update new podcasts

Author: mythz

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

@@ -0,0 +1,16 @@
+---
+title: Text to Blazor upgraded to use best coding LLMs
+summary: Text to Blazor now generates CRUD Apps using best coding models from Google, Anthropic, Meta, DeepSeek & Mistral
+tags: [okai,ai,autoquery,blazor,vue]
+author: Demis Bellot
+url: https://media.servicestack.com/podcasts/text-to-blazor-premium.mp3
+media: {size:7818860,duration:779.808000,format:mp3}
+---
+
+This episode looks at the latest version of **Text to Blazor** that has been upgraded to utilize top-tier AI coding models from various leading companies to generate CRUD applications. 
+
+This tool allows users to input a text description and receive five different sets of data models, APIs, database migrations, and admin UIs, enabling them to select the best fit. 
+
+Unlike some AI tools, it primarily focuses on generating TypeScript data models, which are then used within existing Blazor templates to create functional admin or public-facing applications with automatically generated CRUD functionalities and optional audit logging. 
+
+Over one hundred Blazor CRUD applications have already been created using this enhanced system. The generated applications include features like instant admin UIs, database migration scripts, and the ability to create new records directly from search dialogs.

MyApp/_podcasts/2025-04-29_ai-server-improvements.md

@@ -0,0 +1,16 @@
+---
+title: AI Server improvements
+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
+url: https://media.servicestack.com/podcasts/angular-template.mp3
+media: {size:3086348,duration:313.176000,format:mp3}
+---
+
+This episode covers the significant upgrades to **AI Server**, an open-source tool for managing various AI model APIs. 
+
+A key enhancement is the addition of numerous **new state-of-the-art large language models** from providers like Google, OpenAI, and Meta. 
+
+The update also introduces support for **"thinking" responses** with specialized rendering and integrates **Ollama Vision Models**, enabling image understanding capabilities using models like Gemma and Mistral. Furthermore, new **OllamaGenerate endpoints** were implemented to facilitate interactions with these vision models for tasks such as image-to-text conversion. 
+
+These improvements aim to provide a more comprehensive and versatile platform for managing AI integrations.