Fixes

Author: theresa-i

learn-pr/wwl-data-ai/multistage-reasoning-azure-databricks/includes/01-introduction.md

@@ -1,9 +1,9 @@
-**Large Language Models** (**LLMs**) are advanced artificial intelligence systems designed to understand and generate human-like text based on vast amounts of data. These models, such as GPT-4 and Llama, revolutionized natural language processing by enabling machines to perform tasks like translation, summarization, and even creative writing with remarkable accuracy.
+While Large Language Models excel at many tasks, they often struggle with complex reasoning that requires multiple steps or different types of analysis. Traditional approaches ask LLMs to solve everything at once, which can lead to errors in logic and inference.
 
-However, despite their impressive capabilities, LLMs often face challenges when it comes to complex reasoning tasks. Traditional methods encourage LLMs to plan and solve problems independently or to sample extensive reasoning chains, which can lead to conceptual and inferential fallacies.
-
-To address these limitations, you can use **multi-stage reasoning systems**. These systems break down complex problems into *multiple stages or steps*, with each stage focusing on a specific reasoning task. The output of one stage serves as the input for the next, allowing for a more structured and systematic approach to problem-solving.
+**Multi-stage reasoning systems** address these limitations by breaking complex problems into sequential steps. Each stage focuses on a specific reasoning task, with the output of one stage serving as input for the next. This structured approach reduces errors and improves the reliability of complex problem-solving.
 
 :::image type="content" source="../media/model-system.png" alt-text="Diagram illustrating the difference between using one complex model or building a multi-stage reasoning system.":::
 
-In Azure Databricks, you can create multi-stage reasoning systems using popular libraries. When you combine the computing power of Apache Spark, the reliable data storage of Delta Lake, and advanced machine learning libraries, Databricks makes it easy to efficiently process complex tasks.
+The diagram illustrates this difference: instead of using one complex model to handle everything, a multi-stage system uses specialized components that work together systematically. Each stage can be optimized for its specific task, leading to better overall results.
+
+In this module, you'll explore how to work with multi-stage reasoning systems using Azure Databricks. Azure Databricks provides access to popular libraries like LangChain, LlamaIndex, Haystack, and DSPy that support building these systems. You'll learn about these libraries' key components and understand how they can be applied to implement multi-stage reasoning workflows.

learn-pr/wwl-data-ai/retrieval-augmented-generation-azure-databricks/includes/2-workflow.md

@@ -67,9 +67,9 @@ After finding the most relevant documents, the RAG system combines this informat
 
 The augmentation process looks like this:
 
-1. Start with the user's question: "What's our vacation policy?"
-2. Add retrieved context: Include relevant excerpts from your HR documents
-3. Create augmented prompt: "Based on these HR policy documents: [retrieved content], what's our vacation policy?"
+- Start with the user's question: "What's our vacation policy?"
+- Add retrieved context: Include relevant excerpts from your HR documents
+- Create augmented prompt: "Based on these HR policy documents: [retrieved content], what's our vacation policy?"
 The LLM now has both the user's question **and** the specific information needed to answer it accurately. This is called "in-context learning" because the LLM learns from the context provided in the prompt rather than from its original training data.
 
 In the final step, the augmented prompt is sent to the Large Language Model (LLM), which generates a response based on both the question and the retrieved information. The LLM can include citations of the original sources, allowing users to verify where the information came from.

learn-pr/wwl-data-ai/retrieval-augmented-generation-azure-databricks/includes/4-vector-search.md

@@ -36,7 +36,7 @@ There are two main options for implementing vector search in Azure Databricks: v
 
 A vector database is a specialized database optimized to store and retrieve embeddings - those vectors with hundreds or thousands of numbers that represent meaning. Like traditional databases, vector databases use indices (organized structures that speed up searches) to quickly find relevant data, but these vector indices are designed to find mathematically similar vectors rather than exact matches. In RAG applications, vector databases primarily store text embeddings - vectors that represent the semantic meaning of your document chunks - along with metadata about each chunk (like source document, page numbers, or categories).
 
-:::image type="content" source="../media/matched-query.png" alt-text="Vector space visualization showing both document and query vectors as dots. A relevant document vector is positioned close to the query vector.":::
+:::image type="content" source="../media/matched-query.png" alt-text="Diagram of vector space visualization showing both document and query vectors as dots. A relevant document vector is positioned close to the query vector.":::
 
 This visualization shows how vectors work in practice. Each dot represents a vector - the blue dots are document chunk embeddings stored in the vector database, and the orange dot is a query vector. The image labels "Relevant document" and "Query" indicate vectors that are close together in the mathematical space, showing similarity. When you search, the database finds document vectors nearest to your query vector.