Date format.

Author: StormHub

site/_includes/postslist.njk

@@ -9,7 +9,7 @@
             {% endif %}
         </a>
         <time class="text-muted" datetime="{{ post.date | htmlDateString }}">
-            <small>{{ post.date | readableDate("LLLL yyyy") }}</small>
+            <small>{{ post.date | readableDate }}</small>
         </time> 
     </div>
 {% endfor %}

site/content/blog/2024-09-30-TypeScript-Pretty.md

@@ -8,7 +8,7 @@ permalink: "typescript/2024/09/29/TypeScript-Pretty.html"
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 TypeScript helper from [Matt Pocock](https://twitter.com/mattpocockuk) to reveal type details.
 

site/content/blog/2024-10-10-Extensions-AI.md

@@ -8,7 +8,7 @@ permalink: ".net/ai/2024/10/10/Extensions-AI.html"
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 [Microsoft.Extensions.AI](https://devblogs.microsoft.com/dotnet/introducing-microsoft-extensions-ai-preview/)
 

site/content/blog/2024-11-18-KernelMemory-Azure.md

@@ -8,7 +8,7 @@ permalink: ".net/ai/kernelmemory/2024/11/18/KernelMemory-Azure.html"
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 [Kernel Memory](https://github.com/microsoft/kernel-memory) with Azure OpenAI,
 Blob storage and AI Search.

site/content/blog/2024-11-25-KernelMemory-Azure-Distributed.md

@@ -8,7 +8,7 @@ permalink: ".net/ai/kernelmemory/2024/11/25/KernelMemory-Azure-Distributed.html"
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 ## Document ingestion
 Benifits of document ingestion asynchronously with [Kernel Memory](https://github.com/microsoft/kernel-memory) on Azure

site/content/blog/2024-11-27-KernelMemory-CosmosDB.md

@@ -8,7 +8,7 @@ permalink: ".net/ai/kernelmemory/2024/11/27/KernelMemory-CosmosDB.html"
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 Officially announced in Microsoft Build 2024, Cosmos DB for NoSQL now support vector search. It also means [Kernel Memory](https://github.com/microsoft/kernel-memory) can be integrated with Cosmos DB for NoSQL. 
 

site/content/blog/2024-11-30-KernelMemory-Azure-AI-Vision.md

@@ -8,7 +8,7 @@ permalink: ".net/ai/kernelmemory/2024/11/29/KernelMemory-Azure-AI-Vision.html"
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 
 Extracting text from images for Retrieval-Augmented Generation (RAG) is a common task. [Kernel Memory](https://github.com/microsoft/kernel-memory) supports OCR functionality out of the box. 

site/content/blog/2024-12-04-KernelMemory-Tokenizer.md

@@ -8,7 +8,7 @@ permalink: ".net/ai/kernelmemory/2024/12/03/KernelMemory-Tokenizer.html"
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 Choosing the right tokenizer for in AI is crucial because it directly impacts the accuracy and efficiency. There is an optional 'tokenizer' parameter when configure [Kernel Memory](https://github.com/microsoft/kernel-memory) for both text generation and embedding.
 If no 'tokenizer' specified, [Kernel Memory](https://github.com/microsoft/kernel-memory) attempts to pick up 'default' one.  But it does this by the AI model name (Depolyment in Azure OpenAI) like this 

site/content/blog/2024-12-05-Extensions-AI-Evaluation.md

@@ -8,7 +8,7 @@ permalink: ".net/ai/microsoft.extensions.ai/2024/12/03/Extensions-AI-Evaluation.
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 Implementing a 'demo' RAG is straightforward with AI libraries like [Kernel Memory](https://github.com/microsoft/kernel-memory) or [Semantic Kernel](https://github.com/microsoft/semantic-kernel). However, production grade AI applications are significantly more challenging. AI programs are sensitive to changes and inherently probabilistic, unlike traditional deterministic tests. Tools like [Ragas](https://docs.ragas.io/en/stable/) address these issues. Microsoft has released a preview of [Microsoft.Extensions.AI.Evaluation](https://devblogs.microsoft.com/dotnet/evaluate-the-quality-of-your-ai-applications-with-ease/), followed by [Microsoft.Extensions.AI](https://devblogs.microsoft.com/dotnet/introducing-microsoft-extensions-ai-preview). Notably, Microsoft.Extensions.AI.Evaluation uses an 'LLM-as-a-Judge' approach to rank outcomes.
 

site/content/blog/2024-12-11-ChatCompletion-JsonFormat.md

@@ -7,7 +7,7 @@ tags: [ ".NET", "AI", "Semantic Kernel" ]
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
+*{{date | readableDate }}*
 
 I can't recall how many times I've tried to convince a LLM to return JSON so that I could perform API calls based on natural language inputs from users. Recently, I discovered that this functionality is natively supported by the [Semantic Kernel](https://github.com/microsoft/semantic-kernel) and Microsoft AI Extension Library. It is officially documented by the OpenAI API [here](https://platform.openai.com/docs/guides/structured-outputs). Note that this feature is only available in the latest large language models from GPT-4o/o1 and later. If you are using Azure OpenAI, ensure you have the supported versions when deploying models.
 

site/content/blog/2024-12-11-SemanticKernel-Evaluation.md

@@ -8,8 +8,7 @@ permalink: ".net/ai/semantickernel/2024/12/11/SemanticKernel-Evaluation.html"
 
 # {{title}}
 
-*{{date | readableDate("LLLL yyyy")}}*
-
+*{{date | readableDate }}*
 
 For quick and easy evaluation or comparison of AI responses in .NET applications, particularly tests. We can leverage [autoevals](https://github.com/braintrustdata/autoevals) excellent 'LLM-as-a-Judge' prompts with the help of [Semantic Kernel](https://github.com/microsoft/semantic-kernel).