Merge pull request #1536 from zachlasiuk/main

TEMPLATE: Merging RAG demo staging into real LP

Author: pareenaverma

assets/css/demo.css

@@ -261,8 +261,8 @@
 }
 .chatbot-response-text * {
     max-width: 98%;
-    margin-bottom:0;
-    line-height: 1.2;
+    margin-bottom: 8px;
+    line-height: 1.3;
 }
 
 

content/learning-paths/servers-and-cloud-computing/aaaaaaRAGexample/config-diagram-dark.png

@@ -162,6 +162,6 @@ Using what you have learned, navigate to the **Train, Test and Deploy** workflow
 
 The diagram below shows the end-to-end workflow, the relationship between the steps, and the time required to run each step:
 
-![#e2e-workflow](/images/e2e-workflow.png)
+![#e2e-workflow](images/e2e-workflow.png)
 
 You have run an MLOps workflow using GitHub Actions with Arm-hosted runners for managing all of the steps in your ML application's lifecycle.

content/learning-paths/servers-and-cloud-computing/aaaaaaRAGexample/config-diagram.png

@@ -21,7 +21,7 @@ example_user_prompts:
   - Do Hyperscan and Snort3 work on Graviton4?
   - How can I easily build multi-architecture Docker images?
 
-rag_data_cutoff_date: 2025/01/13
+rag_data_cutoff_date: 2025/01/17
 
 title_chatbot_area: Arm RAG Demo
 

content/learning-paths/servers-and-cloud-computing/gh-runners/e2e-workflow.md

@@ -22,7 +22,7 @@
     <div class="c-row u-gap-1/2 u-flex-nowrap u-padding-top-0">
         <div class="c-col">
             <h2>RAG Vector Store Details</h2>
-            <p>This app uses all data on this site, <a href="https://www.learn.arm.com">learn.arm.com</a>, as the RAG data set. The Markdown formatted content across Learning Paths and Install Guides was segmented into labeled chunks, vector embeddings were generated using FAISS, which the LLM demo below references for your query.</p>
+            <p>This app uses all data on this site, <a href="https://www.learn.arm.com">learn.arm.com</a>, as the RAG data set. The Markdown formatted content across Learning Paths and Install Guides was segmented into labeled chunks, and vector embeddings were generated. FAISS is used for the embedded similarity search. The LLM demo below references this vector store for your query.</p>
             <p><b>Note:</b> Data was sourced on {{.Params.rag_data_cutoff_date}}.</p>
         </div>    
     </div>