Apply pencil edits for blocking issues in PR review

Author: Court72

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

@@ -28,10 +28,10 @@ You can use RAG for chatbots, search enhancement, and content creation and summa
 
 The RAG workflow is built on four essential components that work together:
 
-1. **Embeddings** - Convert text into mathematical vectors that capture meaning
-2. **Vector databases** - Store and organize these vectors for fast searching
-3. **Search and retrieval** - Find the most relevant information based on user queries
-4. **Prompt augmentation** - Combine retrieved information with the original question
+- **Embeddings** - Convert text into mathematical vectors that capture meaning
+- **Vector databases** - Store and organize these vectors for fast searching
+- **Search and retrieval** - Find the most relevant information based on user queries
+- **Prompt augmentation** - Combine retrieved information with the original question
 
 Think of these components as building blocks: embeddings translate everything into a common language, vector databases organize this information, search and retrieval find what's needed, and prompt augmentation puts it all together for the AI to use.
 
@@ -67,9 +67,9 @@ After finding the most relevant documents, the RAG system combines this informat
 
 The augmentation process looks like this:
 
-- 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?"
+1. Start with the user's question: "What's our vacation policy?"
+1. Add retrieved context: Include relevant excerpts from your HR documents
+1. 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.
@@ -81,4 +81,4 @@ The complete RAG workflow combines all the components we've reviewed into a unif
 
 The key mechanism is **in-context learning** - instead of retraining the LLM, you provide relevant information as context in each prompt, allowing the LLM to generate informed responses without permanent modification.
 
-Advanced implementations might include feedback loops to refine results when the initial response doesn't meet quality thresholds.
+Advanced implementations might include feedback loops to refine results when the initial response doesn't meet quality thresholds.