PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

OpenSSA: Small Specialist Agents based on Domain-Aware Neurosymbolic Agent (DANA) architecture for industrial problem-solving

roadmap to applied ai

Ontology, and Knowledge graph based RAG that uses local LLM.

AI SDK Tutorials helps you to get familiar with AI Software Development Kit (AI SDK) through a set of end-to-end tutorials, how-to jupyter notebooks, and how-to guides.

[CVPRW'25] Official Code For "SK-RD4AD: Skip-Connected Reverse Distillation for One-Class Anomaly Detection"

Industrial AI Agents using LLMs

Async-first, production-grade AI agent framework with workflow, RAG, observability & multi-agent teams（Python 智能体框架）

An end-to-end deep learning system for automated PCB defect detection that combines computer vision with domain expertise. This project demonstrates the practical application of AI in industrial quality control, achieving 91.2% F1-score on multi-label defect classification.

WeldFusionNet: Multimodal deep learning for automated weld defect classification using sensor, audio, and video data (F1: 0.9567)

Build an enterprise-level AI agent operating system enabling cross-departmental and cross-system intelligent collaboration.

The Compositional Agentic Architecture (CAA): A blueprint for building reliable, deterministic, and safe industrial AI agents.

A visual editor to convert Chemical P&IDs into Neo4j Knowledge Graphs for Industrial AI/RAG. (Build by Expert + AI)

Real-time Industrial Anomaly Defect Inference Detection implemented by cpp（实时工业缺陷检测cpp）

Zero and few-shot industrial image anomaly detection framework comparing AnomalyDINO & MuSc models across MVTec AD, BTAD, and ViSA datasets with MLflow tracking and flexible configuration.

This article presents a reference architecture to enhance the compatibility of Siemens Industrial Artificial Intelligence (Industrial AI) products with Microsoft Azure.

AI Software Development Kit is a Python library that allows you to create, package, and test AI inference pipelines for the AI Inference Server.

Few-shot bearing fault diagnosis using multimodal LLMs and prototypical networks

Automatically identify whether the sounds produced by industrial machines are normal or anomalous (faulty machines). This is crucial for ensuring efficient and safe operations in the context of AI-based factory automation.

This repository provides code for the paper "Vipul Bansal, Yong Chen, Shiyu Zhou, Component-Wise Markov Decision Process for Solving Condition Based Maintenance of Large Multi-Component Systems with Economic Dependence"