diff --git a/01-IntroToGenAI/readme.md b/01-IntroToGenAI/readme.md index f52090d..690fc0b 100644 --- a/01-IntroToGenAI/readme.md +++ b/01-IntroToGenAI/readme.md @@ -4,7 +4,9 @@ Refresh your generative AI knowledge and understand the .NET tooling available t --- -**INSERT: LESSON 1 VIDEO** +[![Introduction to Generative AI](http://img.youtube.com/vi/SZvE_meBdvg/0.jpg)](http://www.youtube.com/watch?v=SZvE_meBdvg) + +_⬆️Click the image to watch the video⬆️_ ## What you'll learn in this lesson: diff --git a/02-SetupDevEnvironment/readme.md b/02-SetupDevEnvironment/readme.md index 53d5539..e5fc333 100644 --- a/02-SetupDevEnvironment/readme.md +++ b/02-SetupDevEnvironment/readme.md @@ -15,9 +15,11 @@ This lesson will guide you through setting up your development environment for t Let's dive in and set up your development environment! 🏃‍♂️ -## Which AI service should I use for this course? +[![Watch the Video Tutorial](https://img.youtube.com/vi/7kYoVRNQXyA/0.jpg)](https://youtu.be/7kYoVRNQXyA?feature=shared) + +_⬆️Click the image to watch the video⬆️_ -**INSERT: CHAT EXPLANATION VIDEO HERE** +## Which AI service should I use for this course? We provide instructions for setting up your development environment with GitHub Models, Azure OpenAI, and Ollama. You can choose the one that best fits your needs. We recommend using GitHub Models for this course, but you can use any of the three services. diff --git a/03-CoreGenerativeAITechniques/01-lm-completions-functions.md b/03-CoreGenerativeAITechniques/01-lm-completions-functions.md index 91bf63e..5f38607 100644 --- a/03-CoreGenerativeAITechniques/01-lm-completions-functions.md +++ b/03-CoreGenerativeAITechniques/01-lm-completions-functions.md @@ -6,7 +6,9 @@ In this lesson, we will explore the basics of building chat applications using l ## Text completions and chat -**INSERT: CHAT EXPLANATION VIDEO HERE** +[![Text completions and chat video](https://img.youtube.com/vi/Av1FCQf83QU/0.jpg)](https://youtu.be/Av1FCQf83QU?feature=shared) + +_⬆️Click the image to watch the video⬆️_ Text completions might be the most basic form of interaction with the language model in an AI application. A text completion is a single response generated by the model based on the input, or prompt, that is given to the model. @@ -104,7 +106,9 @@ while (true) ## Function calling -**INSERT: FUNCTIONS EXPLANATION VIDEO HERE** +[![function explainer video](https://img.youtube.com/vi/i84GijmGlYU/0.jpg)](https://youtu.be/i84GijmGlYU?feature=shared) + +_⬆️Click the image to watch the video⬆️_ When building AI applications you are not limited to just text-based interactions. It is possible to extend the functionality of the chatbot by calling pre-defined functions in your code based off user input. In other words, function calls serve as a bridge between the model and external systems. diff --git a/03-CoreGenerativeAITechniques/02-retrieval-augmented-generation.md b/03-CoreGenerativeAITechniques/02-retrieval-augmented-generation.md index b74e357..a131a8b 100644 --- a/03-CoreGenerativeAITechniques/02-retrieval-augmented-generation.md +++ b/03-CoreGenerativeAITechniques/02-retrieval-augmented-generation.md @@ -4,7 +4,9 @@ In this lesson learn how to use **Retrieval-Augmented Generation (RAG)** in your --- -**INSERT: LESSON 3 RAG VIDEO HERE** +[![RAG explainer video](https://img.youtube.com/vi/Av1FCQf83QU/0.jpg)](https://youtu.be/Av1FCQf83QU?feature=shared) + +_⬆️Click the image to watch the video⬆️_ Retrieval Augmented Generation (RAG) is a technique used to augment the response of a language model with information retrieved from a data store. diff --git a/03-CoreGenerativeAITechniques/03-vision-audio.md b/03-CoreGenerativeAITechniques/03-vision-audio.md index 0d8c6ad..d478bdd 100644 --- a/03-CoreGenerativeAITechniques/03-vision-audio.md +++ b/03-CoreGenerativeAITechniques/03-vision-audio.md @@ -6,7 +6,9 @@ In this lesson learn how vision AI allows your apps to generate and interpret im ## Vision -**INSERT: LESSON 3 VISION VIDEO HERE** +[![Vision AI explainer](https://img.youtube.com/vi/QXbASt1KXuw/0.jpg)](https://youtu.be/QXbASt1KXuw?feature=shared) + +_⬆️Click the image to watch the video⬆️_ Vision-based AI approaches are used to generate and interpret images. This can useful for a wide range of applications, such as image recognition, image generation, and image manipulation. Current models are multimodal, meaning they can accept a variety of inputs, such as text, images, and audio, and generate a variety of outputs. In this case, we are going to focus on image recognition. @@ -78,7 +80,9 @@ Here's a point I want to drive home. We're conversing with a language model, or ## Audio AI -**INSERT: LESSON 3 AUDIO VIDEO HERE** +[![Audio AI explainer video](https://img.youtube.com/vi/fuquPXRNqCo/0.jpg)](https://youtu.be/fuquPXRNqCo?feature=shared) + +_⬆️Click the image to watch the video⬆️_ Real-time audio techniques allow your apps to generate audio and transcribe it in real-time. This can be useful for a wide range of applications, such as voice recognition, speech synthesis, and audio manipulation. diff --git a/03-CoreGenerativeAITechniques/04-agents.md b/03-CoreGenerativeAITechniques/04-agents.md index 391ae79..62da84c 100644 --- a/03-CoreGenerativeAITechniques/04-agents.md +++ b/03-CoreGenerativeAITechniques/04-agents.md @@ -4,7 +4,9 @@ In this lesson learn to create an AI entity that... makes decisions and executes --- -**INSERT: LESSON 3 AGENT VIDEO HERE** +[![Agents explainer video](https://img.youtube.com/vi/Btkmw1Bosh0/0.jpg)](https://youtu.be/Btkmw1Bosh0?feature=shared) + +_⬆️Click the image to watch the video⬆️_ AI agents allow LLMs to evolve from assistants into entities capable of taking actions on behalf of users. Agents are even able to interact with other agents to perform tasks. Some of the key attributes of an agent include a level of **autonomy** allowing the agent to initiate actions based on their programming which leads to the ability for **decision-making** based on pre-defined objectives. They are also **adaptable** in that they learn and adjust to improve performance over time. diff --git a/04-PracticalSamples/readme.md b/04-PracticalSamples/readme.md index 5d3cd6e..1fa7cd6 100644 --- a/04-PracticalSamples/readme.md +++ b/04-PracticalSamples/readme.md @@ -22,7 +22,9 @@ See all the concepts you've learned in action in these real-world and practical - [Next steps](#next-steps) -**INSERT: LESSON 4 INTRO VIDEO HERE** +[![overall explainer video](https://img.youtube.com/vi/Ky4CACXJqR8/0.jpg)](https://youtu.be/Ky4CACXJqR8?feature=shared) + +_⬆️Click the image to watch the video⬆️_ ## eShopLite Demos @@ -34,6 +36,10 @@ The first demo, we show how to use the Semantic Kernel to enhance the search cap ### eShopLite with semantic search +[![eShop Semantic Search explainer video](https://img.youtube.com/vi/FlkruF6USro/0.jpg)](https://youtu.be/FlkruF6USro?feature=shared) + +_⬆️Click the image to watch the video⬆️_ + In eShopLite with semantic search, we use Semantic Kernel to enhance the search capabilities of the e-commerce application. Semantic Kernel helps us create a more robust search engine that can understand the context of the user's queries and provide more accurate results. For example, if a user searches for "do you have something for cooking", the search engine can understand that the user is looking for kitchenware and show the most relevant products, in context of our sample, it returns Camping Cookware. @@ -229,9 +235,13 @@ In the image, we can see the Application Insights dashboard, providing how the s > 💡 **Pro Tip**: For more information on eShopLite with Semantic Search, look at the repository to learn more: https://aka.ms/netaieshoplitesemanticsearch -### eShopLite with realtime analysis +### eShopLite with realtime audio + +[![eShop with real-time audio explainer video](https://img.youtube.com/vi/bx0hRNdr_bQ/0.jpg)](https://youtu.be/bx0hRNdr_bQ?feature=shared) -In eShopLite with real-time analysis, we use the real-time audio capabilities of GPT-4o to analyze the conversations between the customer and the chatbot, providing a more personalized and engaging experience. For example, if a customer asks for a product recommendation, the chatbot can analyze the customer's request in real-time and provide a more accurate and relevant response. +_⬆️Click the image to watch the video⬆️_ + +In eShopLite with real-time audio, we use the real-time audio capabilities of GPT-4o to analyze the conversations between the customer and the chatbot, providing a more personalized and engaging experience. For example, if a customer asks for a product recommendation, the chatbot can analyze the customer's request in real-time and provide a more accurate and relevant response. > 🧑‍💻**Sample**: Check out the [eShopLite semantic search sample](https://aka.ms/netaieshopliterealtimechat) @@ -307,6 +317,10 @@ Each tool is added to the session options, and the conversation session is start ## Creative Writer Agent +[![Creative Writing Agent explainer video](https://img.youtube.com/vi/ZjZWilI_5z8/0.jpg)](https://youtu.be/ZjZWilI_5z8?feature=shared) + +_⬆️Click the image to watch the video⬆️_ + Agents are a big topic in the current AI landscape, and to demonstrate their capabilities, we'll use the Creative Writer Agent, a tool that can generate creative and engaging text based on the user's input, helping to write researched, specific, and engaging content. > 🧑‍💻**Sample**: Check out the [Creative Writing Agent sample code](https://aka.ms/netaicreativewriter) diff --git a/README.md b/README.md index 34f92cd..a71ccb0 100644 --- a/README.md +++ b/README.md @@ -14,6 +14,8 @@ [![Azure AI Community Discord](https://dcbadge.vercel.app/api/server/ByRwuEEgH4)](https://discord.com/invite/ByRwuEEgH4) +![Generative AI for Beginners .NET logo](./images/main-logo.jpg) + Welcome to **Generative AI for Beginners .NET**, the hands-on course for .NET developers diving into the world of Generative AI! This isn’t your typical “here’s some theory, good luck” course. This repository is all about **real-world applications** and **live coding** to empower .NET developers to take full advantage of Generative AI. diff --git a/images/main-logo.jpg b/images/main-logo.jpg new file mode 100644 index 0000000..50f9330 Binary files /dev/null and b/images/main-logo.jpg differ