update stack

docs/index.md

@@ -1,6 +1,6 @@
 # Home
 
-Inspired by Github Copilot's impact on developer productivity, this experiential workshop is designed to demonstrate how you can infuse similar intelligence and product experience into traditional software systems. Using [Microsoft's Copilot stack](https://learn.microsoft.com/en-us/semantic-kernel/overview/#semantic-kernel-is-at-the-center-of-the-copilot-stack) and practical [use cases](https://iappwksp.com/wksp/05-use-cases/#use-cases), this workshop will guide you in envisioning and creating intelligent systems that integrate foundation models throughout all stages of application development - from design and user experience to deployment, resulting in improved productivity and hyper-personalized product experiences. 
+Inspired by Github Copilot's impact on developer productivity, this experiential workshop is designed to demonstrate how you can infuse similar intelligence and product experience into traditional software systems. Using [Microsoft's Copilot stack](https://learn.microsoft.com/en-us/semantic-kernel/overview/#semantic-kernel-is-at-the-center-of-the-copilot-stack) and practical [use cases](https://iappwksp.com/wksp/05-use-cases/#use-cases), this workshop will guide you in envisioning and creating intelligent systems and agents that integrate foundation models throughout all stages of application development - from design and user experience to deployment, resulting in improved productivity and hyper-personalized product experiences. 
 
 [Sign up for updates](https://forms.office.com/r/rLds2s8RH1){ :target="_blank" .md-button .md-button--primary }
 
@@ -23,7 +23,7 @@ By leveraging design thinking, [Project Miyagi](https://github.com/Azure-Samples
 
 1. Exploring the Art of the Possible with [Miyagi](https://github.com/Azure-Samples/miyagi) and [Semantic Kernel (SK)](https://github.com/microsoft/semantic-kernel) demos: Engage in interactive demonstrations to envision the potential applications of SK and [Miyagi](https://github.com/Azure-Samples/miyagi).
 1. Design Thinking Session: A collaborative brainstorming activity to identify your idiosyncratic use cases, focusing on addressing user needs and alleviating pain points, so that the workshop will be relevant for you.
-1. Introduction to Semantic Kernel (SK): A comprehensive presentation to familiarize participants with the fundamentals of SK and goals-first AI.
+1. Introduction to Assistants API and Semantic Kernel (SK): A comprehensive presentation to familiarize participants with the fundamentals of SK, agent-like orchestration, and goals-first AI.
 1. End-to-End Application Lifecycle Workshop featuring [Miyagi](https://github.com/Azure-Samples/miyagi): Gain hands-on experience in incorporating SK primitives into the entire application lifecycle, including leveraging SK skills and prompt engineering to orchestrate complex flows with Azure OpenAI models. <p align="center"><img src="assets/images/basic-arch.png" width=50% /></p>
 1. Architecture Design Session: Dive into the intricacies of designing a robust and effective system architecture to support intelligent app development.
 

docs/wksp/00-intro/agenda-and-outcomes.md

@@ -14,21 +14,21 @@
 1. Unearthing Customer Needs and Pain Points (Design Thinking session to personalize the workshop for your organization needs and use cases)
     1. Crafting AI-Driven Design and User Experience
 1. First steps to integrate AI into cloud-native and Azure backing services and data processing
-1. Empowering Development with AI Capabilities (inner-loop), including leveraging Github CoPilot X
+1. Empowering Development with AI Capabilities (inner-loop), including leveraging Github CoPilot
 1. Learn LLM capabilities and Prompt Engineering
     1. In-context learning (ICL)
-    1. Chain-of-thought prompting
-    1. Chat Markup Language (ChatML)
-    1. Retrieval augmented generation (RaG)
-    1. Embeddings with vector database (CosmosDB PostgreSQL pg_vector extension)
-    1. Completions API and Chat Completions API configurations
+    1. Prompt Engineering techniques
+    1. Advanced Retrieval augmented generation (RaG)
+    1. Integrating vector databases
     1. Prompt Flow
+    1. Agents with Semantic Kernel, Autogen, and TaskWeaver
 1. Deep-dive into AI orchestration primitives through use cases with Miyagi and Reddog
 1. Exploring Agents and Agent-like Orchestration
-1. Tradeoffs with AI orchestrators (Semantic Kernel, Langchain, TypeChat etc.)
-1. Prompt Flow Studio and metaprompts
+1. Tradeoffs with AI orchestrators (Semantic Kernel, Langchain, TypeChat, PromptFlow etc.)
+1. Copilot Studio and Power Platform
+1. AI Studio and Prompt Flow
 1. AI Content Safety Studio
-1. Fine-tuning Llama2 model with proprietary training data to improve task specific accuracy and latency
+1. Fine-tuning OSS models with proprietary training data to improve task specific accuracy and latency
 1. Streamlined Deployment and Monitoring of AI-Infused Apps
 1. (Optional) First Principles of Large Language Models for application developers
     1. High Level Overview of AI and ML
@@ -43,20 +43,19 @@
             1. Grounding
             1. Alignment
         1. Retrieval augmented generation (RaG)
-1. Hands-on Project: Constructing a Semantic Kernel Skill and Integrating it with an Existing App using Miyagi
+1. Hands-on Project: Constructing a Semantic Kernel Plugin and integrating it with an Existing App using Miyagi
 1. Reliability and controllability of LLM output
-1. Embracing "Everything as Code": Automation, Deployment, and Operationalization of Miyagi
-1. Architecture Design Session: Crafting a Customized PoC for Your Unique Use Case
-1. Conclusion and Next Steps with Semantic Kernel Hackathon
+1. Embracing "Everything as Code": Automation, Deployment, and Operationalization for production
+1. Architecture Design Session: Crafting a customized PoC for your unique use case(s)
+1. Conclusion and Next Steps with MVP
 
 ## Outcomes
 
 Upon completing this workshop, participants will:
 
-- Comprehend the transformative potential of Azure AI services and development tools in revolutionizing every facet of app development.
-- Skillfully identify customer needs addressable through AI solutions
+- Comprehend the transformative potential of Azure AI services and Copilot Stack in revolutionizing every facet of AI app development.
 - Acquire hands-on experience in AI-driven design and user experience techniques
 - Learn to effortlessly integrate foundation models into backend services, data processing, and frontend development
 - Build an AI-infused app from the ground up during the hands-on project
-- Grasp the best practices for AI-driven app development and deployment in Azure
+- Implement Agents using Assistants API, Code Interpretor, and Retrieval intefaces. 
 

docs/wksp/00-intro/architecture-overview.md

@@ -2,12 +2,12 @@
 
 Polyglot, AI-Infused Microservices Architecture with Event-Driven Backend
 
-[Sign up for updates](https://forms.office.com/r/rLds2s8RH1){ :target="_blank" .md-button .md-button--primary }
-
+[Sign up for updates](https://forms.office.com/r/rLds2s8RH1){ :target="\_blank" .md-button .md-button--primary }
 
 ![architecture](../../assets/images/wip-azure.png)
 
 ### Copilot Stack
+
 ![copilot-stack](../../assets/images/copilot-stack.png)
 
 ## Overview
@@ -31,8 +31,8 @@ The entire development and deployment pipeline is streamlined using GitHub Actio
 In summary, Project Miyagi's architecture presents a forward-looking approach to building intelligent applications, leveraging advanced AI techniques and robust Azure services to create highly engaging, personalized user experiences. By incorporating cutting-edge technologies and embracing event-driven, scalable microservices, Miyagi offers developers a glimpse into the future of application design and development.
 
 ### Orchestration flow
-![sk-orchestration](../../assets/images/sk-memory-orchestration.png)
 
+![sk-orchestration](../../assets/images/sk-memory-orchestration.png)
 
 ![embeddings](../../assets/images/embeddings.png)
 
@@ -42,16 +42,18 @@ In summary, Project Miyagi's architecture presents a forward-looking approach to
 
 ## Tech Stack
 
-
 ### Services and Features
+
 - [Azure OpenAI](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/models)
-  - gpt-4
-  - gpt-35-turbo
-  - text-embedding-ada-002
 - [Semantic Kernel](https://github.com/microsoft/semantic-kernel)
-- [Use your own data with Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/use-your-data-quickstart?tabs=command-line&pivots=rest-api#example-curl-commands)
+- [AI Studio](https://azure.microsoft.com/en-us/products/ai-studio)
+- [AI Search](https://azure.microsoft.com/en-us/products/ai-services/ai-search)
+- [AI Speech](https://azure.microsoft.com/en-us/products/ai-services/ai-speech)
 - [AzureML PromptFlow](https://learn.microsoft.com/en-us/azure/machine-learning/prompt-flow/overview-what-is-prompt-flow?view=azureml-api-2)
 - [TypeChat](https://microsoft.github.io/TypeChat)
+- [Kernel-memory](https://github.com/microsoft/kernel-memory)
+- [AutoGen](https://github.com/microsoft/autogen)
+- [TaskWeaver](https://github.com/microsoft/TaskWeaver)
 - [Azure Functions](https://azure.microsoft.com/en-ca/products/functions/)
 - [APIM](https://learn.microsoft.com/en-us/azure/api-management/)
 - [Service Bus](https://learn.microsoft.com/en-us/azure/service-bus-messaging/service-bus-messaging-overview)
@@ -64,11 +66,5 @@ In summary, Project Miyagi's architecture presents a forward-looking approach to
 - [Azure DB for PostgreSQL](https://azure.microsoft.com/en-us/products/postgresql)
 - [Azure Redis Cache](https://azure.microsoft.com/en-us/products/cache)
 - [Azure Storage](https://learn.microsoft.com/en-us/azure/storage/common/storage-introduction)
-- [Apache Kafka on Azure Event Hubs](https://learn.microsoft.com/en-us/azure/event-hubs/azure-event-hubs-kafka-overview)
-- [Azure HuggingFace Inference Endpoints](https://azure.microsoft.com/en-us/solutions/hugging-face-on-azure)
 - [LangChain](https://github.com/hwchase17/langchain#readme)
-- [Foundation Models from CogServices](https://azure.microsoft.com/en-us/blog/announcing-a-renaissance-in-computer-vision-ai-with-microsofts-florence-foundation-model/)
-- [Qdrant](https://qdrant.tech/solutions/)
-- [Microsoft DeepSpeed Chat](https://github.com/microsoft/DeepSpeedExamples/tree/master/applications/DeepSpeed-Chat)
-- [Azure Web PubSub](https://azure.microsoft.com/en-us/products/web-pubsub)
-- [Azure Communication Services (ACS)](https://learn.microsoft.com/en-us/azure/communication-services/overview#common-scenarios)
+- [LlamaIndex](https://github.com/run-llama/llama_index)