system, authenticate with Gemini using a free API key, configure a default model, and verify that OpenCode responds correctly to your Python questions before you start coding with it.

Install and Launch OpenCode

The quickest way to install OpenCode is to use the official installation script, which you can do with the following command:

$ curl -fsSL https://opencode.ai/install | bash

This script detects your platform, downloads the appropriate binary, installs the tool, and adds it to your PATH.

If you prefer a package manager, you can also install OpenCode with Homebrew on macOS or Linux:

$ brew install anomalyco/tap/opencode

Note that the Homebrew team maintains the official formula and updates it less frequently than the installation script above.

Alternatively, you can install it as a Node.js package using npm if you already have this tool on your system:

$ npm install -g opencode-ai

If you’re on Windows, the best experience comes from using WSL (Windows Subsystem for Linux). Set up WSL first by following Microsoft’s WSL installation guide, then open a WSL terminal and run the curl command above. For optimal performance, you should store your project within the WSL filesystem rather than on a Windows drive.

Read the full article at https://realpython.com/opencode-guide/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Building Type-Safe LLM Agents With Pydantic AI

2026-05-12T14:00:00+00:00

Pydantic AI is a Python framework for building LLM agents that return validated, structured outputs using Pydantic models. Instead of parsing raw strings from LLMs, you get type-safe objects with automatic validation.

If you’ve used FastAPI or Pydantic before, then you’ll recognize the familiar pattern of defining schemas with type hints and letting the framework handle the type validation for you.

By the end of this video course, you’ll understand that:

Pydantic AI uses BaseModel classes to define structured outputs that guarantee type safety and automatic validation.
The @agent.tool decorator registers Python functions that LLMs can invoke based on user queries and docstrings.
Dependency injection with deps_type provides type-safe runtime context like database connections without using global state.
Validation retries automatically rerun queries when the LLM returns invalid data, which increases reliability but also API costs.
Google Gemini, OpenAI, and Anthropic models support structured outputs best, while other providers have varying capabilities.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: Building Type-Safe LLM Agents With Pydantic AI

2026-05-12T12:00:00+00:00

In this quiz, you’ll test your understanding of Building Type-Safe LLM Agents With Pydantic AI.

By working through this quiz, you’ll revisit how Pydantic AI returns structured outputs from LLMs, how validation retries improve reliability, how tools and function calling work, how dependency injection flows through RunContext, and what trade-offs to expect when running agents in production.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Quiz: The LEGB Rule & Understanding Python Scope

2026-05-12T12:00:00+00:00

In this quiz, you’ll test your understanding of The LEGB Rule & Understanding Python Scope.

By working through this quiz, you’ll revisit how Python resolves names using the LEGB rule, what the local, enclosing, global, and built-in scopes look like in practice, and how the global and nonlocal statements let you reach across scope boundaries.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

How to Flatten a List of Lists in Python

2026-05-11T14:00:00+00:00

Flattening a list in Python involves converting a nested list structure into a single, one-dimensional list. A common approach to flatten a list of lists is to use a for loop to iterate through each sublist. Then you can add each item to a new list with the .extend() method or the augmented concatenation operator (+=). This will “unlist” the list, resulting in a flattened list.

Python’s standard library offers other tools to achieve similar results. You can also use a list comprehension for a concise one-liner solution. Each method has its own performance characteristics, but for loops and list comprehensions are generally more efficient.

By the end of this tutorial, you’ll understand that:

Flattening a list involves converting nested lists into a single list.
You can use a for loop and .extend() or a list comprehension to flatten lists in Python.
Standard-library functions like itertools.chain() and functools.reduce() can also flatten lists.
A custom flatten() function, either recursive or iterative, handles arbitrarily nested lists.
The .flatten() method in NumPy efficiently flattens arrays for data science tasks.

To better illustrate what it means to flatten a list, say that you have the following matrix of numeric values:

>>> matrix = [
...     [9, 3, 8, 3],
...     [4, 5, 2, 8],
...     [6, 4, 3, 1],
...     [1, 0, 4, 5],
... ]

The matrix variable holds a Python list that contains four nested lists. Each nested list represents a row in the matrix. The rows store four items or numbers each. Now say that you want to turn this matrix into the following list:

[9, 3, 8, 3, 4, 5, 2, 8, 6, 4, 3, 1, 1, 0, 4, 5]

How do you manage to flatten your matrix and get a one-dimensional list like the one above? In this tutorial, you’ll learn how to do that in Python.

Free Bonus: Click here to download the free sample code that showcases and compares several ways to flatten a list of lists in Python.

Take the Quiz: Test your knowledge with our interactive “How to Flatten a List of Lists in Python” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

How to Flatten a List of Lists in Python

Test your understanding of how to flatten a list of lists in Python using for loops, list comprehensions, itertools, recursion, and NumPy.

How to Flatten a List of Lists With a `for` Loop

How can you flatten a list of lists in Python? In general, to flatten a list of lists, you can run the following steps either explicitly or implicitly:

Create a new empty list to store the flattened data.
Iterate over each nested list or sublist in the original list.
Add every item from the current sublist to the list of flattened data.
Return the resulting list with the flattened data.

You can follow several paths and use multiple tools to run these steps in Python. The most natural and readable way to do this is to use a for loop, which allows you to explicitly iterate over the sublists.

Then you need a way to add items to the new flattened list. For that, you have a couple of valid options. First, you’ll turn to the .extend() method from the list class itself, and then you’ll give the augmented concatenation operator (+=) a go.

To continue with the matrix example, here’s how you would translate these steps into Python code using a for loop and the .extend() method:

>>> def flatten_extend(matrix):
...     flat_list = []
...     for row in matrix:
...         flat_list.extend(row)
...     return flat_list
...

Inside flatten_extend(), you first create a new empty list called flat_list. You’ll use this list to store the flattened data when you extract it from matrix. Then you start a loop to iterate over the inner, or nested, lists from matrix. In this example, you use the name row to represent the current nested list.

In every iteration, you use .extend() to add the content of the current sublist to flat_list. This method takes an iterable as an argument and appends its items to the end of the target list.

Now go ahead and run the following code to check that your function does the job:

>>> flatten_extend(matrix)
[9, 3, 8, 3, 4, 5, 2, 8, 6, 4, 3, 1, 1, 0, 4, 5]

That’s neat! You’ve flattened your first list of lists. As a result, you have a one-dimensional list containing all the numeric values from matrix.

With .extend(), you’ve come up with a Pythonic and readable way to flatten your lists. You can get the same result using the augmented concatenation operator (+=) on your flat_list object. However, this alternative approach may not be as readable:

>>> def flatten_concatenation(matrix):
...     flat_list = []
...     for row in matrix:
...         flat_list += row
...     return flat_list
...

Read the full article at https://realpython.com/python-flatten-list/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #294: Declarative Charts in Python & Discerning Iterators vs Iterables

2026-05-08T12:00:00+00:00

What if you could build charts in Python by describing what your data means, instead of scripting every visual detail? Christopher Trudeau is back on the show this week with another batch of PyCoder's Weekly articles and projects.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

ChatterBot: Build a Chatbot With Python

2026-05-06T14:00:00+00:00

The Python ChatterBot library lets you build a self-learning command-line chatbot with just a few lines of code. You’ll set up a basic bot, clean real WhatsApp conversation data with regular expressions, and train your chatbot on that custom corpus. You’ll also plug in a local LLM through Ollama to augment its replies with contextual knowledge.

By the end of this tutorial, you’ll understand that:

ChatterBot is a Python library that combines text processing, machine learning, and a local database to generate chatbot replies.
A minimal ChatterBot script instantiates ChatBot, collects user input in a loop, and returns matching responses through .get_response().
Training with ListTrainer and default settings stores conversation pairs in a SQLite database that ChatterBot queries with Levenshtein distance to pick each reply.
ChatterBot can call a local LLM through OllamaLogicAdapter, voting against other logic adapters with a confidence score.
ChatterBot was revived in 2025 with spaCy-based NLP, CSV and JSON trainers, and experimental LLM support.

Along the way, you’ll move from a potted plant that can only echo hello to a chatbot that chats knowledgeably about houseplants. You can follow along with your own WhatsApp export or grab the provided sample data below.

Get Your Code: Click here to download the free sample code that you’ll use to build a chatbot with Python’s Chatterbot.

Take the Quiz: Test your knowledge with our interactive “ChatterBot: Build a Chatbot With Python” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

ChatterBot: Build a Chatbot With Python

Test your understanding of the ChatterBot Python library, from training a basic bot with ListTrainer to wiring in a local LLM through Ollama.

Preview the Chatbot

At the end of this tutorial, you’ll have a command-line chatbot that can respond to your inputs with semi-meaningful replies:

You’ll achieve that by preparing WhatsApp chat data and using it to train the chatbot. Beyond learning from your automated training, the chatbot will improve over time as it gets more exposure to questions and replies from user interactions.

Project Overview

The ChatterBot library combines text processing, machine learning algorithms, and data storage and retrieval to allow you to build flexible chatbots.

You can build an industry-specific chatbot by training it with relevant data. Additionally, the chatbot will remember user responses and continue building its internal graph structure to improve the responses that it can give.

Note: After a long hiatus, ChatterBot was revived in early 2025 with support for modern Python, new training formats for CSV and JSON data, and even experimental LLM integration. Under the hood, ChatterBot now uses spaCy for language processing, which gives it a more robust NLP pipeline than before.

If you want to develop an LLM-first chatbot, Real Python’s LLM Application Development With Python learning path takes you through the concepts and libraries step by step:

Learning Path

LLM Application Development With Python

13 Resources ⋅ Skills: OpenAI, Ollama, OpenRouter, Prompt Engineering, LangChain, LlamaIndex, ChromaDB, MarkItDown, RAG, Embeddings, Pydantic AI, LangGraph, MCP

In this tutorial, you’ll start with an untrained chatbot that’ll showcase how quickly you can create an interactive chatbot using Python’s ChatterBot. You’ll also notice how small the vocabulary of an untrained chatbot is.

Next, you’ll learn how you can train such a chatbot and check on the slightly improved results. The more plentiful and high-quality your training data is, the better your chatbot’s responses will be.

Therefore, you’ll either fetch the conversation history of one of your WhatsApp chats or use the provided chat.txt file that you can download here:

Get Your Code: Click here to download the free sample code that you’ll use to build a chatbot with Python’s Chatterbot.

It’s rare that input data comes exactly in the form you need, so you’ll clean the chat export data to get it into a useful input format. This process will show you some tools you can use for data cleaning, which may help you prepare other input data to feed to your chatbot.

After data cleaning, you’ll retrain your chatbot and give it another spin to experience the improved performance. Finally, you’ll hook a local LLM into your chatbot to augment the variety and contextual relevance of its responses.

When you work through this process from start to finish, you’ll get a good idea of how you can build and train a Python chatbot with the ChatterBot library so that it can provide an interactive experience with relevant replies.

Prerequisites

Before you get started, make sure that you have Python 3.10 or later installed, which is the minimum Python version that ChatterBot supports. If you need help setting up Python, check out Python 3 Installation & Setup Guide.

Read the full article at https://realpython.com/build-a-chatbot-python-chatterbot/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Use Codex CLI to Enhance Your Python Projects

2026-05-05T14:00:00+00:00

After watching this video course, you’ll be able to use Codex CLI to add features to a Python project directly from your terminal. Codex CLI is an AI-powered coding assistant that runs inside your terminal. It understands your project structure, reads your files, and proposes multi-file changes using natural language instructions.

Instead of copying code from a browser or relying on an IDE plugin, you’ll use Codex CLI to implement a real feature in a multi-file Python project directly from your terminal.

In the following lessons, you’ll install and configure Codex CLI, use it to implement a deletion feature in a contact book app, and then refine that feature through iterative prompting.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

A New Python Packaging Council and Other News for May 2026

2026-05-04T14:00:00+00:00

April gave Python developers a new governing body. PEP 772 was accepted on April 16, creating a dedicated Python Packaging Council that will make binding decisions about packaging standards and tools. After years of informal coordination through the Python Packaging Authority (PyPA), the packaging community now has its own elected five-member council with authority comparable to the Steering Council.

On the release side, Python 3.15.0 alpha 8 dropped with a refreshed JIT delivering 6–7 percent speedups on x86-64 Linux and 12–13 percent on AArch64 macOS. The core team also decided to revert 3.14’s incremental garbage collector after production reports of runaway memory use, with the fix landing in the upcoming 3.14.5 patch release. The next pre-release is the first beta, scheduled for May 5, which marks the feature freeze for Python 3.15.

Elsewhere, Google released the open-weights Gemma 4 family, Starlette 1.0 shipped for FastAPI’s foundation, and the broader Python ecosystem absorbed the news that OpenAI acquired Astral, the company behind uv, Ruff, and ty. Get ready to dig into the biggest Python news from the past month!

Join Now: Click here to join the Real Python Newsletter and you’ll never miss another Python tutorial, course, or news update.

Python Releases and PEP Highlights

April pushed Python 3.15 to its final alpha before the beta freeze, walked back the incremental garbage collector introduced in 3.14, and gave the Steering Council a busy month of PEP decisions. The packaging community even got its own elected governing body for the first time. Plenty to unpack on the language and process side of the ecosystem.

Python 3.15.0 Alpha 8: Final Alpha Before Beta Freeze

Python 3.15.0a8 landed on April 7, released alongside maintenance updates 3.14.4 and 3.13.13. Release manager Hugo van Kemenade confirmed that a8 is the final alpha before the beta phase begins. If you maintain a library, this is the last alpha where you can file an issue against an unreleased feature and reasonably expect it to land before the freeze.

Alpha 8 consolidates a long list of PEPs you’ve been hearing about in earlier alphas:

PEP 810: Explicit lazy imports, which we covered last month
PEP 814: frozendict as a built-in type
PEP 799: Statistical sampling profiler
PEP 798: Unpacking in comprehensions
PEP 686: UTF-8 as the default encoding
PEP 728: TypedDict enhancements

The headline number is the JIT performance jump. On x86-64 Linux, the alpha reports a 6–7 percent geometric mean improvement over the standard interpreter. On AArch64 macOS, the gain is 12–13 percent over the tail-calling interpreter introduced in 3.14. Those aren’t microbenchmark curiosities. They’re cumulative gains across a broad suite of workloads.

Note: If you haven’t tried the alpha yet, installing it in an isolated environment is a good idea. Running uv python install 3.15.0a8 pulls the binary, and pyenv handles alpha builds too. The next pre-release, 3.15.0 beta 1, is scheduled for May 5, which marks the feature freeze. After that, no new PEPs land in 3.15.

Incremental GC Reverted in 3.14.5 and 3.15

On April 16, release manager Hugo van Kemenade proposed reverting the incremental garbage collector that debuted in Python 3.14, and the core team agreed. The revert will ship in Python 3.14.5 and also make it into 3.15 before feature freeze.

The reasoning is practical. Neil Schemenauer’s testing on production workloads showed that the incremental collector cut maximum pause times from 26 ms down to 1.3 ms, which looks great on paper. But peak memory usage climbed to as much as 5x the generational baseline in the worst case, and total runtime went up, not down, because of the extra bookkeeping.

For most Python programs, like web apps, data pipelines, and batch jobs, reducing long pauses isn’t the win that matters. Memory pressure is.

The unusual part is doing this in a patch release. The working assumption during 3.14’s release cycle was that the incremental GC had earned its place. Rolling it back in 3.14.5 is a reminder that “passed the benchmark suite” and “works in production” aren’t the same thing. If you noticed your 3.14 deployments using noticeably more memory than 3.13, this is almost certainly why, and 3.14.5 should give you the old behavior back.

Note: The incremental approach isn’t dead. The core team noted that it could return in Python 3.16 through a proper PEP review process, which the original implementation had skipped. If you were on the fence about the switch, waiting for the formal design round is probably the right call.

PEP 772 Accepted: Python Gets a Packaging Council

On April 16, the Python Software Foundation (PSF) and the Steering Council accepted PEP 772, which creates a five-member Packaging Council with broad authority over packaging standards, tools, and implementations. It’s one of the biggest governance changes the ecosystem has seen since the Steering Council itself was established back in 2019.

Council members will be elected by PSF voting members who opt into the election. The council runs on staggered two-year terms, with two seats and three seats rotating in different cycles to preserve institutional continuity. Decision-making emphasizes consensus over voting, following the same pattern that has worked for the Steering Council.

The practical impact is that a formal, elected body now owns decisions about tools like pip, setuptools, and PyPI, replacing the ambiguous delegation model defined in PEP 609.

If you’ve ever wondered why packaging decisions in Python sometimes feel stuck in committee, PEP 772 is the structural answer to that complaint. It also sets the stage for the council to weigh in on LLM-era packaging concerns, which are popping up faster than the PyPA’s informal coordination could address them.

PEP 803 Accepted: Stable ABI Goes Free-Threaded

PEP 803 was accepted on March 30 and targets Python 3.15. It defines abi3t, a new variant of the stable ABI that works with free-threaded builds. When the Steering Council accepted PEP 779 last year, it promised free-threading would get a proper stable ABI story for 3.15. PEP 803 is that follow-through.

Read the full article at https://realpython.com/python-news-may-2026/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #293: Agentic Data Science Pair Programming With marimo pair

2026-05-01T12:00:00+00:00

How do you add agent skills to your data science workflow? How can a coding agent assist with data wrangling and research? This week on the show, Trevor Manz from marimo joins us to discuss marimo pair.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

AI Coding Agents Guide: A Map of the Four Workflow Types

2026-04-29T14:00:00+00:00

AI coding agents can read your code, reason about changes, and act on your behalf. To choose the right one, it helps to understand the four common workflow types: integrated development environment (IDE), terminal, pull request (PR), and cloud.

In this tutorial, you’ll:

Identify the four common agent interaction modes
Understand what makes each workflow distinct
Recognize which mode fits common development scenarios
Weigh the risks and tradeoffs of each workflow

Before exploring the four workflow types, it’s worth looking at what makes a coding tool agentic in the first place.

Take the Quiz: Test your knowledge with our interactive “AI Coding Agents Guide: A Map of the Four Workflow Types” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

AI Coding Agents Guide: A Map of the Four Workflow Types

Check your understanding of how AI coding agents fit into your workflow through four interaction modes: IDE, terminal, pull request, and cloud.

Get Your Cheat Sheet: Click here to download your free AI coding agents cheat sheet and keep the four workflow types at your fingertips when choosing the right agent for the job.

Understanding AI Coding Agents

While standard chatbots provide one-off answers, coding agents are designed for autonomy, operating through a continuous execution loop to solve complex tasks. This loop typically follows four distinct steps:

Read: They read relevant files from your codebase to form their context.
Reason: They determine the logical steps needed to achieve your goal.
Act: They execute those steps by editing files, running terminal commands, or using external tools.
Evaluate: They check the results of their actions to see if more work is needed.

This loop repeats until the task is completed or the agent hands control back to you. Unlike simple predictive text or one-off prompts, agents bridge the gap between suggestion and execution by autonomously navigating the development workflow.

The core agent loop will generally stay the same, but where an agent runs will shape how you interact with it:

In an editor, it works alongside you.
In a terminal, you guide it step by step.
In pull requests, it reviews changes asynchronously.
In the cloud, it works in a managed environment and reports back later.

These environments define four primary agent types, each enabling a distinct workflow: IDE agents, terminal agents, PR agents, and cloud agents.

Exploring the Four Workflow Types

The four workflow types describe interaction modes and don’t always map cleanly to product categories. The same tool often spans multiple workflows. For example, Claude Code runs in your terminal, in your editor, and in the cloud with Claude Code on the web. It can also review pull requests with Code Review.

The goal is to match the workflow to the task. The diagram below summarizes the four types at a glance:

Read the full article at https://realpython.com/ai-coding-agents-guide/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Testing Your Code With Python's unittest

2026-04-28T14:00:00+00:00

The Python standard library ships with a testing framework named unittest, which you can use to write automated tests for your code. The unittest package has an object-oriented approach where test cases derive from a base class, which has several useful methods.

The framework supports many features that will help you write consistent unit tests for your code. These features include test cases, fixtures, test suites, and test discovery capabilities.

In this video course, you’ll learn how to:

Write unittest tests with the TestCase class
Explore the assert methods that TestCase provides
Use unittest from the command line
Group test cases using the TestSuite class
Create fixtures to handle setup and teardown logic

To get the most out of this video course, you should be familiar with some important Python concepts, such as object-oriented programming, inheritance, and assertions. Having a good understanding of code testing is a plus.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

How to Conceptualize Python Fundamentals for Greater Mastery

2026-04-27T14:00:00+00:00

Struggling to conceptualize Python fundamentals is a common problem learners face. If you’re unable to put a fundamental concept into perspective and form a clear mental picture of what it’s about, it’ll be difficult to understand and apply it.

In this guide, you’ll walk through a framework of steps to help you better conceptualize Python fundamentals. This process is helpful for Python developers and learners at any experience level, but especially for beginners. If you are just starting out, this guide will help you build a solid understanding of the basics.

You might want to set aside twenty minutes or so to read through the tutorial, and another thirty minutes to practice on a few key concepts. You should also gather a list of difficult topics, your preferred learning resources, and a note-taking app or pen and paper.

Click the link below to download a free cheat sheet that covers the framework steps you’ll walk through in this guide:

Get Your Cheat Sheet: Click here to download a free PDF that outlines the framework of steps for conceptualizing Python fundamentals.

Take the Quiz: Test your knowledge with our interactive “How to Conceptualize Python Fundamentals for Greater Mastery” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

How to Conceptualize Python Fundamentals for Greater Mastery

Check your understanding of a framework for conceptualizing Python fundamentals, from defining concepts to comparing similar ideas.

Step 1: Define the Concept in Your Own Words

Begin by briefly describing the concept in your own words. You can write your definition in the downloadable worksheet provided with this tutorial. Note that writing is a powerful tool for reinforcing learning, as educator and former Rutgers University professor Janet Emig asserted in her paper, Writing as a Mode of Learning.

Answer Key Questions for Defining a Concept

As a framework for your definition, consider these key questions:

What: What is a short description of the concept?
Why: Why is the concept important in the broader Python context?
How: How is the concept used in a Python program?

These questions will help you establish a core understanding of the concept you’re learning.

You might feel intimidated when you’re trying to define a Python concept. If you need help, there are many resources that can assist you. Real Python’s Reference section has concise definitions of Python keywords, built-in types, standard library modules, and more to help you build your own descriptions.

If you’re a visual learner, using an illustration can be a powerful way to enhance your understanding. In addition to a written definition, you can draw a picture or diagram to illustrate the concept. For example, the Variables in Python: Usage and Best Practices tutorial shows some example images of how you might picture variables. If you look at the Lists vs Tuples in Python tutorial, you can see a diagram of a Python list.

While pictures can be helpful, being able to conceptualize doesn’t necessarily mean you have to think visually. There are different thinking styles. Some researchers suggest that people can be visual or verbal thinkers. Pattern-based thinking is another style. Several of the tips in this tutorial encourage you to explore different aspects of these styles, depending on which works best for you.

View Examples of Concept Definitions

You might find a couple of examples helpful in understanding how to define difficult concepts. Suppose you’re studying variables. Here are possible responses to the key questions:

What: A variable is a name that points to an object stored in the program’s memory.
Why: Variables are key for data processing.
How: Assigning a value to a variable using the assignment operator (=) allows you to access your program’s data in a user-friendly way. You can then access and change the value by name throughout the program as needed.

This description provides a concise summary of what a variable is, why it matters, and how to use one. You can also include an example of variable usage as an addendum to your definition:

>>> age = 25

Here, you created a variable called age and assigned it a value of 25. From now on, you can use the variable name age to access, modify, or use the variable’s value.

Or, you might be learning about lists. Your definitions could look like this:

What: A list is a sequence of values or objects.
Why: Working with sequences of items is a common, foundational task in programming. Python lists make this important work easier.
How: You can create a list by writing a pair of square brackets, with a comma-separated sequence of items inside them. Assign the list to a variable to use it throughout your program.

Here’s a short Python list that demonstrates the points in the definitions above:

Read the full article at https://realpython.com/conceptualize-python-fundamentals/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #292: Becoming a Better Python Developer Through Learning Rust

2026-04-24T12:00:00+00:00

How can learning Rust help make you a better Python Developer? How do techniques required by a compiled language translate to improving your Python code? Christopher Trudeau is back on the show this week with another batch of PyCoder's Weekly articles and projects.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Altair: Declarative Charts With Python

2026-04-22T14:00:00+00:00

There’s a moment many data analysts know well: you have a new dataset and a clear question, and you open a notebook only to find yourself writing boilerplate axis and figure setup before you’ve even looked at the data. Matplotlib gives you fine-grained control, but that control comes with a cost. Altair takes a completely different approach to data visualization in Python.

Instead of scripting every visual detail, you describe what your data means. This includes specifying which column goes on which axis, what should be colored, and what should be interactive. Altair then generates the visualization.

If you’re wondering whether it’s worth adding another visualization library to your toolkit, here’s how Altair and Matplotlib compare:

Use Case	Pick Altair	Pick Matplotlib
Interactive exploratory charts in notebooks	✅	—
Pixel-precise publication figures or 3D plots	—	✅

Altair generates web-native charts. The output is HTML and JavaScript, which means charts render right in your notebook and can be saved as standalone HTML files or embedded in web pages. It’s not a replacement for Matplotlib, and it doesn’t try to be. Think of them as tools you reach for in different situations.

Get Your Code: Click here to download the free sample code you’ll use to build interactive Python charts the declarative way with Altair.

Take the Quiz: Test your knowledge with our interactive “Altair: Declarative Charts With Python” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

Altair: Declarative Charts With Python

Test your knowledge of Altair, the declarative data visualization library for Python that turns DataFrames into interactive charts.

Start Using Altair in Python

It’s a good idea to install Altair in a dedicated virtual environment. It pulls in several dependencies like pandas and the Vega-Lite renderer, and a virtual environment keeps them from interfering with your other projects. Create one and install Altair with pip:

$ python -m venv altair-venv
$ source altair-venv/bin/activate
(altair-venv) $ python -m pip install altair

This tutorial uses Python 3.14 and Altair 6.0. All the code runs inside a Jupyter notebook, which is the most common environment for interactive data exploration with Altair. If you prefer a different JavaScript-capable environment like VS Code, Google Colab, or JupyterLab, feel free to use that instead. To launch a Jupyter notebook, run the following:

(altair-venv) $ python -m pip install notebook
(altair-venv) $ jupyter notebook

The second command launches the Jupyter Notebook server in your browser. Create a new notebook and enter the following code, which builds a bar chart from a small DataFrame containing daily step counts for one week:

import altair as alt
import pandas as pd

steps = pd.DataFrame({
    "Day": ["1-Mon", "2-Tue", "3-Wed", "4-Thu", "5-Fri", "6-Sat", "7-Sun"],
    "Steps": [6200, 8400, 7100, 9800, 5500, 9870, 3769],
})

weekly_steps = alt.Chart(steps).mark_bar().encode(
    x="Day",
    y="Steps",
)
weekly_steps

You should see a bar chart displaying daily step counts:

The dataset is intentionally minimal because data isn’t the main focus: it has seven rows for seven days, and two columns for the day name and step count. Notice how the weekly_steps chart is constructed. Every Altair chart follows this same pattern. It’s built from these three building blocks:

Data: A pandas DataFrame handed to alt.Chart().
Mark: The visual shape you want, chosen via .mark_*(). Here, .mark_bar() draws bars. Other options include .mark_point(), .mark_line(), and .mark_arc().
Encode: The mapping from data columns to visual properties, declared inside .encode(). Here, Day goes to the x-axis and Steps to the y-axis.

This is Altair’s core grammar in action: Data → Mark → Encode. You’ll use it every time.

Read the full article at https://realpython.com/altair-python/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Leverage OpenAI's API in Your Python Projects

2026-04-21T14:00:00+00:00

Python’s openai library provides the tools you need to integrate the ChatGPT API into your Python applications. With it, you can send text prompts to the API and receive AI-generated responses. You can also guide the AI’s behavior with developer role messages and handle both simple text generation and more complex code creation tasks.

After watching this video course, you’ll understand how examples like this work under the hood. You’ll learn the fundamentals of using the ChatGPT API from Python and have code examples you can adapt for your own projects.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Gemini CLI vs Claude Code: Which to Choose for Python Tasks

2026-04-20T14:00:00+00:00

When comparing Gemini CLI vs Claude Code, the answer to “which one is better?” is usually it depends. Both tools boost productivity for Python developers, but they have different strengths. Choosing the right one depends on your budget, workflow, and what you value most in generated code.

Gemini CLI, for instance, is known for its generous free tier, while Claude Code is a paid tool known for its production-ready output.

In this tutorial, you’ll explore features such as user experience, performance, code quality, and usage cost to help make that decision easier. The AI coding assistance these tools provide right in your terminal generally makes writing Python code much more seamless, helping you save time and be more productive.

This table highlights the key differences at a glance:

Use Case	Gemini CLI	Claude Code
You need free generous usage limits	✅	—
You need Google Cloud integration	✅	—
You need faster task completion	—	✅
You need code close to production quality	—	✅

You can see that Gemini CLI is a promising choice if you’re looking for free usage limits and prefer Google Cloud integration. However, if you want to complete tasks faster, Claude Code has an edge. Both tools produce code of good quality, but Claude Code generates code that is closer to production quality. If you’d like a more thorough comparison, then read on.

Get Your Code: Click here to download the free sample code for the to-do app projects built with Gemini CLI and Claude Code in this tutorial.

Take the Quiz: Test your knowledge with our interactive “Gemini CLI vs Claude Code: Which to Choose for Python Tasks” quiz. You’ll receive a score upon completion to help you track your learning progress:

Interactive Quiz

Gemini CLI vs Claude Code: Which to Choose for Python Tasks

Compare Gemini CLI and Claude Code across user experience, performance, code quality, and cost to find the right AI coding tool for you.

Metrics Comparison: Gemini CLI vs Claude Code

To ground the comparisons in hands-on data, both tools are tested using the same prompt throughout this tutorial:

Prompt

Build a CLI-based mini to-do application in Python. It should allow users to create tasks, mark tasks as completed, list tasks with filtering for completed and pending tasks, delete tasks, include error handling, persist tasks to a local JSON file, and include basic unit tests.

For a fair comparison, Gemini CLI is tested on its free tier using Gemini 3 Flash Preview, which is the default model the free tier provides access to. Claude Code is tested on the Pro plan using Claude Sonnet 4.6, which is the model Claude Code primarily uses for everyday interactions on that plan.

Each tool will run this prompt three times. Completion time, token usage, and the quality of the generated code are recorded from the runs and are referenced in the Performance, Code Quality, and Usage Cost sections of this tutorial.

Note: If you want to learn more about these tools so you can compare them yourself, Real Python has you covered. The How to Use Google’s Gemini CLI for AI Code Assistance tutorial covers installation, authentication, and hands-on usage, while the Getting Started With Claude Code video course walks you through setup and core features.

You should also be comfortable using your terminal, since both Gemini CLI and Claude Code are command-line tools.

The table below provides more detailed metrics to help with each comparison:

Metric	Gemini CLI	Claude Code
User Experience	Intuitive, browser-based auth, terminal-native	Minimal setup, terminal-native, strong project awareness
Performance	Good performance, however slower generation speed	Good performance, code is generated generally faster
Code Quality	Solid, better for exploratory tasks	Strong, better for production-grade work
Usage Cost	Free tier available; paid plans for heavier use	Requires a paid subscription to get started

The following sections explore each metric in detail, so you can decide which tool fits your workflow best.

User Experience

When writing Python programs, it helps to be able to comfortably use your tools without dealing with unintuitive interfaces. Both Gemini CLI and Claude Code prioritize a smooth terminal experience, but user experience goes beyond the interface itself—installation, setup, available models, and features offered are also part of it.

Installation and Setup

A few differences exist between Gemini CLI and Claude Code during installation. Gemini CLI requires a Google account for authentication. Claude Code doesn’t need a Google account. Instead, it requires an Anthropic subscription or API key.

Gemini CLI is first installed using npm:

$ npm install -g @google/gemini-cli

You can also install Gemini CLI with Anaconda, MacPorts, or Homebrew, which you can find in the Gemini CLI documentation.

When installing Claude Code, you run the following commands:

Read the full article at https://realpython.com/gemini-cli-vs-claude-code/ »

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #291: Reassessing the LLM Landscape & Summoning Ghosts

2026-04-17T12:00:00+00:00

What are the current techniques being employed to improve the performance of LLM-based systems? How is the industry shifting from post-training towards context engineering and multi-agent orchestration? This week on the show, Jodie Burchell, data scientist and Python Advocacy Team Lead at JetBrains, returns to discuss the current AI coding landscape.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Python Game Development

2026-04-16T12:00:00+00:00

Build Python games from command-line projects to 2D graphical games with turtle, Tkinter, Pygame, and Arcade.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Vector Databases and Embeddings With ChromaDB

2026-04-14T14:00:00+00:00

The era of large language models (LLMs) is here, bringing with it rapidly evolving libraries like ChromaDB that help augment LLM applications. You’ve most likely heard of chatbots like OpenAI’s ChatGPT, and perhaps you’ve even experienced their remarkable ability to reason about natural language processing (NLP) problems.

Modern LLMs, while imperfect, can accurately solve a wide range of problems and provide correct answers to many questions. However, due to the limits of their training and the number of text tokens they can process, LLMs aren’t a silver bullet for all tasks.

You wouldn’t expect an LLM to deliver relevant responses about topics that don’t appear in its training data. For example, if you asked ChatGPT to summarize information in confidential company documents, you’d be out of luck. You could show some of these documents to ChatGPT, but there’s a limit to how many documents you can upload before you exceed ChatGPT’s maximum token count. How would you select which documents to show ChatGPT?

To address these limitations and scale your LLM applications, a great option is to use a vector database like ChromaDB. A vector database allows you to store encoded unstructured objects, like text, as lists of numbers that can be compared to one another. For instance, you can find a collection of documents relevant to a question you’d like an LLM to answer.

In this video course, you’ll learn about:

Representing unstructured objects with vectors
Using word and text embeddings in Python
Harnessing the power of vector databases
Encoding and querying over documents with ChromaDB
Providing context to LLMs like ChatGPT with ChromaDB

After watching, you’ll have the foundational knowledge to use ChromaDB in your NLP or LLM applications. Before watching, you should be comfortable with the basics of Python and high school math.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #290: Advice on Managing Projects & Making Python Classes Friendly

2026-04-10T12:00:00+00:00

What goes into managing a major project? What techniques can you employ for a project that's in crisis? Christopher Trudeau is back on the show this week with another batch of PyCoder's Weekly articles and projects.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Using Loguru to Simplify Python Logging

2026-04-07T14:00:00+00:00

Logging is a vital programming practice that helps you track, understand, and debug your application’s behavior. Loguru is a Python library that provides simpler, more intuitive logging compared to Python’s built-in logging module.

Good logging gives you insights into your program’s execution, helps you diagnose issues, and provides valuable information about your application’s health in production. Without proper logging, you risk missing critical errors, spending countless hours debugging blind spots, and potentially undermining your project’s overall stability.

By the end of this video course, you’ll understand that:

Logging in Python can be simple and intuitive with the right tools.
Using Loguru lets you start logging immediately without complex configuration.
You can customize log formats and send logs to multiple destinations like files, the standard error stream, or external services.
Loguru provides powerful debugging capabilities that make troubleshooting easier.
Loguru supports structured logging with JSON formatting for modern applications.

After watching this course, you’ll be able to quickly implement better logging in your Python applications. You’ll spend less time wrestling with logging configuration and more time using logs effectively to debug issues. This will help you build production-ready applications that are easier to troubleshoot when problems occur.

To get the most from this course, you should be familiar with Python concepts like functions, decorators, and context managers. You might also find it helpful to have some experience with Python’s built-in logging module, though this isn’t required.

Don’t worry if you’re new to logging in Python. This course will guide you through everything you need to know to get started with Loguru and implement effective logging in your applications.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Adding Python to PATH

2026-03-31T14:00:00+00:00

You may need to add Python to PATH if you’ve installed Python, but typing python on the command line doesn’t seem to work. You might see a message saying that python isn’t recognized, or you might end up running the wrong version of Python.

A common fix for these problems is adding Python to the PATH environment variable. In this video course, you’ll learn how to add Python to PATH. You’ll also learn what PATH is and why it’s essential for tools like the command line to be able to find your Python installation.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #289: Limitations in Human and Automated Code Review

2026-03-27T12:00:00+00:00

With the mountains of Python code that it's possible to generate now, how's your code review going? What are the limitations of human review, and where does machine review excel? Christopher Trudeau is back on the show this week with another batch of PyCoder's Weekly articles and projects.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Understanding CRUD Operations in SQL

2026-03-24T14:00:00+00:00

CRUD operations are at the heart of nearly every application you interact with. As a developer, you usually want to create data, read or retrieve data, update data, and delete data. Whether you access a database or interact with a REST API, only when all four operations are present are you able to make a complete data roundtrip in your app.

Creating, reading, updating, and deleting are so vital in software development that these methods are widely referred to as CRUD. Understanding CRUD will give you an actionable blueprint when you build applications and help you understand how the applications you use work behind the scenes. So, what exactly does CRUD mean?

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #288: Automate Exploratory Data Analysis & Invent Python Comprehensions

2026-03-20T12:00:00+00:00

How do you quickly get an understanding of what's inside a new set of data? How can you share an exploratory data analysis with your team? Christopher Trudeau is back on the show this week with another batch of PyCoder's Weekly articles and projects.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: LLM Application Development With Python

2026-03-19T12:00:00+00:00

Build LLM-powered applications in Python. Call model APIs, craft prompts, add retrieval-augmented generation, create AI agents, and connect via MCP.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Downloading Files From URLs With Python

2026-03-17T14:00:00+00:00

Python makes it straightforward to download files from a URL with its robust set of libraries. For quick tasks, you can use the built-in urllib module or the requests library to fetch and save files. When working with large files, streaming data in chunks can help save memory and improve performance.

You can also perform parallel file downloads using ThreadPoolExecutor for multithreading or the aiohttp library for asynchronous tasks. These approaches allow you to handle multiple downloads concurrently, significantly reducing the total download time if you’re handling many files.

By the end of this video course, you’ll understand that:

You can use Python to download files with libraries like urllib and requests.
To download a file using a URL in Python, you can use urlretrieve() or requests.get().
To extract data from a URL in Python, you use the response object from requests.
To download a CSV file from a URL in Python, you may need to specify the format in the URL or query parameters.

In this video course, you’ll be downloading a range of economic data from the World Bank Open Data platform.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

The Real Python Podcast – Episode #287: Crafting and Editing In-Depth Tutorials at Real Python

2026-03-13T12:00:00+00:00

What goes into creating the tutorials you read at Real Python? What are the steps in the editorial process, and who are the people behind the scenes? This week on the show, Real Python team members Martin Breuss, Brenda Weleschuk, and Philipp Acsany join us to discuss topic curation, review stages, and quality assurance.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Python Coding With AI

2025-12-07T12:00:00+00:00

Use AI coding assistants to write, review, and debug Python code faster. Pick from Claude Code, Cursor, or Gemini CLI and start coding.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Python Control Flow and Loops

2024-11-14T12:00:00+00:00

Learn Python control flow and loops. Use conditional statements, Boolean operators, for and while loops, and keywords like break and continue.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Modules and Packages

2024-11-14T12:00:00+00:00

Learn Python's import system, organize code into modules and packages, manage dependencies with pip, and publish to PyPI.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Functions and Scopes

2024-11-14T12:00:00+00:00

Learn to define Python functions, use parameters and return values, create inner functions, and understand namespaces and scope.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Create Graphical User Interfaces (GUI)

2024-11-14T12:00:00+00:00

Build Python GUI applications with Tkinter, PyQt, wxPython, and Kivy. Learn layouts, event handling, threading, and database integration.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Important Standard Library Modules

2024-11-14T12:00:00+00:00

Explore Python standard library modules including math, datetime, JSON, CSV, regex, subprocess, and argparse through hands-on tutorials and courses.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Network Programming and Security

2024-11-14T12:00:00+00:00

Learn network programming and security in Python. Work with CRUD operations, REST APIs, HTTPS, and socket programming to build networked apps.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Learning Path: Functional Programming With Python

2024-11-14T12:00:00+00:00

Explore functional programming in Python. Learn lambda functions, map(), filter(), reduce(), closures, decorators, and recursion.

[ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]

Real Python

The Real Python Podcast – Episode #296: Managing Polars Schema Issues & Profiling GitHub Users

Quiz: Build a Tic-Tac-Toe Game With Python and Tkinter

Quiz: Context Managers and Using Python's with Statement

How to Use the Claude API in Python

Prerequisites

Step 1: Set Up the Claude API in Python

Get Your API Key and Install anthropic

Send Your First Prompt

Quiz: How to Use the Claude API in Python

Tapping Into the Zen of Python

Quiz: Tapping Into the Zen of Python

Quiz: Absolute vs Relative Imports in Python

Python Built-in Functions: A Complete Guide

Built-in Functions in Python

Using Math-Related Built-in Functions

Getting the Absolute Value of a Number: abs()

The Real Python Podcast – Episode #295: Agentic Architecture: Why Files Aren't Always Enough

Quiz: Python's Array: Working With Numeric Data Efficiently

Quiz: Cursor vs Windsurf: Which AI Code Editor Is Best for Python?

Quiz: Python Metaclasses

How to Use OpenCode for AI-Assisted Python Coding

Prerequisites

Step 1: Install and Set Up OpenCode

Install and Launch OpenCode

Building Type-Safe LLM Agents With Pydantic AI

Quiz: Building Type-Safe LLM Agents With Pydantic AI

Quiz: The LEGB Rule & Understanding Python Scope

How to Flatten a List of Lists in Python

How to Flatten a List of Lists With a for Loop

The Real Python Podcast – Episode #294: Declarative Charts in Python & Discerning Iterators vs Iterables

ChatterBot: Build a Chatbot With Python

Preview the Chatbot

Project Overview

LLM Application Development With Python

Prerequisites

Use Codex CLI to Enhance Your Python Projects

A New Python Packaging Council and Other News for May 2026

Python Releases and PEP Highlights

Python 3.15.0 Alpha 8: Final Alpha Before Beta Freeze

Incremental GC Reverted in 3.14.5 and 3.15

PEP 772 Accepted: Python Gets a Packaging Council

PEP 803 Accepted: Stable ABI Goes Free-Threaded

The Real Python Podcast – Episode #293: Agentic Data Science Pair Programming With marimo pair

AI Coding Agents Guide: A Map of the Four Workflow Types

Understanding AI Coding Agents

Exploring the Four Workflow Types

Testing Your Code With Python's unittest

How to Conceptualize Python Fundamentals for Greater Mastery

Step 1: Define the Concept in Your Own Words

Answer Key Questions for Defining a Concept

View Examples of Concept Definitions

The Real Python Podcast – Episode #292: Becoming a Better Python Developer Through Learning Rust

Altair: Declarative Charts With Python

Start Using Altair in Python

Leverage OpenAI's API in Your Python Projects

Gemini CLI vs Claude Code: Which to Choose for Python Tasks

Metrics Comparison: Gemini CLI vs Claude Code

User Experience

Installation and Setup

The Real Python Podcast – Episode #291: Reassessing the LLM Landscape & Summoning Ghosts

Learning Path: Python Game Development

Vector Databases and Embeddings With ChromaDB

The Real Python Podcast – Episode #290: Advice on Managing Projects & Making Python Classes Friendly

Using Loguru to Simplify Python Logging

Adding Python to PATH

The Real Python Podcast – Episode #289: Limitations in Human and Automated Code Review

Understanding CRUD Operations in SQL

The Real Python Podcast – Episode #288: Automate Exploratory Data Analysis & Invent Python Comprehensions

Learning Path: LLM Application Development With Python

Downloading Files From URLs With Python

The Real Python Podcast – Episode #287: Crafting and Editing In-Depth Tutorials at Real Python

Learning Path: Python Coding With AI

Learning Path: Python Control Flow and Loops

Learning Path: Modules and Packages

Learning Path: Functions and Scopes

Learning Path: Create Graphical User Interfaces (GUI)

Learning Path: Important Standard Library Modules

Learning Path: Network Programming and Security

Learning Path: Functional Programming With Python

Get Your API Key and Install `anthropic`

Getting the Absolute Value of a Number: `abs()`

How to Flatten a List of Lists With a `for` Loop