Build an Offline Hybrid RAG Stack with ONNX and Foundry Local | Microsoft Community Hub If you are building local AI applications, basic retrieval augmented generation is often only the starting point. This sample shows a more practical...

Build an Offline Hybrid RAG Stack with ONNX and Foundry Local | by Lee Stott

techcommunity.microsoft.com/blog/educato...

#ai #onnx #rag #foundry #foundrylocal #softwaredev #javascript #npm

Windows App SDK 2.0 release notes - Windows apps Provides information about what's new in Windows App SDK 2.0.

Windows App SDK Version 2.0 Experimental 6 (2.0.0-Experimental6) Release Notes | Microsoft Learn

buff.ly/aCtHIDw

#windowsdev #winui #dotnet #xaml #csharp #cpp #windowsappsdk #onnx #windowsai

GitHub - inference4j/inference4j: Java Inference API for Onnx models Java Inference API for Onnx models. Contribute to inference4j/inference4j development by creating an account on GitHub.

inference4j: Java Inference API for Onnx models. Run AI models in Java. Three lines of code, zero setup.

#ai #inference #java #models #onnx

github.com/inference4j/...

Inside the Web AI Revolution: On-Device ML, WebGPU, and Real-World Deployments Client-Side AI Systems: Integrating WebGPU, ONNX, MediaPipe, and Built-In Browser Models

Inside the Web AI Revolution: On-Device ML, WebGPU, and Real-World Deployments #webai #webgpu #webassembly #onnx #llm #mediapipe senoritadeveloper.medium.com/inside-the-w...

Machine Learning in Java - SPAM detection using ONNX - foojay.io See how to use machine learning in java by building a Spring Boot API for Spam Detection using the ONNX Runtime for Java.

New on Foojay: Learn how to build a spam detection system in Java using machine learning models with ONNX. Zikani Nyirenda Mwase shows you the practical implementation.

foojay.io/today/machin...

#Java #MachineLearning #ONNX

Simple OCR and NER Feature Extraction in C# with ONNX

Skip the LLM for entity extraction. This post walks through Tesseract OCR plus BERT NER in C# with ONNX to get fast, private, deterministic entities from scanned text. #csharp #dotnet #onnx

Toxicity detection isn’t a keyword problem. It’s a semantic one.

I rebuilt a production-grade toxicity guardrail in Java using Quarkus, ONNX, and a dedicated classifier model instead of pattern matching.

Hands-on, opinionated, and built for real systems 👇
buff.ly/tQNkjoR

#Java #Quarkus #ONNX

“I’m fine.” Parents know that sentence can mean anything.

So can your customer emails, support tickets, and Slack messages, and most software systems are terrible at reading them.

I built a small #Java + #Quarkus API to explore emotion detection.

buff.ly/8V0AFuS
#ONNX #AIEngineering #NLP

ASUS UGen300 USB AI Accelerator targets edge inference with Hailo-10H ASUS has announced the UGen300 USB AI Accelerator, a compact external device designed to add hardware-accelerated machine learning and generative inference capabilities to existing systems over a USB connection. The UGen300 is built around the Hailo Hailo-10H processor, which ASUS rates at up to 40 TOPS (INT4) of inference performance. The accelerator integrates 8 GB […]

Why Java is the real production language for AI.

Python is ideal for experiments, but enterprise AI needs predictable concurrency, type safety, and stable runtimes. Java already gives us that, plus native performance through ONNX Runtime and Project Panama.

Read: buff.ly/0j6CZ8O

#Java #AI #ONNX

Intel NPU Driver Now Available in openSUSE Versions As the founder of the openSUSE Innovator initiative initiative, and a member of the openSUSE and Intel Innovator communities, I maintain my ongoing commitmen...

Check out the support for Intel NPU devices, enabling AI workloads like #LLMs and #ONNX inference without a discrete GPU. The driver is available as an #RPM package thanks to the #openSUSE for Innovators initiative. news.opensuse.org/2025/12/02/N...

Optimizing AI for Mobile: The Power of Model Quantization (2) Part 2: Choosing the Right Quantization Method for Real-World Models

Following up on my previous post, this is the second installment in my series on on-device AI benchmarks.

medium.com/@cupid20103/...

#ai #on_device_ai #onnx #executorch #quantization #hugging_face

Magika 1.0 goes stable as Google rebuilds its file detection tool in Rust Google’s Magika 1.0 is now stable and rebuilt in Rust, offering faster file detection and support for over 200 modern file formats.

ONNX and DirectML execution provider guide - part 1 - AMD GPUOpen Learn how to optimize neural network inference on AMD hardware using the ONNX Runtime with the DirectML execution provider and DirectX 12 in the first part of our guide.

🚀 Unlock blazing-fast neural network inference on AMD hardware!

Discover how to maximize #ONNX Runtime + #DirectML with DirectX 12 for seamless GPU pipelines.

🛠️ Dive into practical setup tips and code samples in our latest guide: gpuopen.com/learn/onnx-d...

Samsung Galaxy Book 6 Pro surge em benchmark com novo chip Intel Panther Lake

Samsung Galaxy Book 6 Pro surge em benchmark com novo chip Intel Panther Lake

#base #benchmark #CES #computador #cpu #framework #gpu #ia #Intel #metadados #ONNX #processador #processadores #ram #samsung #windows

📰 NVIDIA dan Oracle Percepat Transformasi AI Enterprise dan Pemrosesan Data

👉 Baca artikel lengkap di sini: ahmandonk.com/2025/10/16/oracle-nvidia...

#ai #database #26ai #ai #for #data #autonomous #ai #lakehouse #exadata #mcp #nvidia #onnx #oracle #rag #vector #search

ONNX and Onyx: The Ultimate Combo for AI Model Deployment ONNX & Onyx AI: Streamline AI deployment. ONNX converts models for cross-platform use, Onyx offers self-hosted AI management. Boost efficiency, ensure compatibility.

Two Onyx techs—ONNX for model portability, Onyx AI for platform management—are streamlining AI deployment. Which approach better suits your production needs: framework interoperability or enterprise-ready platforms?
#Onyx #ONNX #AI
open.substack.com/pub/pythonli...

GitHub - NeptuneHub/AudioMuse-AI: AudioMuse-AI is an Open Source Dockerized environment that brings automatic playlist generation to your self-hosted music library. Using powerful tools like Librosa a... AudioMuse-AI is an Open Source Dockerized environment that brings automatic playlist generation to your self-hosted music library. Using powerful tools like Librosa and ONNX, it performs sonic anal...

AudioMuse-AI is a #free an #opensource tool for automatic playlist generation and sonic analysis to your #selfhosted music libraries like #jellyfin #navidrome and #lyrion. Powered by #librosa and #ONNX, it analyzes your audio to create mood-based playlists
github.com/NeptuneHub/A...

ONNX-Net Enables Architecture Encoding for Performance Prediction

ONNX-Bench aggregates over 600 k architecture-accuracy pairs in ONNX format, and ONNX-Net uses natural-language descriptions to predict performance with strong zero-shot accuracy. Read more: getnews.me/onnx-net-enables-archite... #onnx #nas #ml

Live Depth Point Cloud + Rain Collisions

This project is a real-time, browser-based visualizer that turns a live depth + RGB stream into a 3D

github.com/sylwesterdigital/webcam-monocular-depth

#DepthSensing #PointCloud #ThreeJS #WebGL #WebXR #ComputerVision #MiDaS #PyTorch #ONNX #RealTime #AR

Windows ML is generally available: Empowering developers to scale local AI across Windows devices The future of AI is hybrid, utilizing the respective strengths of cloud and client while harnessing every Windows device to achieve more. At Microsoft, we are reimagining what’s possible by bringing…

Windows ML is generally available: Empowering developers to scale local AI across Windows devices

buff.ly/BHl76LH

#windowsdev #windowsml #ai #windowsappsdk #dotnet #onnx

What is Windows ML Learn how Windows Machine Learning (ML) helps your Windows apps run AI models locally.

What is Windows ML | Microsoft Learn

buff.ly/mlSJvxO

#windowsml #windowsappsdk #windowsdev #ai #onnx

Mastering C++ Computer Vision Serving: Your Powerful 10-Step Guide to High-Performance AI Deployment In the rapidly evolving world of artificial intelligence, particularly in computer vision, deploying models with speed, efficiency, and minimal latency is paramount. While Python has become the go-to for rapid prototyping and development, when it comes to production-grade, high-performance C++ computer vision serving, the compiled power of C++ often emerges as the superior choice. This in-depth guide will walk you through the process of building a robust and efficient computer vision model serving solution using C++, leveraging key technologies like ONNX for model interoperability, OpenCV for image processing, Docker for streamlined dependency management, and Crow for building a lightweight REST API.

C++ computer vision serving is the secret to high-performance AI! Learn 10 proven steps for fast, efficient model deployment. #CPlusPlus #ComputerVision #AI #Docker #ONNX #OpenCV #MachineLearning #AIDeployment

Create embeddings in SQL Server 2025 RC0 with a local ONNX model on Windows - Azure SQL Devs’ Corner Azure SQL Devs’ Corner - Azure SQL Create embeddings in SQL Server 2025 RC0 with a local ONNX model on Windows

Create embeddings in #SQLServer2025 RC0 with a local #ONNX model on Windows
devblogs.microsoft.com/azure-sql/cr...

#Microsoft #SQLServer #OpenAI #AI #MadeiraData

Original post on pyimagesearch.com

Run YOLO Model in the Browser with ONNX, WebAssembly, and Next.js Table of Contents Run YOLO Model in the Browser with ONNX, WebAssembly, and Next.js What Is Browser-Based Inference and Why Does It...

#Computer #Vision #Next.js #ONNX #Real-Time #Inference […]

[Original post on pyimagesearch.com]

Original post on pyimagesearch.com

Run YOLO Model in the Browser with ONNX, WebAssembly, and Next.js Table of Contents Run YOLO Model in the Browser with ONNX, WebAssembly, and Next.js What Is Browser-Based Inference and Why Does It...

#Computer #Vision #Next.js #ONNX #Real-Time #Inference […]

[Original post on pyimagesearch.com]

Real-Time AI on the Edge: Deploying a Quantized LLM on Raspberry Pi with ONNX From Cloud to Circuit Board — How I Packed a Language Model into a $35 Computer for Offline Inference

Real-Time AI on the Edge: Deploying a Quantized LLM on Raspberry Pi with ONNX From Cloud to Circuit Board — How I Packed a Language Model into a $35 Computer for Offline Inference Continue re...

#llm #raspberry-pi #edge-ai #machine-learning #onnx

Origin | Interest | Match

Can you run modern #AI models in Delphi? Yes, and we’ll show you how.

We’ve put together a demo where we show how to use #ONNX Runtime in #Delphi to run #objectdetection. Only practical steps, real code, and working results.

Watch the full video here: youtu.be/WDaCjraF9ts

3/
ONNX is a standard format to convert models between ML frameworks.
Train in PyTorch, export to ONNX, and now your model can run in many different environments.
ONNXRuntime takes it further with cross-platform execution in Python, JS, Rust, mobile and more.
#ONNX #MLops