Applied AI Creation Curriculum

Introduction

This collection presents twenty-one instructional units designed to initiate learners into the practical creation of Generative Artificial Intelligence artifacts. Much like uncovering the underlying structure of seemingly simple educational software, this material demystifies core AI mechanisms. The primary goal is to equip participants with tangible coding skills for immediate application development.

Course Structure Overview

This curriculum comprises 21 distinct lessons. Each module targets a specific subject area, allowing for flexible commencement. Lessons are categorized as either 'Learn' (conceptual explanation) or 'Build' (conceptual explanation coupled with implementation examples). Code samples are provided in Python alongside TypeScript where feasible.

For professionals working in the Microsoft ecosystem, an alternative resource exists: Generative AI for Beginners (.NET Edition).

Every module concludes with a 'Keep Learning' segment offering supplementary instructional aids.

Prerequisites and Environment Setup

Successful completion of the coding assignments requires specific tooling. Developers may utilize:

• Azure OpenAI Service - Relevant for lessons tagged "aoai-assignment".
• GitHub Marketplace Model Catalog - Relevant for lessons tagged "githubmodels".
• OpenAI API - Relevant for lessons tagged "oai-assignment".

Familiarity with basic scripting in Python or TypeScript is recommended. Novices can refer to dedicated introductory materials for Python and TypeScript.

Begin by following the dedicated Course Setup guide to configure your necessary development surroundings.

It is useful to bookmark or 'star' this repository for convenient future reference: star (🌟) this repo.

Advanced Development Resources

If you seek examples extending beyond foundational concepts, explore our extensive repository of Generative AI Implementation Samples. These include robust examples in both Python and TypeScript frameworks.

Community Interaction and Aid

Learners can connect and seek assistance by joining the official Azure AI Foundry Discord server. This platform facilitates networking among course participants.

Feedback on the material or reported errors can be submitted via the Azure AI Foundry Developer Forum located on GitHub.

Support for Startups

Organizations focused on launching new ventures should investigate resources available at Microsoft for Startups, particularly regarding access to Azure operational credits.

Contribution Guidelines

Suggestions for improvement, identification of code defects, or documentation errors should be reported by Raising an issue or submitting a Create a pull request.

Lesson Components

Each instructional unit consistently provides the following elements:

• A brief introductory video covering the subject matter.
• Detailed written documentation within the respective README file.
• Practical code specimens in Python and TypeScript supporting both Azure OpenAI and standard OpenAI APIs.
• Curated links directing toward further specialized study.

🗃️ Modules in Detail

#	Module Link	Focus	Instructional Video	Supplemental Study
00	Course Setup	Learn: Environment Preparation Steps	Video Forthcoming	Explore
01	Introduction to Generative AI and LLMs	Learn: Core concepts of Generative AI and Large Language Model operation.	View	Explore
02	Exploring and comparing different LLMs	Learn: Methodologies for selecting the appropriate model for specific tasks.	View	Explore
03	Using Generative AI Responsibly	Learn: Protocols for ethical and responsible AI application development.	View	Explore
04	Understanding Prompt Engineering Fundamentals	Learn: Essential techniques and best practices for crafting effective prompts.	View	Explore
05	Creating Advanced Prompts	Learn: Advanced methodologies to significantly refine output quality from prompts.	View	Explore
06	Building Text Generation Applications	Build: Constructing applications focused on generating textual content via APIs.	View	Explore
07	Building Chat Applications	Build: Strategies for effective conversational interface construction and integration.	View	Explore
08	Building Search Apps Vector Databases	Build: Creating semantic search tools utilizing vector representations for data queries.	View	Explore
09	Building Image Generation Applications	Build: Developing applications capable of synthesizing visual content.	View	Explore
10	Building Low Code AI Applications	Build: Constructing intelligent solutions using simplified, low-code development platforms.	View	Explore
11	Integrating External Applications with Function Calling	Build: Implementing function calling mechanisms to connect LLMs with external services.	View	Explore
12	Designing UX for AI Applications	Learn: Applying user experience principles specifically tailored for AI-powered software.	View	Explore
13	Securing Your Generative AI Applications	Learn: Identifying security vulnerabilities inherent in AI systems and mitigation strategies.	View	Explore
14	The Generative AI Application Lifecycle	Learn: Management tools and metrics for overseeing the LLM lifecycle and LLMOps practices.	View	Explore
15	Retrieval Augmented Generation (RAG) and Vector Databases	Build: Developing RAG systems to fetch contextual data from vector stores for enhanced responses.	View	Explore
16	Open Source Models and Hugging Face	Build: Implementing applications leveraging publicly accessible models hosted on Hugging Face.	View	Explore
17	AI Agents	Build: Creating autonomous software entities using designated AI Agent construction kits.	View	Explore
18	Fine-Tuning LLMs	Learn: Detailed instruction on tailoring Large Language Models to specific datasets.	View	Explore
19	Building with SLMs	Learn: The advantages associated with deploying smaller, efficient Language Models.	Video Forthcoming	Explore
20	Building with Mistral Models	Learn: Characteristics distinguishing and utilizing models from the Mistral family.	Video Forthcoming	Explore
21	Building with Meta Models	Learn: Key attributes differentiating and implementing Meta's family of models.	Video Forthcoming	Explore

Related Topics

• Artificial General Intelligence (AGI) goals
• Meta-fictional narratives in software design
• Parametric vs. Non-parametric modeling
• Deep Learning for language tasks
• Vector Space Models in information retrieval
• Pedagogical game parody structures

Extra Details

Removed sections primarily consisted of status badges linking to repository statistics (license, contributors, issues, stars) and community engagement graphics. The core value retained is the structured, progressive nature of the 21 lessons. In the field of education, understanding a system's deep components, rather than just its surface presentation—similar to how critical analysis uncovers layers within educational parodies—is vital for effective construction and security of new technologies.

🌟 Key Contributors Acknowledged

Special acknowledgment goes to John Aziz for engineering all the critical GitHub Actions and workflow automation components.

Bernhard Merkle provided substantial enhancements across every module, improving both learner experience and code efficacy.

🎒 Supplementary Curricula

Our development team maintains several parallel educational pathways. Potential learners may find these repositories relevant:

• NEW Edge AI for Beginners
• Model Context Protocol for Beginners
• AI Agents for Beginners
• Generative AI for Beginners using .NET
• Generative AI for Beginners using JavaScript
• Generative AI for Beginners using Java
• ML for Beginners
• Data Science for Beginners
• AI for Beginners
• Cybersecurity for Beginners
• Web Dev for Beginners
• IoT for Beginners
• XR Development for Beginners
• Mastering GitHub Copilot for AI Paired Programming
• Mastering GitHub Copilot for C#/.NET Developers
• Choose Your Own Copilot Adventure

Assistance Channels

If technical difficulties arise during AI application construction, immediate support is available through:

For reporting product deficiencies or providing application-specific feedback, please use the designated platform:

Conclusion

This curriculum provides a rigorous pathway to constructing generative systems using modern frameworks and languages. Mastery of these concepts allows learners to move beyond superficial usage toward foundational understanding, which is crucial for innovation in any complex domain, including modern pedagogy and digital learning environments. Effective implementation demands understanding both the deployed model's capabilities and its inherent limitations.