-
CPU vs GPU: Which Wins for Running LLMs Locally?
Introduction Running large language models (LLMs) locally has become increasingly accessible, thanks to advancements in hardware and model optimization. For .NET programmers, understanding the performance differences between CPUs and GPUs is crucial to selecting the best setup for their use case. In this blog post, we’ll explore these differences by benchmarking the Llama 3.2 Vision… — read more
-
Full Local RAG scenario using #Phi3, #SemanticKernel and TextMemory. Bonus: Test in CodeSpaces
Hi! Today’s scenario is once again, using Phi-3. You know, a groundbreaking Small Language Model (SLM) that is redefining the capabilities of AI for developers and businesses alike. In this blog post, we will explore the importance of leveraging Phi-3 for full-scale scenarios and how you can test these scenarios for free using the Ollama… — read more
-
Code Sample: Integrating Azure OpenAI Search with #SemanticKernel in .NET
Hi! Today I’ll try to expand a little the scenario described in this Semantic Kernel blog post: “Azure OpenAI On Your Data with Semantic Kernel“. The code below uses an GPT-4o model to support the chat and also is connected to Azure AI Search using SK. While runing this demo, you will notice the mentions… — read more
-
Sample Code using the new OpenAI library for .NET
Hi! The new OpenAI SDK for NET was officially announced, so today, let’s review the annoucement and show some sample code on how to use it. The current blog scenarios are Here is a sample output for the chat demo! And yes, with a funny system message and questions about France! OpenAI SDK for .NET… — read more
-
Powering Up #NET Apps with #Phi-3 and #SemanticKernel
Hi! Introducing the Phi-3 Small Language Model Hi! Phi-3 is an amazing Small Language Model. And hey, it’s also an easy one to use in C#. I already wrote how to use it with ollama, now it’s time to hit the ONNX version. Introduction to Phi-3 Small Language Model The Phi-3 Small Language Model (SLM)… — read more
-
#SemanticKernel and GPT-4o: Image analysis labs
Hi! Introduction to GPT-4o GPT-4o, developed by OpenAI, represents a significant leap forward in AI technology. Dubbed “omni” for its all-encompassing capabilities, GPT-4o is a multimodal model that can process and generate text, audio, and images. It’s designed to facilitate more natural human-computer interactions, responding to audio inputs in as little as 232 milliseconds. This model is… — read more
-
Demo – API Manifest Plugins for Semantic Kernel
Hi! Today, it’s time to share some insights into the world of API Manifest Plugins for Semantic Kernel, these are a cool way to work with OpenAI’s Large Language Models (LLMs). Introduction to API Manifest Plugins for Semantic Kernel Semantic Kernel is at the forefront of AI development, allowing developers to import plugins from OpenAPI… — read more
-
#SemanticKernel: Local LLMs Unleashed on #RaspberryPi 5
Hi! Welcome to the exciting world of local Large Language Models (LLMs) where we’re pushing the boundaries of what’s possible with AI. Today let’s talk about a cool topic: run models locally, especially on devices like the Raspberry Pi 5. Let’s dive into the future of AI, right in our own backyards. Ollama and using… — read more
-
📎 Extending #SemanticKernel using OllamaSharp for chat and text completion
Hi! In previous posts I shared how to host and chat with a Llama 2 model hosted locally with Ollama. (view post). And then I also found OllamaSharp (nuget package and repo). OllamaSharp is a .NET binding for the Ollama API, making it easy to interact with Ollama using your favorite .NET languages. So, I… — read more
-
How to Use #SemanticKernel, Plugins – 2/N
Hi! In the previous posts we learned how to create a simple Semantic Kernel Chat Application Today we will switch a little the interaction with the AI Models, instead of a chat conversation, we will use Plugins. Plugins Let’s start with the PlugIn definition thanks to Microsoft Copilot: A plugin is a unit of functionality… — read more
-
How to Use #SemanticKernel with OpenAI and Azure OpenAI in C# – 1/N
Hi! Today I’m starting a series of posts to describe an “easy way to use” AI Services with Semantic Kernel. I’m a fan of code, so I’ll focus mostly on code samples. Semantic Kernel (via Copilot) Semantic Kernel is a powerful tool that allows developers to integrate cutting-edge language models into their applications with ease.… — read more
-
#SemanticKernel – 📎Chat Service demo running Llama2 LLM locally in Ubuntu
Hi! Today’s post is a demo on how to interact with a local LLM using Semantic Kernel. In my previous post, I wrote about how to use LM Studio to host a local server. Today we will use ollama in Ubuntu to host the LLM. Ollama Ollama is an open-source language model platform designed for… — read more
-
#SemanticKernel – 📎Chat Service demo running Phi-2 LLM locally with #LMStudio
Hi! It’s time to go back to AI and NET, so today’s post is a small demo on how to run a LLM (large language model, this demo using Phi-2) in local mode, and how to interact with the model using Semantic Kernel. LM Studio I’ve tested several products and libraries to run LLMs locally,… — read more
-
How to control your 🚁 drone using #Azure OpenAI or OpenAI APIs and Semantic Kernel
Hi! In my previous post, I wrote about how we can use ChatGPT to generate Python code to control a drone. Today, we are going to use Azure OpenAI Services or OpenAI APIs to generate the same code using GPT models. We are going to use the same prompt that we had for ChatGPT. Running… — read more
-
How to control your 🚁 drone using #ChatGPT
Hi! I’ve been doing live demos of how to use Azure OpenAI Services or OpenAI APIs to generate code to control the drone, so I think I may write about it to have it public for future references. So, using the base code to send and read drone information, we can create a simple prompt… — read more
-
My 1st NET #ChatGPT Plugin. Demo Included!
Hi! Plugins are the hottest topics now, for both ChatGPT and Microsoft products like BingChat and Windows Copilot. After learning and testing using Javascript and Python versions, I decided to create one in NET. I even talk several times about it in my podcast (in Spanish). NET Pet Store ChatGPT Plugin Repository And here is… — read more
-
#Code – 🔌Building Plugins for ChatGPT, Microsoft Bing and Edge
Hi! This one was in my top three announcements from Build 2023. We can now build Chat Plugins for Microsoft Bing and Edge. Look at this 10 min intro: Video Summary: Creating Plugins Microsoft is adopting the same open plugin standard that OpenAI introduced for ChatGPT, enabling interoperability across ChatGPT and the breadth of Microsoft’s copilot offerings.… — read more
-
#AzureIoT – RTSP Webcam, add rtsp camera 📷 capabilities to your Edge Device #JulyOT
Hi ! Today, during my [Let’s setup a Raspberry Pi and a reTerminal as an Azure IoT ☁️ device] session, one of the questions was about what cool scenarios we can run once we have a Raspberry Pi as an Azure IoT Edge device. Besides the use of Cognitive Services (only for x64), a cool… — read more
-
#OpenCV – Convert camera feed 🎦 to Grayscale and resalt Blue 🔵 and Red ❤️
Hi ! A new twist on these days demos, this time: Open a camera feed Convert each frame to grayscale Use a hue mask to resalt colors, Blue and Red Here is a live sample from my office. Note: I created a mask that identifies the Captain America shield, SpyderGwen poster and Ahsoka frame, but… — read more
-
#OpenCV – Replace background with video in camera feed 🎦 (Black Adam ⚡)
Hi ! A new twist on these days demos, based on a request from an online friend. Let’s remove and replace the background from our camera feed using a video. For this demo, I’m using the “Black Adam – Official Trailer 1“. And the output is kind of funny. Hey, funny scenario, and if you… — read more
-
Subscribe
Subscribed
Already have a WordPress.com account? Log in now.
El Bruno 