Skip to content

Commit

Permalink
deploy: c6e4bbf
Browse files Browse the repository at this point in the history
  • Loading branch information
@github-actions
github-actions[bot] committed Oct 28, 2024
1 parent ccd26a1 commit e620a0d
Show file tree
Hide file tree
Showing 1,538 changed files with 1,539 additions and 1,539 deletions.
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/archive/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/atom.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@
<li>The default evaluation metrics do not cover a specific application behavior (e.g., <em>friendliness</em>) that we want to assess for our application needs.</li>
</ol>
<p>Let's take a quick look at the <a href="https://learn.microsoft.com/azure/ai-studio/concepts/evaluation-metrics-built-in?tabs=warning#generation-quality-metrics" target="_blank" rel="noopener noreferrer"><strong>default quality metrics</strong></a> defined by Azure AI Studio, and understand what the metric is, how it works, when to use it, and what input it requires for assessment.</p>
<table><thead><tr><th style="text-align:left">Metric</th><th style="text-align:left">What does it assess?</th><th style="text-align:left">How does it work?</th><th style="text-align:left">When should you use it?</th><th style="text-align:left">Inputs Needed</th></tr></thead><tbody><tr><td style="text-align:left"><strong>Groundedness</strong> <br> 1=ungrounded <br> 5=grounded</td><td style="text-align:left">How well does model's generated answers align with information from source data ("context")?</td><td style="text-align:left">Checks if response corresponds <em>verifiably</em> to source context</td><td style="text-align:left">When factual correctness and contextual accuracy are key - e.g., is it grounded in "my" product data?</td><td style="text-align:left">Question, Context, Generated Response</td></tr><tr><td style="text-align:left"><strong>Relevance</strong> <br> 1=bad <br> 5=good</td><td style="text-align:left">Are the model's generated responses pertinent, and directly related, to the given queries?</td><td style="text-align:left">Assesses ability of responses to capture the key points of context that relate to the query</td><td style="text-align:left">When evaluating your application's ability to understand the inputs and generate <em>contextually-relevant</em> responses</td><td style="text-align:left"></td></tr><tr><td style="text-align:left"><strong>Groundedness</strong></td><td style="text-align:left">Given support knowledge, does the ANSWER use the information provided by the CONTEXT?</td><td style="text-align:left"></td><td style="text-align:left"></td><td style="text-align:left"></td></tr><tr><td style="text-align:left"><strong>Relevance</strong></td><td style="text-align:left">How well does the ANSWER address the main aspects of the QUESTION, based on the CONTEXT?</td><td style="text-align:left"></td><td style="text-align:left"></td><td style="text-align:left"></td></tr></tbody></table>
<table><thead><tr><th style="text-align:left">Metric</th><th style="text-align:left">What does it assess?</th><th style="text-align:left">How does it work?</th><th style="text-align:left">When should you use it?</th><th style="text-align:left">Inputs Needed</th></tr></thead><tbody><tr><td style="text-align:left"><strong>Groundedness</strong> <br> 1=ungrounded <br> 5=grounded</td><td style="text-align:left">How well does model's generated answers align with information from source data ("context")?</td><td style="text-align:left">Checks if response corresponds <em>verifiably</em> to source context</td><td style="text-align:left">When factual correctness and contextual accuracy are key - e.g., is it grounded in "my" product data?</td><td style="text-align:left">Question, Context, Generated Response</td></tr><tr><td style="text-align:left"><strong>Relevance</strong> <br> 1=bad <br> 5=good</td><td style="text-align:left">Are the model's generated responses pertinent, and directly related, to the given queries?</td><td style="text-align:left">Assesses ability of responses to capture the key points of context that relate to the query</td><td style="text-align:left">When evaluating your application's ability to understand the inputs and generate <em>contextually-relevant</em> responses</td><td style="text-align:left">Question, Answer</td></tr><tr><td style="text-align:left"><strong>Fluency</strong> 1=bad <br> 5=fluent</td><td style="text-align:left">How grammatically and linguistically correct the model's predicted answer is.</td><td style="text-align:left">Checks quality of individual sentences in the ANSWER? Are they well-written and grammatically correct?</td><td style="text-align:left">When evaluating your application's ability to generate <em>readable</em> responses</td><td style="text-align:left">Question, Answer</td></tr><tr><td style="text-align:left"><strong>Coherence</strong> <br> 1=bad <br> 5=good</td><td style="text-align:left">Measures the quality of all sentences in a model's predicted answer and how they fit together naturally.</td><td style="text-align:left">Checks how well do all sentences in the ANSWER fit together? Do they sound natural when taken as a whole?</td><td style="text-align:left">When the <em>readability</em> of the response is important</td><td style="text-align:left">Question, Answer</td></tr></tbody></table>
<p>To create these custom evaluators, we need to do three things:</p>
<ol>
<li>Define the scoring criteria for that metrics, when evaluating our application responses.</li>
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/build-content-generation-app-part-1/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/build-content-generation-app-part-2/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/closing-summary/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/demo-our-ai-based-content-generation-app/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/deploy-application-with-AKS-part-1/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/deploy-application-with-AKS-part-2/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/deploy-application-with-azure-app-service-part-1/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/deploy-application-with-azure-app-service-part-2/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
4 changes: 2 additions & 2 deletions 30-days-of-ia-2024/evaluate-with-ai/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down Expand Up @@ -61,7 +61,7 @@ <h2 class="anchor anchorWithStickyNavbar_LWe7" id="2-what-are-custom-evaluators"
<li>The default evaluation metrics do not cover a specific application behavior (e.g., <em>friendliness</em>) that we want to assess for our application needs.</li>
</ol>
<p>Let&#x27;s take a quick look at the <a href="https://learn.microsoft.com/azure/ai-studio/concepts/evaluation-metrics-built-in?tabs=warning#generation-quality-metrics" target="_blank" rel="noopener noreferrer"><strong>default quality metrics</strong></a> defined by Azure AI Studio, and understand what the metric is, how it works, when to use it, and what input it requires for assessment.</p>
<table><thead><tr><th style="text-align:left">Metric</th><th style="text-align:left">What does it assess?</th><th style="text-align:left">How does it work?</th><th style="text-align:left">When should you use it?</th><th style="text-align:left">Inputs Needed</th></tr></thead><tbody><tr><td style="text-align:left"><strong>Groundedness</strong> <br> 1=ungrounded <br> 5=grounded</td><td style="text-align:left">How well does model&#x27;s generated answers align with information from source data (&quot;context&quot;)?</td><td style="text-align:left">Checks if response corresponds <em>verifiably</em> to source context</td><td style="text-align:left">When factual correctness and contextual accuracy are key - e.g., is it grounded in &quot;my&quot; product data?</td><td style="text-align:left">Question, Context, Generated Response</td></tr><tr><td style="text-align:left"><strong>Relevance</strong> <br> 1=bad <br> 5=good</td><td style="text-align:left">Are the model&#x27;s generated responses pertinent, and directly related, to the given queries?</td><td style="text-align:left">Assesses ability of responses to capture the key points of context that relate to the query</td><td style="text-align:left">When evaluating your application&#x27;s ability to understand the inputs and generate <em>contextually-relevant</em> responses</td><td style="text-align:left"></td></tr><tr><td style="text-align:left"><strong>Groundedness</strong></td><td style="text-align:left">Given support knowledge, does the ANSWER use the information provided by the CONTEXT?</td><td style="text-align:left"></td><td style="text-align:left"></td><td style="text-align:left"></td></tr><tr><td style="text-align:left"><strong>Relevance</strong></td><td style="text-align:left">How well does the ANSWER address the main aspects of the QUESTION, based on the CONTEXT?</td><td style="text-align:left"></td><td style="text-align:left"></td><td style="text-align:left"></td></tr></tbody></table>
<table><thead><tr><th style="text-align:left">Metric</th><th style="text-align:left">What does it assess?</th><th style="text-align:left">How does it work?</th><th style="text-align:left">When should you use it?</th><th style="text-align:left">Inputs Needed</th></tr></thead><tbody><tr><td style="text-align:left"><strong>Groundedness</strong> <br> 1=ungrounded <br> 5=grounded</td><td style="text-align:left">How well does model&#x27;s generated answers align with information from source data (&quot;context&quot;)?</td><td style="text-align:left">Checks if response corresponds <em>verifiably</em> to source context</td><td style="text-align:left">When factual correctness and contextual accuracy are key - e.g., is it grounded in &quot;my&quot; product data?</td><td style="text-align:left">Question, Context, Generated Response</td></tr><tr><td style="text-align:left"><strong>Relevance</strong> <br> 1=bad <br> 5=good</td><td style="text-align:left">Are the model&#x27;s generated responses pertinent, and directly related, to the given queries?</td><td style="text-align:left">Assesses ability of responses to capture the key points of context that relate to the query</td><td style="text-align:left">When evaluating your application&#x27;s ability to understand the inputs and generate <em>contextually-relevant</em> responses</td><td style="text-align:left">Question, Answer</td></tr><tr><td style="text-align:left"><strong>Fluency</strong> 1=bad <br> 5=fluent</td><td style="text-align:left">How grammatically and linguistically correct the model&#x27;s predicted answer is.</td><td style="text-align:left">Checks quality of individual sentences in the ANSWER? Are they well-written and grammatically correct?</td><td style="text-align:left">When evaluating your application&#x27;s ability to generate <em>readable</em> responses</td><td style="text-align:left">Question, Answer</td></tr><tr><td style="text-align:left"><strong>Coherence</strong> <br> 1=bad <br> 5=good</td><td style="text-align:left">Measures the quality of all sentences in a model&#x27;s predicted answer and how they fit together naturally.</td><td style="text-align:left">Checks how well do all sentences in the ANSWER fit together? Do they sound natural when taken as a whole?</td><td style="text-align:left">When the <em>readability</em> of the response is important</td><td style="text-align:left">Question, Answer</td></tr></tbody></table>
<p>To create these custom evaluators, we need to do three things:</p>
<ol>
<li>Define the scoring criteria for that metrics, when evaluating our application responses.</li>
Expand Down
2 changes: 1 addition & 1 deletion ...-ia-2024/how-it-works-behind-the-scenes-of-our-ai-based-content-generation-app/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
2 changes: 1 addition & 1 deletion 30-days-of-ia-2024/ideate-with-prompty/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@

<script src="https://code.jquery.com/jquery-3.7.1.min.js"></script>
<script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.912b9083.css">
<script src="/Cloud-Native/assets/js/runtime~main.a8cc4147.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/runtime~main.19ae275c.js" defer="defer"></script>
<script src="/Cloud-Native/assets/js/main.09ffe1d8.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
Expand Down
Loading

0 comments on commit e620a0d

Please sign in to comment.