Skip to content

Commit c84e508

Browse files
committed
fix 4 / created consistent headers for all notebooks (except FT)
1 parent 57fce55 commit c84e508

18 files changed

+1851
-1533
lines changed

labs/0-setup/00-validate-setup.ipynb

Lines changed: 25 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,32 @@
55
"id": "543643eb",
66
"metadata": {},
77
"source": [
8-
"# Environment Setup Validation\n",
8+
"# 🛍️ | Cora-For-Zava: Validate Setup\n",
99
"\n",
10-
"This notebook validates that all required environment variables are properly configured for the lab exercises."
10+
"Welcome! This notebook validates that your Azure environment is properly configured before you start building **Cora**, our AI-powered shopping assistant for Zava Hardware Store.\n",
11+
"\n",
12+
"## 🛒 Our Zava Scenario\n",
13+
"\n",
14+
"**Cora** is a customer service chatbot for **Zava** - a fictitious retailer of home improvement goods for DIY enthusiasts. Before we can build Cora, we need to ensure all Azure resources, API keys, and configurations are properly set up.\n",
15+
"\n",
16+
"## 🎯 What This Notebook Does\n",
17+
"\n",
18+
"This validation notebook will check:\n",
19+
"- ✅ Azure subscription and resource group configuration\n",
20+
"- ✅ Azure OpenAI service endpoint and API keys\n",
21+
"- ✅ Azure AI Search service configuration\n",
22+
"- ✅ Azure AI Foundry project settings\n",
23+
"- ✅ Application Insights connection (for monitoring)\n",
24+
"\n",
25+
"## 💡 What You'll Learn\n",
26+
"\n",
27+
"- How to verify environment variables are properly configured\n",
28+
"- Which Azure services are required for the lab exercises\n",
29+
"- How to troubleshoot common setup issues\n",
30+
"\n",
31+
"Ready to validate your setup? Let's begin! 🚀\n",
32+
"\n",
33+
"---"
1134
]
1235
},
1336
{

labs/1-agents/01-build-cora-retail-agent.ipynb renamed to labs/1-agents/11-build-cora-retail-agent.ipynb

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,10 @@
99
"\n",
1010
"Welcome! In this beginner-friendly tutorial, you'll learn how to build **Cora**, an AI-powered shopping assistant for Zava Hardware Store, using **Azure AI Agent Service**.\n",
1111
"\n",
12+
"## 🛒 Our Zava Scenario\n",
13+
"\n",
14+
"**Cora** is a customer service chatbot for **Zava** - a fictitious retailer of home improvement goods for DIY enthusiasts. Zava offers a wide range of products including paint, power tools, hand tools, hardware, electrical supplies, and plumbing materials. Cora helps customers find products, check inventory, and provides personalized assistance for home improvement projects.\n",
15+
"\n",
1216
"## 🎯 What You'll Build\n",
1317
"\n",
1418
"By the end of this tutorial, you'll have created **Cora-For-Zava**, a helpful and polite retail chatbot that:\n",

labs/1-agents/12-agent-framework-orchstration.ipynb renamed to labs/1-agents/12-agent-framework-orchestration.ipynb

Lines changed: 20 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -5,24 +5,32 @@
55
"id": "48208819",
66
"metadata": {},
77
"source": [
8-
"# Multi-Agent System with Azure AI Search\n",
8+
"# 🛍️ | Cora-For-Zava: Multi-Agent Pattern\n",
99
"\n",
10-
"Welcome! In this notebook, you'll create a **multi-agent system** that uses **Azure AI Search** to answer customer questions about products.\n",
10+
"Welcome! In this notebook, you'll create a **multi-agent system** that uses relevant tools to answer customer questions about products.\n",
11+
"\n",
12+
"## 🛒 Our Zava Scenario\n",
13+
"\n",
14+
"**Cora** is a customer service chatbot for **Zava** - a fictitious retailer of home improvement goods for DIY enthusiasts. As Zava retail stores grow, Cora needs to handle more complex customer needs. This notebook shows you how to evolve from a single agent to a multi-agent system, with specialized agents for inventory management and customer service. You'll learn to orchestrate multiple agents working together to provide sophisticated and role-specific assistance.\n",
15+
"\n",
16+
"## 🎯 What You'll Build\n",
1117
"\n",
12-
"## What You'll Build\n",
1318
"Two specialized agents for a hardware store:\n",
14-
"1. **Product Inventory Agent** - Technical expert for product specs and stock levels\n",
15-
"2. **Customer Service Agent** - Friendly helper for recommendations and guidance\n",
19+
"- **Product Inventory Agent** - Technical expert for product specs and stock levels\n",
20+
"- **Customer Service Agent** - Friendly helper for recommendations and guidance\n",
1621
"\n",
1722
"Both agents will search the same product database but respond differently based on their role.\n",
1823
"\n",
19-
"## What You'll Learn\n",
20-
"- Connect to Azure AI Search from your agents\n",
21-
"- Create agents with different personalities\n",
22-
"- Route questions to the right agent\n",
23-
"- Stream responses with citations\n",
24+
"## 💡 What You'll Learn\n",
25+
"\n",
26+
"- How to connect agents to Azure AI Search\n",
27+
"- How to create agents with different personalities\n",
28+
"- How to route questions to the right agent\n",
29+
"- How to orchestrate multiple agents working together\n",
30+
"\n",
31+
"Ready to build a multi-agent system? Let's get started! 🚀\n",
2432
"\n",
25-
"Let's get started! 🚀\n"
33+
"---"
2634
]
2735
},
2836
{
@@ -717,7 +725,7 @@
717725
"metadata": {},
718726
"outputs": [],
719727
"source": [
720-
"await cleanup_agents()"
728+
"#await cleanup_agents()"
721729
]
722730
},
723731
{

labs/2-models/21-simulate-dataset.ipynb

Lines changed: 16 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,18 +6,31 @@
66
"tags": []
77
},
88
"source": [
9-
"# Simulate Datasets for Evaluation\n",
9+
"# 🛍️ | Cora-For-Zava: Simulate Test Datasets\n",
1010
"\n",
1111
"Welcome! This notebook will walk you through generating synthetic datasets using Azure AI Search and the Azure AI Evaluation Simulator.\n",
1212
"\n",
13-
"## What You'll Learn\n",
13+
"## 🛒 Our Zava Scenario\n",
14+
"\n",
15+
"**Cora** is a customer service chatbot for **Zava** - a fictitious retailer of home improvement goods for DIY enthusiasts. To ensure Cora provides accurate and helpful responses about hardware and home improvement products, you need quality test data. This notebook helps you generate synthetic query-response pairs based on your product catalog, creating a robust evaluation dataset to measure Cora's performance before deployment.\n",
16+
"\n",
17+
"## 🎯 What You'll Build\n",
18+
"\n",
19+
"By the end of this notebook, you'll have:\n",
20+
"- ✅ Generated synthetic query-response pairs from your product catalog\n",
21+
"- ✅ Created a dataset in JSON Lines format for evaluation\n",
22+
"- ✅ Learned how to use the Azure AI Evaluation Simulator\n",
23+
"- ✅ Saved your dataset for use in future evaluation exercises\n",
24+
"\n",
25+
"## 💡 What You'll Learn\n",
26+
"\n",
1427
"- How to configure the Azure AI Evaluation Simulator\n",
1528
"- How to connect to Azure AI Search to retrieve content\n",
1629
"- How to create a RAG application callback\n",
1730
"- How to generate synthetic query-response pairs\n",
1831
"- How to save and review the generated dataset\n",
1932
"\n",
20-
"Let's get started! 🚀\n",
33+
"Ready to generate your evaluation dataset? Let's get started! 🚀\n",
2134
"\n",
2235
"---"
2336
]

labs/2-models/22-evaluate-models.ipynb

Lines changed: 22 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -5,21 +5,34 @@
55
"id": "745e6fbf",
66
"metadata": {},
77
"source": [
8-
"# Model Selection By Evaluation\n",
8+
"# 🛍️ | Cora-For-Zava: Model Selection \n",
99
"\n",
10-
"Welcome! This notebook will walk you through evaluating multiple AI models using a standardized test dataset and the [Azure AI Evaluation SDK](https://learn.microsoft.com/azure/ai-foundry/how-to/develop/evaluate-sdk).\n",
10+
"Welcome! This notebook will walk you through evaluating multiple AI models using a standardized test dataset and the Azure AI Evaluation SDK.\n",
11+
"\n",
12+
"## 🛒 Our Zava Scenario\n",
13+
"\n",
14+
"**Cora** is a customer service chatbot for **Zava** - a fictitious retailer of home improvement goods for DIY enthusiasts. To ensure Cora provides the best customer experience, you need to select the right foundation model. With multiple Azure OpenAI models available (GPT-4o, GPT-4o-mini, GPT-4), you need to evaluate which model delivers the best balance of quality, safety, and performance for your retail use case.\n",
15+
"\n",
16+
"## 🎯 What You'll Build\n",
17+
"\n",
18+
"By the end of this notebook, you'll have:\n",
19+
"- ✅ Configured multiple Azure OpenAI models for comparison\n",
20+
"- ✅ Loaded standardized test datasets for evaluation\n",
21+
"- ✅ Run evaluations across models using built-in evaluators\n",
22+
"- ✅ Analyzed performance metrics (quality, safety, latency)\n",
23+
"- ✅ Compared model results to make informed selection decisions\n",
24+
"\n",
25+
"## 💡 What You'll Learn\n",
1126
"\n",
12-
"## What You'll Learn\n",
1327
"- How to configure multiple models for evaluation\n",
1428
"- How to load test datasets for evaluation\n",
15-
"- How to run evaluations across multiple models using built-in evaluators\n",
16-
"- How to analyze performance metrics (quality, safety, latency)\n",
17-
"- How to compare model results\n",
18-
"- How to use Azure AI Foundry model leaderboards for model selection\n",
29+
"- How to run evaluations with built-in evaluators\n",
30+
"- How to analyze and compare model performance\n",
31+
"- How to use Azure AI Foundry model leaderboards\n",
1932
"\n",
20-
"> **Note**: This notebook demonstrates [pre-production evaluation](https://learn.microsoft.com/azure/ai-foundry/concepts/observability#the-three-stages-of-genaiops-evaluation), which is essential before deploying AI applications to production.\n",
33+
"> **Note**: This demonstrates pre-production evaluation, which is essential before deploying AI applications.\n",
2134
"\n",
22-
"Let's get started! 🚀\n",
35+
"Ready to compare models? Let's get started! 🚀\n",
2336
"\n",
2437
"---"
2538
]

labs/4-evaluation/41-first-evaluation-run.ipynb

Lines changed: 25 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -5,22 +5,39 @@
55
"id": "9ca87bfb",
66
"metadata": {},
77
"source": [
8+
"# 🛍️ | Cora-For-Zava: Your First Evaluation Flow\n",
89
"\n",
10+
"Welcome! This notebook sets up the Azure AI Evaluation SDK and walks you through your first evaluation with quality and safety evaluators.\n",
911
"\n",
10-
"# 🔍 | Lab 01: Run Your First Evaluation With The SDK \n",
12+
"## 🛒 Our Zava Scenario\n",
1113
"\n",
12-
"This notebook sets up the Azure AI Evaluation SDK and walks you through the first _evaluate()_ call with quality and safety evaluators. Use this to get a sense for how evaluations work, and what built-in evaluators are provided to you. **Bonus** - We'll see how the Azure AI Foundry portal renders results\n",
14+
"**Cora** is a customer service chatbot for **Zava** - a fictitious retailer of home improvement goods for DIY enthusiasts. Before deploying Cora to help customers, you need to ensure it provides accurate, safe, and helpful responses. Evaluation is the foundation of trust in AI applications, making it a critical part of the Generative AI Ops (GenAIOps) lifecycle. Without rigorous evaluation, Cora could produce content that is fabricated, irrelevant, harmful, or vulnerable to adversarial attacks.\n",
1315
"\n",
16+
"## 🎯 What You'll Build\n",
1417
"\n",
15-
"Evaluation is the foundation of trust in AI applications, making it a critical part of the Generative AI Ops (GenAIOps) lifecycle. Without rigorous evaluation at each step, the AI solution can produce content that is fabricated (ungrounded in reality), irrelevant, harmful - or vulnerable to adversarial attacks. \n",
18+
"By the end of this notebook, you'll have:\n",
19+
"- ✅ Run your first evaluation using the Azure AI Evaluation SDK\n",
20+
"- ✅ Configured and used built-in evaluators for quality and safety\n",
21+
"- ✅ Evaluated a test dataset with sample responses\n",
22+
"- ✅ Saved evaluation results to a file\n",
23+
"- ✅ Viewed evaluation results in Azure AI Foundry portal\n",
1624
"\n",
17-
"The three stages of GenAIOps Evaluation can be represented by:\n",
25+
"## 💡 What You'll Learn\n",
1826
"\n",
19-
"1. **Base Model Selection** - Before building your application, you need to select the right base model for your use case. Use evaluators to compare base models for fit using criteria like accuracy, quality, safety and task performance.\n",
20-
"1. **Pre-Production Evaluation** - Once you have selected a base model, you need to customize it to build the AI application (e.g., RAG with data, agentic AI etc.). This pre-production phase is where you iterate rapidly on the prototype, using evaluations to assess robustness, validate edge cases, measure key metrics, and simulate real-world interactins for testing coverage.\n",
21-
"1. **Post-Production Monitoring** - Helps ensure the AI application maintains desired quality, safety and performance goals in real-world environments - with capabilities that include performance tracking and fast incident response.\n",
27+
"- What the `evaluate()` function does and how to use it\n",
28+
"- How to configure and run evaluations with built-in evaluators\n",
29+
"- How to interpret evaluation metrics\n",
30+
"- How to view results in the Azure AI Foundry portal\n",
2231
"\n",
23-
"This is where **evaluators** become critical. Evaluators are specialized tool that help you assess the quality, safety and reliability of your AI application responses. The Azure AI Foundry platform offers a comprehensive suite of built-in evaluators that cover a broad category of use cases including: Retrieval Augmented Generation (RAG), agentic AI, safety & security, and textual similarity - along with general purpose evaluators.\n"
32+
"## 📊 The Three Stages of GenAIOps Evaluation\n",
33+
"\n",
34+
"1. **Base Model Selection** - Compare models for accuracy, quality, safety and task performance\n",
35+
"2. **Pre-Production Evaluation** - Iterate on prototypes, assess robustness, validate edge cases\n",
36+
"3. **Post-Production Monitoring** - Track performance and ensure quality in real-world environments\n",
37+
"\n",
38+
"> **Note**: This notebook focuses on pre-production evaluation using a small test dataset.\n",
39+
"\n",
40+
"Ready to run your first evaluation? Let's get started! 🚀\n"
2441
]
2542
},
2643
{

0 commit comments

Comments
 (0)