Additions to Lesson 3

tiendatnguyen16 · Oct 26, 2023 · 2efef18 · 2efef18
1 parent 7b1486b
commit 2efef18
Show file tree

Hide file tree

Showing 20 changed files with 138 additions and 20 deletions.
diff --git a/01-introduction-to-genai/README.md b/01-introduction-to-genai/README.md
@@ -115,7 +115,7 @@ If you done this task, you might even be ready to apply to Microsoft's incubator
 
 ## Great Work! Continue the Journey 
 
-Want to learn more about different Generative AI concepts? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic. 
+Want to learn more about different Generative AI concepts? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic. 
 
 Head over to the Lesson 2 where we will look at how to [explore and compare different LLM types](/2-exploring-and-comparing-different-llms/README.md)! 
 
diff --git a/02-exploring-and-comparing-different-llms/README.md b/02-exploring-and-comparing-different-llms/README.md
@@ -150,7 +150,7 @@ Training an LLM from scratch is without a doubt the most difficult and the most
 ## Great Work, Continue Your Learning! 
 
 
-Want to learn more about different Generative AI concepts? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about different Generative AI concepts? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 
 Head over to the Lesson 3 where we will look at how to [build with Generative AI Responsibly](/03-using-generative-ai-responsibly%20/README.MD)!

diff --git a/03-using-generative-ai-responsibly /README.MD b/03-using-generative-ai-responsibly /README.MD
@@ -34,13 +34,131 @@ Hallucinations are a term used to describe when an LLM produces content that is
 
 Let's take for example we build a feature for our startup that allows students to ask historical questions to a model. A student asks the question `Who was the sole surivor of Titanic?`
 
-The model produces a a response like the one below: 
+The model produces a a response like the one below:
+
+
+![](/03-using-generative-ai-responsibly%20/images/2135-ChatGPT(1)_11zon.webp)
+
+*(Source: https://flyingbisons.com)*
+
+This is a very confident and thorough answer. Unfortunately, it is incorrect. Even with a minimal amount of research, one would discover there was more than one survivor of the Titantic survivor. For a student that is just starting to research this topic, this answer can be persuasive enough to not be questioned and treated as fact. 
+
+With each iteration of any given LLM we have seen performance improvements around minimising hallucinations. Even with this improvement,  we as applications builders and users still need to remain aware of these limitations. 
+
+
+### Harmful Content 
+
+We covered in the earlier section when a LLM produces incorrect or nonsensical responses.  Another risk we need to be aware of is when a model responds with harmful content. 
+
+Harmful content can be defined as: 
+- Providing instructions or encouraging self harm or harm to certain groups 
+- Hateful or demeaning content 
+- Providing guidance on planning any type of attack or violent acts
+- Providing instructions on how to find illegal content or commit illegal acts 
+
+For our startup, we want to make sure we have the right tools and strategies in place to prevent this type of content from being seen to students. 
+
+### Lack of Fairness 
+
+Fairness is defined as "ensuring that an AI system is free from bias and discrimination and that they treat everyone fairly and equally."  In the world of Generative AI, that exclusionary worldviews of marginalised groups are not reinforced by the model's output. 
+
+These type of outputs are not only harmful to build positive product experiences for our users, they also cause further societal harm. As application builders, we should always keep a wide and diverse user base in mind when building solutions with Generative AI. 
+
+## How to Use Generative AI Responsibly 
+
+Now that we have identified the importance of Responsible Generative AI, let's look at 4 steps we can do to build our AI solutions responsibly: 
+
+![Mitigate Cycle](./images/mitigate-cycle.png)
+
+
+
+### Identify Potential Harms 
+
+In the earlier section we discussed some of the potential harms when building a Generative AI Solution. These harms can change based on the services and the models you are using. Using techniques such as fine-tuning or grounding your data that provides a higher level control on the model's output should also be considered when listing potential harms. 
+
+In this course, we will be building applications for our startups that generates images, text, chat responses and API calls to external services. Each of these applications come with their own unique set of potential harms.
+
+
+### Measure Potential Harms 
+
+
+### Mitigate Potential Harms 
+
+
+### Operate a responsible generative AI solution
+
+You will see as we build our startup we can use Generative AI to create text applications, new images,  improve search results, create better chat experiences and integrate it with other parts of our application.
+
+
+
+## Tools and Strategies for Responsible AI 
+
+
+### Creating Mitigation Layers
+![Mitigation Layers](./images/mitigation-layers.png)
+
+
+
+**Model**
+
+
+**Safety System**
+
+
+**Metaprompt**
+
+
+**User Experience**
+
+### Adversarial Testing 
+
+
+
+### Azure AI Content Safety 
+
+
+https://learn.microsoft.com/en-us/azure/ai-services/content-safety/overview  
+
+
+```python 
+# Create an Content Safety client
+    client = ContentSafetyClient(endpoint, AzureKeyCredential(key))
+
+    # Build request
+    with open(image_path, "rb") as file:
+        request = AnalyzeImageOptions(image=ImageData(content=file.read()))
+
+    # Analyze image
+    try:
+        response = client.analyze_image(request)
+    except HttpResponseError as e:
+        print("Analyze image failed.")
+        if e.error:
+            print(f"Error code: {e.error.code}")
+            print(f"Error message: {e.error.message}")
+            raise
+        print(e)
+        raise
+
+    if response.hate_result:
+        print(f"Hate severity: {response.hate_result.severity}")
+    if response.self_harm_result:
+        print(f"SelfHarm severity: {response.self_harm_result.severity}")
+    if response.sexual_result:
+        print(f"Sexual severity: {response.sexual_result.severity}")
+    if response.violence_result:
+        print(f"Violence severity: {response.violence_result.severity}")
+
+    # [END analyze_image]
+
+```
 
 
 ## Great Work, Continue Your Learning! 
 
 
-Want to learn more about different Generative AI concepts? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about how to build with Generative AI responsibly? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 
 Head over to the Lesson 4 where we will look at [Prompt Engineering Fundamentals](/4-prompt-engineering-fundamentals/README.md)!
+
diff --git a/03-using-generative-ai-responsibly /images/2135-ChatGPT(1)_11zon.webp b/03-using-generative-ai-responsibly /images/2135-ChatGPT(1)_11zon.webp
diff --git a/03-using-generative-ai-responsibly /images/mitigate-cycle.png b/03-using-generative-ai-responsibly /images/mitigate-cycle.png
diff --git a/03-using-generative-ai-responsibly /images/mitigation-layers.png b/03-using-generative-ai-responsibly /images/mitigation-layers.png
diff --git a/04-prompt-engineering-fundamentals/README.md b/04-prompt-engineering-fundamentals/README.md
@@ -370,10 +370,10 @@ Wrap the section with a summary and resources for self-guided learning.
 -->
 
 
-## 1.12 Learning Resources
+## Great Work! Continue Your Learning 
 
-1. [Introduction to Generative AI](https://learn.microsoft.com/training/paths/introduction-generative-ai/) - Microsoft Learning Path (2023)
-1. [Introduction to Prompt Engineering](https://learn.microsoft.com/azure/ai-services/openai/concepts/prompt-engineering) - Azure OpenAI Documentation (2023)
-1. [Prompt Engineering Techniques](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/advanced-prompt-engineering?pivots=programming-language-chat-completions) - Azure OpenAI Documentation (2023)
-1. [Prompt Engineering Overview](https://learn.microsoft.com/en-us/semantic-kernel/prompt-engineering/) - Semantic Kernel Documentation (2023)
-1. [Azure OpenAI for Education Prompts](https://techcommunity.microsoft.com/t5/e1.ucation-blog/azure-openai-for-education-prompts-ai-and-a-guide-from-ethan-and/ba-p/3938259) - Microsoft Tech Community (2023)
+
+Want to learn more about different Prompt Engineering concepts? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
+
+  
+Head over to the Lesson 5 where we will look at [advance prompting techniques](../05-advanced-prompts/README.md)!
diff --git a/05-advanced-prompts/README.md b/05-advanced-prompts/README.md
@@ -615,7 +615,7 @@ Answer: A, because chain-of-thought is about showing the LLM how to solve a prob
 
 ## Great Work! Continue Your Learning 
 
-Want to learn more about creating advanced prompts? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about creating advanced prompts? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 
 Head over to the Lesson 6 where we will apply our knowledge of Prompt Engineering by [building text generation apps](/6-text-generation-apps/README.md)!
diff --git a/06-text-generation-apps/README.md b/06-text-generation-apps/README.md
@@ -656,7 +656,7 @@ A: 3, because environment variables are not stored in code and can be loaded fro
 
 ## Great Work! Continue Your Learning 
 
-Want to learn more about about creating text generation applications? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about about creating text generation applications? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 
 Head over to the Lesson 7 where we will look at how to [build chat applications](/7-building-chat-applications/README.md)!
diff --git a/07-building-chat-applications/README.md b/07-building-chat-applications/README.md
@@ -153,7 +153,7 @@ Microsoft's approach to Responsible AI has identified six principles that should
 
 ## Great Work! Continue the Journey
 
-Want to learn more about creating chat applications with Generative AI? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about creating chat applications with Generative AI? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 
 Head over to Lesson 8 to see how you can start  [building search applications](/8-building-search-applications/README.md)!
diff --git a/08-building-search-applications/README.md b/08-building-search-applications/README.md
@@ -161,7 +161,7 @@ When you run the notebook, you'll be prompted to enter a query. The input box wi
 
 ## Great Work! Continue Your Learning 
 
-Want to learn more about how to build search applications? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about how to build search applications? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 
 Head over to the Lesson 9 where we will look at how to [build image generation applications](/09-building-image-applications/README.md)!
diff --git a/09-building-image-applications/README.md b/09-building-image-applications/README.md
@@ -466,7 +466,7 @@ except openai.error.InvalidRequestError as err:
  ## Great Work! Continue Your Learning 
 
 
-Want to learn more about how to build Image Generation apps? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about how to build Image Generation apps? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 
 Head over to the Lesson 10 where we will look at how to [build AI applications with low-code](/10-building-low-code-ai-applications/README.md))!
diff --git a/10-building-low-code-ai-applications/README.md b/10-building-low-code-ai-applications/README.md
@@ -226,6 +226,6 @@ To learn how to use this AI Model in Power Automate, go through the [Add intelli
 
 ## Great Work! Contiune Your Learning 
 
-Want to learn more about building low-code Generative AI apps? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about building low-code Generative AI apps? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 Head over to the Lesson 11 where we will look at how to [intergrate Generative AI with Function Calling](/2-exploring-and-comparing-different-llms/README.md)!
diff --git a/...lling /Lesson 11 - Function Calling.ipynb → ...lling /Lesson 11 - Function Calling.ipynb b/...lling /Lesson 11 - Function Calling.ipynb → ...lling /Lesson 11 - Function Calling.ipynb
diff --git a/...ergating-with-function-calling /README.md → ...ergating-with-function-calling /README.md b/...ergating-with-function-calling /README.md → ...ergating-with-function-calling /README.md
@@ -438,7 +438,7 @@ To continue your learning of Azure Open AI Function Calling you can build:
 
  ## Great Work! Continue the Journey
 
-Want to learn more about different Function Calling? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about different Function Calling? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 
 Head over to the Lesson 12 where we will look at how to [design UX for AI applications](/12-designing-ux-for-ai-applications/README.md)!
diff --git a/...unction-calling /images/Function-Flow.png → ...unction-calling /images/Function-Flow.png b/...unction-calling /images/Function-Flow.png → ...unction-calling /images/Function-Flow.png
diff --git a/...ith-function-calling /images/LLM-Flow.png → ...ith-function-calling /images/LLM-Flow.png b/...ith-function-calling /images/LLM-Flow.png → ...ith-function-calling /images/LLM-Flow.png
diff --git a/...n-calling /images/genai_course_11[90].png → ...n-calling /images/genai_course_11[90].png b/...n-calling /images/genai_course_11[90].png → ...n-calling /images/genai_course_11[90].png
diff --git a/12-designing-ux-for-ai-applications/README.md b/12-designing-ux-for-ai-applications/README.md
@@ -84,8 +84,8 @@ AI applications are not perfect, therefore, they are bound to make mistakes. Whe
 
 <!-- ## [Post-lecture quiz](quiz-url) -->
 
-## Congrulations, you have finished this course! 
+## Congratulations, you have finished this course! 
 
-Want to learn more about designing UX for AI Applications? Go to the [contiuned learning page](/13%20-%20contiuned-learning/README.md) to find other great resources on this topic.
+Want to learn more about designing UX for AI Applications? Go to the [contiuned learning page](../13-continued-learning/README.md) to find other great resources on this topic.
 
 Congratulation, you have completed this course! The building should not stop here. Hopefully you have been inspired to start building your own Generative AI startup. Head over to the [Microsoft Founders Hub](https://www.microsoft.com/en-us/startups) and apply for the program to recieve support on your journey. 
diff --git a/13 - contiuned-learning/README.md → 13-continued-learning/README.md b/13 - contiuned-learning/README.md → 13-continued-learning/README.md
@@ -1,6 +1,6 @@
 # Additional resources
 
-Here are links to other great resources to contiue your learning and building wih Generative AI.
+Here are links to other great resources to continue your learning and building with Generative AI.
 
 Missing a great resource? Let us know by submitting a PR!