Merge pull request #2097 from zachlasiuk/main

TEMPLATE: Added demo for phi onnx server & cloud lp

Author: jasonrandrews

content/learning-paths/servers-and-cloud-computing/onnx/_demo.md

@@ -0,0 +1,61 @@
+---
+title: Run a Phi-4-mini chatbot powered by ONNX Runtime
+weight: 2
+
+overview: | 
+  This Learning Path shows you how to use a 32-core Azure Dpls_v6 instance powered by an Arm Neoverse-N2 CPU to build a simple chatbot server that you can then use to provide a chatbot to serve a small number of concurrent users.
+
+  This architecture is suitable for businesses looking to deploy the latest Generative AI technologies with RAG capabilities using their existing CPU compute capacity and deployment pipelines. 
+  
+  The demo uses the ONNX runtime, which Arm has enhanced with its own Kleidi technologies. Further optimizations are achieved by using the smaller Phi-4-mini model, which has been optimized at INT4 quantization to minimize memory usage. 
+
+  Chat with the chatbot LLM below to see the performance for yourself, and then follow the Learning Path to build your own Generative AI service on Arm Neoverse.
+
+
+demo_steps:
+  - Type and send a message to the chatbot.
+  - Receive the chatbot's reply.
+  - View performance statistics demonstrating how well Azure Cobalt 100 instances run LLMs. 
+
+diagram: config-diagram-dark.png
+diagram_blowup: config-diagram.png
+
+terms_and_conditions: demo-terms-and-conditions.txt
+
+prismjs: true  # enable prismjs rendering of code snippets
+
+example_user_prompts:
+  - Prompt 1?
+  - Prompt 2?
+
+
+rag_data_cutoff_date: 2025/01/17
+
+title_chatbot_area: Phi-4-mini Chatbot Demo
+
+prismjs: true
+
+
+
+### Specific details to this demo
+# ================================================================================
+tps_max: 30   # sets stat visuals for tps
+tps_ranges:
+  - name: Low
+    context: Around the average human reading rate of 3-5 words per second.
+    color: var(--arm-green)
+    min: 0
+    max: 5
+  - name: High
+    context: This is significantly higher than the average human reading rate of 5 words per second, delivering a stable and usable user chatbot experience from the Phi-4-mini LLM using the ONNX runtime.
+    color: var(--arm-green)
+    min: 5
+    max: 1000
+
+### FIXED, DO NOT MODIFY
+# ================================================================================
+demo_template_name: phi_onnx_chatbot_demo   # allows the 'demo.html' partial to route to the correct Configuration and Demo/Stats sub partials for page render.
+weight: 2                       # _index.md always has weight of 1 to order correctly
+layout: "learningpathall"       # All files under learning paths have this same wrapper
+learning_path_main_page: "yes"  # This should be surfaced when looking for related content. Only set for _index.md of learning path content.
+---

content/learning-paths/servers-and-cloud-computing/onnx/analysis.md

@@ -1,6 +1,6 @@
 ---
 title: Interact with the Phi-4-mini Chatbot
-weight: 4
+weight: 5
 
 layout: learningpathall
 ---

content/learning-paths/servers-and-cloud-computing/onnx/chatbot-icon.png

@@ -1,6 +1,6 @@
 ---
 title: Run the Chatbot Server
-weight: 3
+weight: 4
 
 layout: learningpathall
 ---

content/learning-paths/servers-and-cloud-computing/onnx/chatbot.md

@@ -2,7 +2,7 @@
 # User change
 title: "Build ONNX Runtime and set up the Phi-4-mini Model"
 
-weight: 2
+weight: 3
 
 # Do not modify these elements
 layout: "learningpathall"

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

@@ -440,6 +440,7 @@
                 all_messages_div.removeChild(all_messages_div.firstChild);
             }
         {{ else if eq .Params.demo_template_name "llm_chatbot_first_demo" }}
+        {{ else if eq .Params.demo_template_name "phi_onnx_chatbot_demo" }}
         {{ else }}
         {{ end }}
 
@@ -629,6 +630,9 @@
     {{ else if eq .Params.demo_template_name "llm_chatbot_first_demo" }}
         {{ $server_location = getenv "HUGO_LLM_API" | base64Encode }}
         console.log('Using LLM API.');
+    {{ else if eq .Params.demo_template_name "phi_onnx_chatbot_demo" }}
+        {{ $server_location = getenv "HUGO_PHI_ONNX_LLM_API" | base64Encode }}
+        console.log('Using HUGO_PHI_ONNX_LLM_API.');
     {{ else }}
         console.log('No server location provided.');
     {{ end }}

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

@@ -24,6 +24,9 @@
 {{else if eq .Params.demo_template_name "whisper_audio_demo"}}
     {{/* {{partial "demo-components/config-params-only.html" .}} */}}
 
+{{else if eq .Params.demo_template_name "phi_onnx_chatbot_demo"}}
+    {{/* {{partial "demo-components/config-params-only.html" .}} */}}
+
 {{else if eq .Params.demo_template_name "kubectl_demo"}}
     {{partial "demo-components/config-param-and-file.html" .}}
 
@@ -42,6 +45,10 @@
     {{partial "demo-components/llm-voice-transcriber/demo-stats--llm-voice-transcriber.html" .}} 
     {{partial "demo-components/llm-voice-transcriber/javascript--llm-voice-transcriber.html" .}}
 
+{{else if eq .Params.demo_template_name "phi_onnx_chatbot_demo"}}
+    {{partial "demo-components/llm-chatbot/demo-stats--llm-chatbot.html" .}} 
+    {{partial "demo-components/llm-chatbot/javascript--llm-chatbot.html" .}}
+
 {{else if eq .Params.demo_template_name "kubectl_demo"}}
     {{partial "demo-components/demo--kubectl.html" .}}