v5.7 content updates

Author: mythz

MyApp/_posts/2025-04-17_analytics.md MyApp/_posts/2025-04-15_analytics.mdMyApp/_posts/2025-04-17_analytics.md renamed to MyApp/_posts/2025-04-15_analytics.md

@@ -77,16 +77,6 @@ This will query 5 different leading AI coding models to generate 5x different Da
 
 [![](/img/posts/text-to-blazor-premium/text-to-blazor-premium.webp)](/text-to-blazor)
 
-### Using AI to only generate Data Models
-
-Whilst the result is a working CRUD App, the approach taken is very different from most AI tools
-which uses AI to generate the entire App that ends up with a whole new code-base developers didn't write
-which they'd now need to maintain.
-
-Instead AI is only used to generate the initial Data Models within a **TypeScript Declaration file**
-which we've found is the best format supported by AI models that's also the best typed DSL for defining
-data models with minimal syntax that's easy for humans to read and write.
-
 ### Download preferred Blazor Vue CRUD App
 
 Once you've decided on the Data Models that best matches your requirements, you can download your preferred 
@@ -180,3 +170,12 @@ the Audit Behaviors will also maintain an Audit Trail of all CRUD operations whi
 
 ![](/img/posts/text-to-blazor/okai-audit-form.webp)
 
+### Using AI to only generate Data Models
+
+Whilst the result is a working CRUD App, the approach taken is very different from most AI tools
+which uses AI to generate the entire App that ends up with a whole new code-base developers didn't write
+which they'd now need to maintain.
+
+Instead AI is only used to generate the initial Data Models within a **TypeScript Declaration file**
+which we've found is the best format supported by AI models that's also the best typed DSL for defining
+data models with minimal syntax that's easy for humans to read and write.

…/2025-04-15_identityauth-claims-roles.md …/2025-04-17_identityauth-claims-roles.mdMyApp/_posts/2025-04-15_identityauth-claims-roles.md renamed to MyApp/_posts/2025-04-17_identityauth-claims-roles.md MyApp/_posts/2025-04-15_identityauth-claims-roles.md renamed to MyApp/_posts/2025-04-17_identityauth-claims-roles.md

@@ -1,13 +1,11 @@
 ---
-title: AI Server improvements
+title: AI Server - April 2025 Update
 summary: New SOTA LLMs added, support for thinking responses, Ollama Vision Models & Generate API
 tags: [ai-server,ai,gpt,service-reference,c#,js]
 author: Demis Bellot
 image: ./img/posts/ai-server/bg.webp
 ---
 
-## AI Server improvements
-
 AI Server is our Free OSS Docker self-hosted private gateway to manage API access to multiple LLM APIs, Ollama endpoints, Media APIs, Comfy UI and FFmpeg Agents that's designed as a one-stop solution to manage an organization's AI integrations for all their System Apps with its developer friendly HTTP JSON APIs that supports any programming language or framework.
 
 [![](/img/svgs/ai-server-overview.svg)](https://openai.servicestack.net)
@@ -16,6 +14,8 @@ AI Server is our Free OSS Docker self-hosted private gateway to manage API acces
 Introducing AI Server
 :::
 
+## Support for new Models
+
 This release continues to see a number of improvements to AI Server starting with adding support for popular LLM models added during this release, including:
 
 - **Google:** gemini-pro-2.0, gemini-flash-2.0, gemini-flash-lite-2.0, gemini-flash-thinking-2.0, gemma3
@@ -39,13 +39,6 @@ functionality inside AI Server's Admin UI which lets you monitor your API System
 
 [![](/img/posts/ai-server-improvements/ai-server-logging.webp)](https://docs.servicestack.net/admin-ui-profiling)
 
-## Support for Thinking Responses
-
-With the rise and popularity of **Thinking** Models we've added custom rendering of *thinking* responses in a collapsible
-and scrollable container:
-
-[![](/img/posts/ai-server-improvements/ai-server-thinking.png)](https://docs.servicestack.net/ai-server/chat)
-
 ## Support for Ollama Vision Models
 
 By default [ImageToText](/ai-server/image-to-text) uses a purpose-specific **Florence 2 Vision model** with ComfyUI for its functionality which is capable of generating a very short description about an image, e.g:
@@ -92,3 +85,11 @@ To support Ollama's vision models AI Server added a new feature pipeline around
 - [OllamaGeneration](https://openai.servicestack.net/ui/OllamaGeneration): Synchronous invocation of Ollama's Generate API
 - [QueueOllamaGeneration](https://openai.servicestack.net/ui/QueueOllamaGeneration): Asynchronous or Web Callback invocation of Ollama's Generate API
 - [GetOllamaGenerationStatus](https://openai.servicestack.net/ui/GetOllamaGenerationStatus): Get the generation status of an Ollama Generate API
+
+## Support for Thinking Responses
+
+With the rise and popularity of **Thinking** Models we've added custom rendering of *thinking* responses in a collapsible
+and scrollable container:
+
+[![](/img/posts/ai-server-improvements/ai-server-thinking.png)](https://docs.servicestack.net/ai-server/chat)
+

MyApp/_posts/2025-04-24_text-to-blazor-premium.md

@@ -1,5 +1,5 @@
 ---
-title: AI Server improvements
+title: AI Server - April 2025 Update
 url: https://docs.servicestack.net/ai-server/
 image: /img/posts/ai-server/ai-server-splash.png
 order: 4