Update readme.md

01-IntroToGenAI/readme.md

@@ -84,7 +84,7 @@ Additionally, the library supports middleware components for functionalities lik
 
 ![*Figure: Microsoft.Extensions.AI (MEAI) library.*](./images/meai-architecture-diagram.png)
 
-Using an unified API, MEAI allows developers to work with different AI services, such as Azure AI Inference, Ollama, and OpenAI, in a consistent manner. This simplifies the integration of AI models into .NET applications, adding flexibility for developers to choose the best AI services for their projects and specific requirements.
+Using a unified API, MEAI allows developers to work with different AI services, such as Azure AI Inference, Ollama, and OpenAI, in a consistent manner. This simplifies the integration of AI models into .NET applications, adding flexibility for developers to choose the best AI services for their projects and specific requirements.
 
 > 🏎️ **Quick start**: For a quick start with MEAI, [check out the blog post](https://devblogs.microsoft.com/dotnet/introducing-microsoft-extensions-ai-preview/).
 >

03-CoreGenerativeAITechniques/02-retrieval-augmented-generation.md

@@ -23,7 +23,7 @@ There are 2 main phases in a RAG architecture: **Retrieval** and **Generation**.
 
 ## Embeddings!
 
-We've held off as long as we could to introduce the concept of embeddings. In the retrieval phase of RAG we do not want to pass the entire data store to the model to generate the response. We only want to grab the most relevant information. 
+We've held off as long as we could to introduce the concept of embeddings. In the retrieval phase of RAG we do not want to pass the entire data store to the model to generate the response. We only want to grab the most relevant information.
 
 So we need a way to compare the user's prompt with the data in the knowledge store. So we can pull out the minimum amount of information needed to augment the prompt.
 
@@ -33,7 +33,7 @@ You may have heard of vector databases. These are databases that store data in a
 
 ## Implementing RAG
 
-We'll use the Microsoft.Extension.AI along with the [Microsoft.Extensions.VectorData](https://www.nuget.org/packages/Microsoft.Extensions.VectorData.Abstractions/) and [Microsoft.SemanticKernel.Connectors.InMemory](https://www.nuget.org/packages/Microsoft.SemanticKernel.Connectors.InMemory) libraries to implement RAG below. 
+We'll use the Microsoft.Extension.AI along with the [Microsoft.Extensions.VectorData](https://www.nuget.org/packages/Microsoft.Extensions.VectorData.Abstractions/) and [Microsoft.SemanticKernel.Connectors.InMemory](https://www.nuget.org/packages/Microsoft.SemanticKernel.Connectors.InMemory) libraries to implement RAG below.
 
 > 🧑‍💻**Sample code:** You can follow along with the [sample code here](../03-CoreGenerativeAITechniques/src/RAGSimple-02MEAIVectorsMemory/).
 > 

03-CoreGenerativeAITechniques/readme.md

@@ -7,10 +7,10 @@ In this lesson you'll learn some practical skills for building AI-enabled .NET a
 #### What you'll learn in this lesson:
 
 - 🌟 LLM completions and chat flows
-- 🔗 Functions & plugins with LLMs  
-- 🔎 Retrieval-Augmented Generation (RAG)  
-- 👀 Vision-based AI approaches  
-- 🔊 Audio creation and transcription  
+- 🔗 Functions & plugins with LLMs
+- 🔎 Retrieval-Augmented Generation (RAG)
+- 👀 Vision-based AI approaches
+- 🔊 Audio creation and transcription
 - 🧩 Agents & assistants
 
 For this lesson, we will subdivide the content into the following sections: