AI Engineering

Overview

Syllabus

Courses

• 0 reviews

  1 hour 2 minutes

  View details

  Upon completion this course, learners will obtain the fundamental concepts and practical workings of OpenAI's Assistant APIs, enabling them to build intelligent, conversational agents faster than ever previously possible. Learners will begin by understanding how the API works by getting hands-on experience in creating an Assistant, initiating Threads, crafting Messages, and Running the assistant in a live environment. The final lessons encourage learners to bring together all the learned components in a capstone project, reinforcing their understanding and showcasing their new-found capabilities. This course is perfect for developers, tech enthusiasts, and AI practitioners aspiring to master the intricacies of OpenAI's cutting-edge technologies.
• 0 reviews

  2 hours 3 minutes

  View details

  This course is meticulously designed to navigate learners through the process of building AI applications utilizing the LangChain library. This course begins with an introduction by LangChain's lead maintainer, Jacob Lee, providing a foundational understanding directly from an expert's perspective. As the course unfolds, learners will work through app flow diagrams, setup of databases with Supabase, text processing techniques, and the creation of intricate prompt templates. They will learn to develop starter code, add logic chains for retrieval and processing, and design a user interface for their applications. Each module is crafted to enhance the learner's coding skills, with super challenges that test their ability to apply learned concepts in complex scenarios. The course culminates with a solo project where learners build a personal assistant app, solidifying their coding expertise and understanding of AI app development. The unique aspect of this course lies in its specific focus on LangChain, offering hands-on experience with this cutting-edge tool in the AI landscape, and preparing learners for the next generation of AI app development.
• 0 reviews

  1 hour 4 minutes

  View details

  Upon completing this course, learners will understand the distinctions between open-source and closed-source frameworks and their impact on development. The course offers hands-on experience with HuggingFace.js, enabling learners to perform inference tasks and apply AI solutions in real scenarios. Participants will gain the skills to implement text-to-speech and image transformations using HuggingFace's libraries. The focus on the HuggingFace.js interface provides direct access to leading open-source AI tools, standing out in its practical approach. A key section is on navigating the HuggingFace.js Hub, where learners discover how to access free models, essential for cost-effective AI deployment. The course culminates with insights into AI’s future in browser-based applications, preparing learners for the next wave of AI integration. What distinguishes this course is its blend of theoretical knowledge and practical application, equipping learners to effectively utilize AI models in their projects. It's ideal for those aiming to pioneer in open-source AI application development.
• 0 reviews

  2 hours 27 minutes

  View details

  This course delves into the intricate process of ReAct prompting, a critical component in the design of AI agents. Through dedicated modules, learners will explore the nuanced approach to crafting prompts that effectively guide AI responses in a reactive manner. This technique is essential for developing AI agents that can interact dynamically with users and environments. The curriculum offers an in-depth examination of ReAct prompting, teaching students how to plan and construct prompts that lead to desired actions and responses from the AI. Participants will learn the principles of prompt engineering, which combines elements of psychology, linguistics, and data science to shape the AI's interactions. In addition to theoretical knowledge, the course emphasizes practical experience. Students will engage in hands-on exercises to refine their skills in building ReAct prompts, understanding the "loop" mechanism that enables continuous and context-aware interactions, and setting up code that facilitates these sophisticated dialogues. By focusing on ReAct prompting, the course prepares learners to create AI agents that are not only responsive but also proactive in their engagements, resulting in more natural and effective human-AI interactions. This specialized training is particularly beneficial for those interested in enhancing user experience and creating more intuitive AI systems.
• 0 reviews

  2 hours

  View details

  Upon completing the this course, learners will have established a robust foundation in AI principles and hands-on proficiency with AI tools and APIs. They will learn the art of crafting and manipulating AI models, enabling them to integrate AI into applications with confidence. This course stands out by offering a detailed exploration of AI engineering, from the basics to deeper techniques like the "Few Shot" approach and the creation of images with the latest DALL·E 3 API. Participants will also learn to navigate AI safety and ethical considerations, ensuring responsible use of AI technology. With a blend of theoretical knowledge and practical application, this course is uniquely positioned to empower learners to become innovative problem solvers in the AI domain.
• 0 reviews

  2 hours 6 minutes

  View details

  This course offers an advanced journey into the realm of AI engineering, focusing on the creation, utilization, and management of embeddings in vector databases. Learners will begin by grasping the concept of embeddings and their pivotal role in AI's interpretative processes. The course progresses through practical exercises on setting up environment variables, creating embeddings, and integrating these into vector databases with tools like Supabase. Participants will engage in challenges that test their ability to pair text with corresponding embeddings, manage semantic searches, and use similarity searches to query embeddings. They will also learn to create conversational responses with OpenAI and handle complex tasks like chunking text from documents. What makes this course unique is its comprehensive coverage of both the theoretical aspects of AI embeddings and the practical skills needed to implement these concepts in real-world applications. By the end of the course, learners will not only have mastered the technical knowledge but will also have developed a proof of concept for an AI chatbot, ready to tackle advanced AI engineering challenges.
• 0 reviews

  3 hours 59 minutes

  View details

  Dive into deploying secure and robust applications with our Cloudflare course. Learn to manage API requests with Cloudflare workers, boost app strength with an AI Gateway, and launch websites using Cloudflare Pages. This hands-on course also teaches you to refine error handling for smoother user experiences. Build practical skills in using Cloudflare’s features to secure APIs, enhance sites with AI, and ensure reliability. By the end of the course, you'll be skilled at using Cloudflare to boost your applications' security and performance, ready to solve real-world problems.
• 0 reviews

  1 hour 21 minutes

  View details

  This course teaches you how to generate and manipulate high-quality images with Open AI's Dall-e text-to-image model. You'll then discover how to get the most out of the model using the Open AI API. Finally, you’ll integrate GPT-4 with Vision into your AI-powered apps to carry out comprehensive image analysis, including object detection, to answer questions about an image you upload, for example! Why use AI to generate images? First, it's efficient. AI can save you time and resources compared to traditional methods. Second, AI allows you to create unique images that haven't been seen before, ensuring that your work is original and stands out. Finally, it allows for creativity without using real people, enabling you to depict diverse, imaginary individuals in your visuals. By the end of this course, you'll have gotten to grips with perfecting your image generation prompts, generating images in different formats and styles, editing images, and more! Moreover, you’ll have a solid understanding of AI multimodality - systems that can process input from and produce outputs across different data formats, including text, images, audio, and video. Ready to take the next step in AI? Let's go!

Taught by

Bob Ziroll, Guil Hernandez, Per Harald Borgen and Tom Chant