RodrigTech

Tag: Serveless

  • Phi-3.5 Mixture of Experts

    —

    by

    rodrigtech
    in

    Introduction Microsoft has open-sourced its Phi-3.5 Mixture of Experts model recently on the Azure AI Studio catalog provided as a (Model-as-a-Service) that you can run on Azure or you can also use Huggingface to utilize this model. The first question depending how much you’re following along with the constant upstream releases of models is the…

  • RouteLLM Unlocking Cost Effective LLM Routing

    —

    by

    rodrigtech
    in

    Introduction Costs associated with using closed-source large language models can add up in the use cases of complex tasks due to the nature of how tokens are priced for using APIs. RouteLLM is a open-sourced project that creates a method to determine based on the query a user sends which LLM to choose based on…

  • Github Actions with Azure ML Jobs

    —

    by

    rodrigtech
    in

    Introduction Its no secret that Github is a premier development platform for Source Control Management and does have a robust features that also allow for Continuous Integration/Continuous Deployment. These features are a part of the use of Github Actions, in this blog post I’m going to use the example code in a repository here this…

  • Batch Jobs in Azure OpenAI

    —

    by

    rodrigtech
    in

    Introduction In the existing landscape of Generative AI, optimizing API submissions is crucial for both cost and performance. Whether you’re fine-tuning token usage or streamlining context-aware requests using Retrieval-Augmented Generation (RAG), finding the right tools can make a significant difference. One of the most promising solutions is the Azure OpenAI Batch API, designed specifically for…

  • Vertex AI Agents

    —

    by

    rodrigtech
    in

    Google Cloud Platform’s Vertex AI offers a comprehensive suite of tools designed to simplify the process of building, deploying, and scaling machine learning models. One of the standout features of Vertex AI is its support for Agents, which are frameworks that enable seamless integration and automation within AI workflows. In this blog post, we’ll delve…

  • How to Evaluate a Cloud Native Application Platform: What to evaluate and consider

    —

    by

    rodrigtech
    in

    In order to evaluate a cloud native application platform, it is important to understand what to look for and the different aspects of architecture. There are many benefits to using a cloud native application platform, including the ability to scale applications and manage resources more effectively. When choosing a platform, it is important to consider…

  • Serverless App Engine Logic App

    —

    by

    rodrigtech
    in

    While exploring the services in Azure, I’ve been in constant thought of how to use the Logic App service offered Logic App Designer. While exploring more in-depth MS Documentation I’ve created a logic app for a small project on the calculating the time to travel to my local university on the days I have lectures.…