Merge pull request #3145 from madeline-underwood/sem

Sem reviewed

Author: pareenaverma

content/learning-paths/servers-and-cloud-computing/qdrant-on-axion/_index.md

@@ -2,10 +2,6 @@
 title: Build Semantic Search and Chatbot Retrieval Systems with Qdrant on Google Cloud C4A Axion processors
 description: Learn how to deploy Qdrant on Google Cloud C4A Axion processors, generate vector embeddings with Sentence Transformers, and build a semantic search and chatbot retrieval system on Arm-based infrastructure.
 
-draft: true
-cascade:
-    draft: true
-    
 minutes_to_complete: 30
 
 who_is_this_for: This is an introductory topic for developers, data engineers, and platform engineers who want to build semantic search systems and chatbot retrieval pipelines on Arm64-based Google Cloud C4A Axion processors using the Qdrant vector database.

content/learning-paths/servers-and-cloud-computing/qdrant-on-axion/architecture.md

@@ -1,14 +1,16 @@
 ---
-title: Architecture
+title: Understand the vector search architecture
 weight: 8
 
 ### FIXED, DO NOT MODIFY
 layout: learningpathall
 ---
 
+## How vector search enables intelligent retrieval
+
 In this section, you explore the architecture behind the chatbot retrieval system built using Qdrant on Google Axion Arm-based infrastructure.
 
-This architecture demonstrates how modern AI systems perform **semantic similarity search** to retrieve relevant information from stored knowledge.
+The architecture demonstrates how modern AI systems perform **semantic similarity search** to retrieve relevant information from stored knowledge.
 
 Unlike traditional keyword search systems, vector databases allow applications to retrieve information based on **semantic meaning and contextual similarity**.
 
@@ -88,7 +90,7 @@ This process enables the chatbot to understand intent and meaning, rather than r
 
 ## Benefits of this architecture
 
-This design provides several advantages:
+The design provides several advantages:
 
 - semantic search instead of keyword matching
 - scalable knowledge retrieval
@@ -97,7 +99,7 @@ This design provides several advantages:
 
 ## Running on Axion
 
-This example demonstrates that Axion Arm infrastructure can efficiently run vector search workloads.
+The example demonstrates that Axion Arm infrastructure can efficiently run vector search workloads.
 
 - energy-efficient compute
 - scalable cloud infrastructure

content/learning-paths/servers-and-cloud-computing/qdrant-on-axion/background.md

@@ -1,10 +1,14 @@
 ---
-title: Get started with Qdrant on Google Axion C4A
+title: Understand vector search with Qdrant on Google Axion
 weight: 2
 
 layout: "learningpathall"
 ---
 
+## Why vector search on Google Axion C4A
+
+Qdrant is an open-source vector database designed for efficient similarity search and high-performance vector indexing. Running Qdrant on Google Axion C4A Arm-based infrastructure enables efficient execution of AI and vector search workloads. Axion processors, based on the Arm Neoverse V2 architecture, provide high performance and improved energy efficiency for modern cloud-native applications and data services.
+
 ## Explore Axion C4A Arm instances in Google Cloud
 
 Google Axion C4A is a family of Arm-based virtual machines built on Google’s custom Axion CPU, which is based on Arm Neoverse-V2 cores. Designed for high-performance and energy-efficient computing, these virtual machines offer strong performance for data-intensive and analytics workloads such as big data processing, in-memory analytics, columnar data processing, and high-throughput data services.
@@ -15,14 +19,10 @@ These characteristics make Axion C4A instances well-suited for modern analytics
 
 To learn more, see the Google blog [Introducing Google Axion Processors, our new Arm-based CPUs](https://cloud.google.com/blog/products/compute/introducing-googles-new-arm-based-cpu).
 
-## Explore Qdrant Vector Search on Google Axion C4A (Arm Neoverse V2)
-
-Qdrant is an open-source vector database designed for efficient similarity search and high-performance vector indexing. It enables applications to store and retrieve embeddings—numerical representations of data such as text, images, or audio—allowing systems to perform semantic search and AI-powered retrieval.
+## Qdrant for semantic search and AI retrieval
 
 Vector databases like Qdrant are commonly used in modern AI systems to support applications such as semantic search, recommendation systems, anomaly detection, and Retrieval-Augmented Generation (RAG) pipelines. By storing embeddings and performing nearest-neighbor search, Qdrant allows applications to retrieve the most relevant information based on semantic meaning rather than simple keyword matching.
 
-Running Qdrant on Google Axion C4A Arm-based infrastructure enables efficient execution of AI and vector search workloads. Axion processors, based on the Arm Neoverse V2 architecture, provide high performance and improved energy efficiency for modern cloud-native applications and data services.
-
 Using Qdrant on Axion allows you to achieve:
 
 - High-performance vector similarity search for AI applications

content/learning-paths/servers-and-cloud-computing/qdrant-on-axion/chatbot-usecase.md

@@ -1,18 +1,18 @@
 ---
-title: Chatbot Use Case with Qdrant
+title: Build a chatbot with Qdrant on Axion
 weight: 7
 
 ### FIXED, DO NOT MODIFY
 layout: learningpathall
 ---
 
-## Overview
+## Create a knowledge retrieval chatbot
 
 In this section, you build a simple **chatbot-style knowledge retrieval system** using the Qdrant vector database running on Google Axion Arm-based infrastructure.
 
 The chatbot retrieves relevant knowledge by performing **semantic similarity search** against stored vector embeddings.
 
-This architecture represents the **retrieval component of Retrieval-Augmented Generation (RAG) systems**, commonly used in modern AI assistants and enterprise knowledge platforms.
+The architecture represents the **retrieval component of Retrieval-Augmented Generation (RAG) systems**, commonly used in modern AI assistants and enterprise knowledge platforms.
 
 The chatbot uses:
 
@@ -99,7 +99,7 @@ The output is similar to:
 }
 ```
 
-This confirms the vector collection has been created successfully.
+The output confirms the vector collection has been created successfully.
 
 ## Create chatbot script
 

content/learning-paths/servers-and-cloud-computing/qdrant-on-axion/ingest-vectors.md

@@ -1,11 +1,13 @@
 ---
-title: Generate and Index Vectors
+title: Generate and index vector embeddings
 weight: 5
 
 ### FIXED, DO NOT MODIFY
 layout: learningpathall
 ---
 
+## Create vector embeddings from text
+
 In this section, you generate vector embeddings from sample text data and store them in the **Qdrant vector database**.
 
 Embeddings are numerical vector representations of data such as text, images, or audio. These vectors capture semantic meaning, allowing applications to perform similarity search and retrieve the most relevant results.
@@ -14,7 +16,7 @@ Using **Sentence Transformers**, you convert text into embeddings and store them
 
 ## Architecture overview
 
-This stage of the workflow focuses on embedding generation and vector storage.
+The workflow focuses on embedding generation and vector storage.
 
 ```text
 Text Documents
@@ -59,7 +61,7 @@ mkdir qdrant-rag-demo
 cd qdrant-rag-demo
 ```
 
-This directory will contain the Python scripts used to generate embeddings and query the vector database.
+The directory will contain the Python scripts used to generate embeddings and query the vector database.
 
 ## Create the ingestion script
 
@@ -108,7 +110,7 @@ print("Documents indexed successfully in Qdrant")
 
 ### What this script does
 
-This script performs several important operations:
+The script performs several important operations:
 
 - Connects to the Qdrant API
 - Creates a vector collection
@@ -128,7 +130,7 @@ The output is similar to:
 Documents indexed successfully in Qdrant!
 ```
 
-This confirms that the vectors have been successfully inserted into the database.
+The output confirms that the vectors have been successfully inserted into the database.
 
 ## Verify the vector collection
 

content/learning-paths/servers-and-cloud-computing/qdrant-on-axion/install-qdrant.md

@@ -1,11 +1,13 @@
 ---
-title: Install and Run Qdrant
+title: Install and run Qdrant on Axion
 weight: 4
 
 ### FIXED, DO NOT MODIFY
 layout: learningpathall
 ---
 
+## Prepare the vector database environment
+
 In this section, you prepare a SUSE Linux Enterprise Server (SLES) arm64 virtual machine and deploy **Qdrant**, an open-source vector database designed for efficient similarity search and vector indexing.
 
 Qdrant enables applications to store and retrieve embeddings — numerical vector representations of data such as text, images, and audio. These embeddings allow applications to perform **semantic search and AI-powered retrieval**.
@@ -14,7 +16,7 @@ Running Qdrant on **Google Axion Arm-based infrastructure** enables efficient ex
 
 ## Architecture overview
 
-This architecture represents a simple vector search system where embeddings are generated and stored in Qdrant, enabling fast semantic similarity queries.
+The deployment creates a simple vector search system where embeddings are generated and stored in Qdrant, enabling fast semantic similarity queries.
 
 ```text
 SUSE Linux Enterprise Server (arm64)

content/learning-paths/servers-and-cloud-computing/qdrant-on-axion/instance.md

@@ -1,12 +1,12 @@
 ---
-title: Create a Google Axion C4A arm64 virtual machine on GCP
+title: Create a Google Axion C4A Arm virtual machine
 weight: 3
 
 ### FIXED, DO NOT MODIFY
 layout: learningpathall
 ---
 
-## Provision a Google Axion C4A arm64 virtual machine
+## Provision Axion infrastructure for Qdrant
 
 In this section you'll create a Google Axion C4A arm64 virtual machine on Google Cloud Platform. You'll use the `c4a-standard-4` machine type, which provides 4 vCPUs and 16 GB of memory. This virtual machine hosts your Qdrant applications.
 
@@ -45,7 +45,7 @@ A new browser window opens with a terminal connected to your VM.
 
 ![Browser-based SSH terminal window with black background showing Linux command prompt and Google Cloud branding at top#center](images/gcp-shell.png "Terminal session connected to the VM")
 
-## What you've learned and what's next
+## Summary
 
 In this section:
 

content/learning-paths/servers-and-cloud-computing/qdrant-on-axion/semantic-search.md

@@ -1,21 +1,23 @@
 ---
-title: Perform Semantic Search
+title: Query vector embeddings with semantic search
 weight: 6
 
 ### FIXED, DO NOT MODIFY
 layout: learningpathall
 ---
 
+## Implement semantic similarity queries
+
 In this section, you query the Qdrant vector database using **semantic similarity search**.
 
 Unlike traditional keyword search, semantic search compares vector embeddings to identify the most relevant results based on **meaning and context** rather than exact keyword matches.
 
-This capability enables AI applications such as chatbots, recommendation systems, and knowledge retrieval platforms.
+Semantic search enables AI applications such as chatbots, recommendation systems, and knowledge retrieval platforms.
 
 
 ## Architecture overview
 
-The semantic search workflow retrieves the most relevant documents using vector similarity.
+The workflow retrieves the most relevant documents using vector similarity.
 
 ```text
 User Query
@@ -74,7 +76,7 @@ for point in results.points:
 
 ### What this script does
 
-This script performs the following steps:
+The script performs the following steps:
 
 - Connects to the Qdrant vector database
 - Loads a pretrained transformer embedding model
@@ -96,7 +98,7 @@ Vector databases enable semantic search.
 Qdrant is optimized for vector similarity search.
 ```
 
-This confirms that the system successfully retrieved the most semantically relevant documents.
+The output confirms that the system successfully retrieved the most semantically relevant documents.
 
 ## Why semantic search is powerful
 
@@ -110,7 +112,7 @@ Semantic search uses vector embeddings to capture meaning.
 | Explain Qdrant          | Qdrant is optimized for vector similarity search |
 | How do embeddings work? | Vector databases enable semantic search          |
 
-This allows applications to understand **intent rather than exact wording**.
+Semantic search allows applications to understand **intent rather than exact wording**.
 
 ## What you've learned and what's next