Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Learn Google's Gemini and Anthropic's Claude API with Python

Name: Learn Google's Gemini and Anthropic's Claude API with Python
Rating: 4.7 (133 reviews)

Harness the Power of Google's Gemini 1.5 and Anthropic's Claude 3 LLMs for Cutting-edge Applications. Hands-On Learning

Highest Rated

Created byAndrei Dumitrescu, Crystal Mind Academy

Last updated 6/2026

English

What you'll learn

Gain a deep understanding of the Google's Gemini and Anthropic's Claude 3 API with Python
Install Python SDK for Gemini and Claude 3 API and authenticate to Gemini
Create freeform prompts with Gemini Pro Vision in Google AI Studio
Use variables and parameters in Gemini prompts in Google AI Studio
Generate text from text inputs using Gemini Pro API and Python
Stream model responses from Gemini and Claude
Generate text from image and text inputs using Gemini Pro Vision and Claude 3 API and Python
Control how the model generates responses using Gemini API generation parameters: temperature, top_k, top_p, stop sequences and more
Build custom chat conversational agents
Master prompt-engineering techniques for LLMs
You'll learn how to create web interfaces (front-ends) for you LLM apps using Streamlit
Streamlit: main concepts, widgets, session state, callbacks
Learn how to use Jupyter AI efficiently

Course content

12 sections • 86 lectures • 7h 28m total length

How to Get the Most Out of This Course2:17
Master Google's Gemini and Anthropic's Claude API with Python by following practical tips, using a laptop for coding, and engaging with the question-and-answer section and online community.
Python IDEs For This Course0:34
Discover Python IDEs for this course, including Jupyter Notebook and Google Colab, ideal for data science, machine learning, and AI projects.
Setting Up the Environment: Jupyter Notebook14:09
Setting Up the Environment: Google Colab8:07
Join Our Online Community!0:25
Course Resources0:30

Getting a Gemini API Key4:20
Set up the environment and obtain a Gemini API key for Google Studio, noting regional availability and VPN options. Test the key with curl and review free and paid pricing.
Quiz for Getting a Gemini API Key
Installing the Python SDK for Gemini Pro API and Authenticating to Gemini9:51
Quiz for Installing the Python SDK
Gemini Multimodal Models: Nano, Pro and Ultra5:13
Explore Gemini, Google's multi-modal AI trained on text, images, audio, video, and code, with Nano, Pro, and Ultra, and see how Gemini Pro via API enables multimodal reasoning and outputs.
Quiz for Gemini Models
Google AI Studio: Freeform Prompts With Gemini Pro Vision6:10
Google AI Studio: Using Variables and Parameters in the Prompt3:04
Generating Text From Text Inputs: Gemini Pro4:21
Streaming Model Responses3:34
Explore streaming model responses with the Gemini API, delivering text piece by piece to reduce latency, enable chunked output, and improve learner experiences in an LMS.
Quiz for Generating Text from Text Inputs
Generating Text From Image and Text Inputs: Gemini Pro Vision5:12
Gemini API Generation Parameters: Controlling How the Model Generates Responses6:10
Gemini API Generation Parameters Explained10:12
Quiz for Gemini API Generation Parameters
Building a Chat Conversation7:53
Quiz for Building a Chat Conversation
Project: Building a Conversational Agent Using Gemini Pro7:17

Jupyter AI1:14
Python Version0:15
Introduction to Jupyter AI and Other Coding Companions3:39
Installing Jupyter AI4:15
Using Jupyter AI in JupyterLab12:26
Learn to run Jupyter AI in Jupyter Lab and connect to providers like OpenAI and Anthropic. Set up API keys and use Jupyter Note to generate code and explanations.
Setting Up Jupyter AI in Jupyter Notebook4:36
Set up and use Jupyter AI magic commands in notebooks to authenticate with OpenAI, load the Jupyter I magics extension, and list available models across providers.
Using Jupyter AI in Jupyter Notebook6:24
Using Interpolation for More Advanced Use Cases5:24
Using Jupyter AI with Other Providers and Models4:03

Intro to Prompt Engineering3:11
Master prompt engineering to design effective prompts for large language models, guiding tasks with context, using the Gemini API, and leveraging a helper function for high-quality outputs.
Tactic #1 - Position Instructions Clearly With Delimiters5:01
Tactic #2 - Provide Detailed Instructions for the Context, Outcome, or Length6:09
Tactic #3 - Specify the Response Format6:09
Tactic #4 - Few-Shot Prompting6:55
Tactic #5 - Specify the Steps Required to Complete a Task7:52
Tactic #6 - Give Models Time to "Think"4:32
Other Tactics for Better Prompting and Avoiding Hallucinations6:19
Prompt Engineering Summary2:13

Claude 3 Models: Haiku, Sonnet, Opus4:50
Explore the Claude 3 family: Opus, Sonnet, and Haiku, and their multimodal, vision-enabled capabilities with a 200k token context and cost-efficient Haiku.
Anthropic API Setup5:40
Generating Text from Text Prompts5:52
Learn to generate text from text prompts by making api requests to the cloud with the anthropic python client, including loading the anthropic api key and configuring a model.
Understanding the Assistant Role3:10
The System Prompt3:26
Streaming Responses from Claude3:12
Exploring Multimodal AI: Vision Capabilities12:52
Using Online Images as Input4:19
Vision Testing: Handwriting, Charts, and Visual Prompting9:59
Combining Multiple Images5:03

README0:27
While and continue Statements4:05
Explore how while loops work with the continue statement to skip iterations, print numbers divisible by 13 under 100, and avoid infinite loops caused by missing increments.
While and break Statements5:35
List Slicing and Iteration7:14
Explore Python list slicing and iteration, from start and stop defaults to stepping and reversing, to concatenation, for loops, and membership tests with in and not in.
List Comprehension - Part 16:02
Explore Python's list comprehension, part 1, a concise way to build a new list from an iterable, and compare doubling numbers with a for-loop to the one-line approach.
List Comprehension - Part 26:26
Working with Dictionaries10:27
JSON Data Serialization6:29
JSON Data Deserialization5:36
Assignment: JSON and Requests/REST API1:46
Assignment Answer: JSON and Requests/REST API3:54

Introduction to Streamlit4:41
Streamlit Main Concepts5:41
Displaying Data on the Screen: st.write() and Magic5:45
Widgets, Part 1: text_input, number_input, button5:11
Widgets, Part 2: checkbox, radio, select7:33
Widgets, Part 3: slider, file_uploader, camera_input, image8:28
Layout: Sidebar1:58
Layout: Columns4:32
Layout: Expander2:11
Learn how to use the expander layout as a multi-element container that users can expand or collapse, and add a bar chart and image using the label syntax.
Displaying a Progress Bar3:10
Learn to display a progress bar in Streamlit during extensive computations by updating a placeholder with each iteration, showing operation in progress, and signaling completion.
Session State7:59
Callbacks6:17

Requirements

Basic Python programming experience is required.
The Gemini API is only available in certain regions worldwide. Before enrolling, please verify that Gemini supports your region.
A valid phone number for Claude 3 API free credits.

Description

In this course, you'll learn about both Google's Gemini and Anthropic's Claude 3 API with Python.

**Fully updated for Gemini 1.5 Pro API!**

Welcome to the Gemini Era. Embrace the Gemini Pro Vision API with Python and Become a Pioneer in Multimodal AI

Prepare to master Google's Gemini Pro Vision API with Python and unleash the power of Google's most capable AI family into your applications.

By the end of this journey, you'll master the Gemini Pro API (1.5 included) and become a pro in LLM prompt engineering, equipped to create groundbreaking and intelligent Python applications using the Gemini API.

Get ready to join the forefront of multimodal AI innovation as we constantly update this course with the latest advancements, equipping you with the skills to thrive in the future.

This course on Google's Gemini Pro Vision API with Python covers everything you need to know about the Gemini family of models and about effective prompt engineering for LLMs.

You'll also learn how to use the Python API for the Anthropic's Claude 3 family of models: Opus, Sonnet and Haiku.

Become a pioneer shaping the technological landscape and reap the benefits of being an early adopter.

In today's world, AI is the key to unlock unprecedented productivity.

Embrace the Gemini Pro Vision API with Python, Google AI Studio, and advanced prompting tactics to stay ahead of the curve.

In this course, you'll learn by doing, with practical projects that will guide you in applying what you learn.

You'll also discover the best practices and tips for effective prompting for LLMs, such as using few examples, finding relevant context information, and exploring different prompt engineering techniques.

By the end of this course, you'll be able to:

Learn how to use Google's Gemini Pro [Vision] API with Python, the most advanced and versatile AI tool from Google
Create freeform and dynamic prompts with Gemini Pro Vision in Google AI Studio
Unlock the Power of Gemini 1.5 Pro API
Use the File API for prompting with media files (audio, video and more)
Generate text from text inputs using Gemini Pro API and Python
Stream model responses
Generate text from image and text inputs using Gemini Pro Vision API and Python
Control how the model generates responses using Gemini API generation parameters: temperature, top_k, top_p, stop sequences and more
Build custom chat conversational agents
Master the art of prompt engineering for LLMs and create effective and natural language queries for any task
You'll learn how to create web interfaces (front-ends) for your LLM apps using Streamlit
Learn how to use Anthropic's Claude 3 API with Python: API setup, generating text, streaming, Claude 3 vision capabilities, and more
Learn how to use Jupyter AI efficiently

This course is suitable for anyone who wants to learn how to use the Gemini Pro Vision API, Google AI Studio, Claude 3 API, and how to leverage the power of multimodal AI for various applications.

If you are ready to take your skills to the next level and master one of the most cutting-edge technologies in AI, enroll in this course today and start your journey to multimodal AI mastery!

Who this course is for:

Python programmers who want to integrate the Google's Gemini and Anthropic's Claude models into their applications.
Programmers looking to develop AI apps with cutting-edge AI (Google's Gemini and Anthropic's Claude 3) for free.
Any technical person interested in the most disruptive technology of this decade.

Learn Google's Gemini and Anthropic's Claude API with Python

What you'll learn

Explore related topics

Course content

Getting Started6 lectures • 26min

Deep Dive into Google Gemini Pro API12 lectures • 1hr 13min

Unlocking the Power of Gemini Pro API5 lectures • 27min

Jupyter AI9 lectures • 42min

Project: Talking With an Image6 lectures • 32min

Project: Building an AI-Powered Image Renaming Tool3 lectures • 17min

Prompt Engineering for Gemini API9 lectures • 48min

Deep Dive into Anthropic's Claude API10 lectures • 58min

[Appendix] Python Programming11 lectures • 58min

[Appendix] Building Front-ends for AI Apps With Streamlit12 lectures • 1hr 3min

Requirements

Description

Who this course is for: