open-edge-platform · avinash-palleti · Dec 12, 2025 · Nov 30, 2025 · Dec 8, 2025 · Dec 8, 2025
@@ -0,0 +1,35 @@
+# Smart Classroom
+
+<!--hide_directive
+<div class="component_card_widget">
+  <a class="icon_github" href="https://github.com/open-edge-platform/edge-ai-suites/tree/release-2025.2.0/education-ai-suite/smart-classroom">
+     GitHub project
+  </a>
+  <a class="icon_document" href="https://github.com/open-edge-platform/edge-ai-suites/blob/release-2025.2.0/education-ai-suite/smart-classroom/README.md">
+     Readme
+  </a>
+</div>
+hide_directive-->
+
+The Smart Classroom project is a modular, extensible framework designed to process and summarize educational content using advanced AI models. It supports transcription, summarization, and future capabilities like video understanding and real-time analysis.
+
+The main features are as follows:
+
+- **Audio file processing and transcription** with ASR models (e.g., Whisper, Paraformer)
+- **Summarization** using powerful LLMs (e.g., Qwen, LLaMA)
+- **Plug-and-play architecture** for integrating new ASR and LLM models
+- **API-first design** ready for frontend integration
+- Ready-to-extend for real-time streaming, diarization, translation, and video analysis
+
+<!--hide_directive
+:::{toctree}
+:hidden:
+
+system-requirements
+how-it-works
+get-started
+application-flow
+release-notes
+
+:::
+hide_directive-->
@@ -1,5 +1,15 @@
-HMI Augmented Worker
-============================================
+# HMI Augmented Worker
+
+<!--hide_directive
+<div class="component_card_widget">
+  <a class="icon_github" href="https://github.com/open-edge-platform/edge-ai-suites/tree/release-2025.2.0/manufacturing-ai-suite/hmi-augmented-worker">
+     GitHub project
+  </a>
+  <a class="icon_document" href="https://github.com/open-edge-platform/edge-ai-suites/blob/release-2025.2.0/manufacturing-ai-suite/hmi-augmented-worker/README.md">
+     Readme
+  </a>
+</div>
+hide_directive-->
 
 The HMI Augmented Worker is a RAG enabled HMI application deployed on Type-2 hypervisors.
 Deploying RAG-enabled HMI applications in a Type-2 hypervisor setup allows flexible and
@@ -8,10 +18,10 @@ a single physical machine.
 
 In this architecture, the HMI application operates within a Windows® virtual machine managed
 by a Type-2 hypervisor such as
-`EMT <https://github.com/open-edge-platform/edge-microvisor-toolkit>`__.
+[EMT](https://github.com/open-edge-platform/edge-microvisor-toolkit).
 The Retrieval-Augmented Generation (RAG) pipeline and supporting AI services are deployed
 natively on a host system, which is EMT in this implementation.
-`Chat Question-and-Answer Core <https://github.com/open-edge-platform/edge-ai-libraries/tree/release-2025.2.0/sample-applications/chat-question-and-answer-core>`__
+[Chat Question-and-Answer Core](https://github.com/open-edge-platform/edge-ai-libraries/tree/release-2025.2.0/sample-applications/chat-question-and-answer-core)
 provides the RAG capability.
 This separation ensures robust isolation between the HMI and AI components, enabling
 independent scaling, maintenance, and updates. The setup leverages the strengths of both
@@ -29,15 +39,13 @@ productivity for machine operators. In this sample application, the focus is on
 an RAG pipeline in a Type-2 Hypervisor-based setup. There is no reference HMI used and the
 user is expected to do the HMI integration using the RAG pipeline APIs provided.
 
-How it works
-############
+## How it works
 
 This section highlights the high-level architecture of the sample application.
 
-High-Level Architecture
-+++++++++++++++++++++++
+### High-Level Architecture
 
-The system has a RAG pipeline reusing ``Chat Question and Answer Core`` application
+The system has a RAG pipeline reusing `Chat Question and Answer Core` application
 running on the host alongside a typical HMI application which is executing on
 the Windows® Guest VM (virtual machine). A knowledge base is initialized by using the
 contents from a pre-configured folder. The folder contains the knowledge base like user
@@ -51,27 +59,23 @@ and runs independently from the HMI application. The HMI application is responsi
 providing the required interface along with associated user experience to enable
 the operator to access this knowledge base.
 
+![HMI augmented worker architecture diagram](./_images/hmi-augmented-worker-architecture.png)
 
-.. image:: ./_images/hmi-augmented-worker-architecture.png
-   :alt: HMI Augmented Worker Architecture Diagram
-
-Chat Question-and-Answer Core (ChatQnA Core)
-++++++++++++++++++++++++++++++++++++++++++++
+### Chat Question-and-Answer Core (ChatQnA Core)
 
 The 'ChatQnA Core' sample application serves as a basic Retrieval Augmented Generation
 (RAG) pipeline, allowing users to pose questions and obtain answers, even from their
 private data corpus. This sample application illustrates the construction of RAG pipelines.
 It is designed for minimal memory usage, being developed as a single, monolithic application
 with the complete RAG pipeline integrated into one microservice.
 
-The 'ChatQnA Core` application should be setup on the host system. For further details,
-visit `Chat Question-and-Answer Core Sample Application Overview <https://github.com/open-edge-platform/edge-ai-libraries/blob/release-2025.2.0/sample-applications/chat-question-and-answer-core/docs/user-guide/overview.md>`__.
+The `ChatQnA Core` application should be setup on the host system. For further details,
+visit [Chat Question-and-Answer Core Sample Application Overview](https://github.com/open-edge-platform/edge-ai-libraries/blob/release-2025.2.0/sample-applications/chat-question-and-answer-core/docs/user-guide/overview.md).
 The application is used as is without any changes.
 The configurable parameters like the LLM model, Embedding model, Reranker model, or
 Retriever model are setup based on the HMI application requirement.
 
-File Watcher Service
-++++++++++++++++++++
+### File Watcher Service
 
 The File Watcher Service runs alongside with HMI application on the Windows environment,
 consistently observing file system activities like creation, modification, and deletion.
@@ -80,11 +84,9 @@ When changes are detected, it sends the pertinent file data over the network to
 Retrieval-Augmented Generation (RAG) workflows. The watcher service logic is shown in
 the following flow diagram:
 
-.. image:: ./_images/file-watcher-implementation-logic.png
-   :alt: File Watcher Service Implementation Logic Flow
+![file watcher service implementation logic flow](./_images/file-watcher-implementation-logic.png)
 
-Human Machine Interface(HMI) Application
-++++++++++++++++++++++++++++++++++++++++
+### Human Machine Interface(HMI) Application
 
 A Human-Machine Interface(HMI) can vary depending on the use case or the creator.
 While HMIs generally serve as interface connecting users to machines, systems, or
@@ -96,17 +98,19 @@ an accurate summary to state that this sample application illustrates how the `C
 RAG pipeline can be executed in a Type-2 Hypervisor setup enabling applications like HMI
 to benefit from it.
 
-Supporting Resources
-####################
+## Supporting Resources
 
 For more comprehensive guidance on beginning, see the
-:doc:`Getting Started Guide <./get-started>`.
-
-.. toctree::
-   :hidden:
-
-   system-requirements
-   get-started
-   release-notes
-   how-to-build-from-source
-   Source Code <https://github.com/open-edge-platform/edge-ai-suites/tree/release-2025.2.0/manufacturing-ai-suite/hmi-augmented-worker>
+[Getting Started Guide](./get-started).
+
+<!--hide_directive
+:::{toctree}
+:hidden:
+
+system-requirements
+get-started
+release-notes
+how-to-build-from-source
+Source Code <https://github.com/open-edge-platform/edge-ai-suites/tree/release-2025.2.0/manufacturing-ai-suite/hmi-augmented-worker>
+:::
+hide_directive-->
@@ -11,7 +11,7 @@ Let's discuss how this architecture translates to data flow in the weld defect d
 
 ### 1. **Weld Data Simulator**
 
-The Weld Data Simulator uses the sets of time synchronized .avi and .csv files from the `edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-multimodal/weld-data-simulator/simulation-data/`, subset of test dataset coming from [Intel_Robotic_Welding_Multimodal_Dataset](https://huggingface.co/datasets/amr-lopezjos/Intel_Robotic_Welding_Multimodal_Dataset).
+The Weld Data Simulator uses sets of time synchronized .avi and .csv files from the `edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-multimodal/weld-data-simulator/simulation-data/` subset of test dataset coming from [Intel_Robotic_Welding_Multimodal_Dataset](https://huggingface.co/datasets/amr-lopezjos/Intel_Robotic_Welding_Multimodal_Dataset).
 It ingests the .avi files as RTSP streams via the **mediamtx** server. This enables real-time video ingestion, simulating camera feeds for weld defect detection.
 Similarly, it ingests the .csv files as data points into **Telegraf** using the **MQTT** protocol.
 

@@ -1,5 +1,13 @@
 # Weld Anomaly Detection
 
+<!--hide_directive
+<div class="component_card_widget">
+  <a class="icon_github" href="https://github.com/open-edge-platform/edge-ai-suites/tree/release-2025.2.0/manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection">
+     GitHub project
+  </a>
+  </div>
+hide_directive-->
+
 This sample app demonstrates how AI-driven analytics enable edge devices to monitor weld quality.
 It detects anomalous weld patterns and alerts operators for timely intervention,
 ensuring proactive maintenance, safety, and operational efficiency. No more failures
@@ -81,7 +89,6 @@ detect the anomalous power generation data points relative to wind speed.
 
 **Note**: Please note, CatBoost models doesn't run on Intel GPUs.
 
-
 ##### **`tick_scripts/`**
 
 The TICKScript `weld_anomaly_detector.tick` determines processing of the input data coming in.
@@ -92,4 +99,3 @@ By default, it is configured to publish the alerts to **MQTT**.
 
 The `weld_anomaly_detector.cb` is a model built using the CatBoostClassifier Algo of CatBoost ML
 library.
-
@@ -1,5 +1,13 @@
 # Wind Turbine Anomaly Detection
 
+<!--hide_directive
+<div class="component_card_widget">
+  <a class="icon_github" href="https://github.com/open-edge-platform/edge-ai-suites/tree/release-2025.2.0/manufacturing-ai-suite/industrial-edge-insights-time-series/apps/wind-turbine-anomaly-detection">
+     GitHub project
+  </a>
+  </div>
+hide_directive-->
+
 This sample app demonstrates a time series use case by detecting anomalous power generation
 patterns in wind turbines, relative to wind speed. By identifying deviations, it helps
 optimize maintenance schedules and prevent potential turbine failures, enhancing
@@ -11,7 +19,6 @@ If you want to start working with it, instead, check out the
 [Get Started Guide](../get-started.md) or [How-to Guides](../how-to-guides/index.md)
 for Time-series applications.
 
-
 ## App Architecture
 
 As seen in the following architecture diagram, the sample app at a high-level comprises of data simulators(can act as data destinations if configured) - these in the real world would be the physical devices, the generic Time Series AI stack based on **TICK Stack** comprising of Telegraf, InfluxDB, Time Series Analytics microservice using Kapacitor and Grafana.

@@ -1,19 +1,27 @@
-Pallet Defect Detection
-==============================
+# Pallet Defect Detection
+
+<!--hide_directive
+<div class="component_card_widget">
+  <a class="icon_github" href="https://github.com/open-edge-platform/edge-ai-suites/tree/release-2025.2.0/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection">
+     GitHub project
+  </a>
+  <a class="icon_document" href="https://github.com/open-edge-platform/edge-ai-suites/blob/release-2025.2.0/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/README.md">
+     Readme
+  </a>
+</div>
+hide_directive-->
 
 Automated quality control with AI-driven vision systems.
 
-Overview
-########
+## Overview
 
 This Sample Application enables real-time pallet condition monitoring by running inference
 workflows across multiple AI models. It connects multiple video streams from warehouse
 cameras to AI-powered pipelines, all operating efficiently on a single industrial PC.
 This solution enhances logistics efficiency and inventory management by detecting
 defects before they impact operations.
 
-How It Works
-############
+## How It Works
 
 This sample application consists of the following microservices:
 DL Streamer Pipeline Server, Model Registry Microservice(MRaaS), MediaMTX server,
@@ -31,39 +39,35 @@ be seen on Prometheus UI. Any desired AI model from the Model Registry Microserv
 (which can interact with Postgres, Minio and Geti Server for getting the model) can be
 pulled into DL Streamer Pipeline Server and used for inference in the sample application.
 
-.. figure:: ./images/industrial-edge-insights-vision-architecture.drawio.svg
-   :alt: Architecture and high-level representation of the flow of data through the architecture
-
-   Figure 1: Architecture diagram
+![architecture and high-level representation of the flow of data through the architecture](./images/industrial-edge-insights-vision-architecture.drawio.svg)
 
 This sample application is built with the following Intel Edge AI Stack Microservices:
 
-- `DL Streamer Pipeline Server <https://docs.openedgeplatform.intel.com/2025.2/edge-ai-libraries/dlstreamer-pipeline-server/index.html>`__
+- [DL Streamer Pipeline Server](https://docs.openedgeplatform.intel.com/2025.2/edge-ai-libraries/dlstreamer-pipeline-server/index.html)
   is an interoperable containerized microservice based on Python for video ingestion
   and deep learning inferencing functions.
-- `Model Registry Microservice <https://docs.openedgeplatform.intel.com/2025.2/edge-ai-libraries/model-registry/index.html>`__
+- [Model Registry Microservice](https://docs.openedgeplatform.intel.com/2025.2/edge-ai-libraries/model-registry/index.html)
   provides a centralized repository that facilitates the management of AI models
 
 It also consists of the below Third-party microservices:
 
-- `Nginx <https://hub.docker.com/_/nginx>`__
+- [Nginx](https://hub.docker.com/_/nginx)
   is a high-performance web server and reverse proxy that provides TLS termination and unified HTTPS access.
-- `MediaMTX Server <https://hub.docker.com/r/bluenviron/mediamtx>`__
+- [MediaMTX Server](https://hub.docker.com/r/bluenviron/mediamtx)
   is a real-time media server and media proxy that allows to publish webrtc stream.
-- `Coturn Server <https://hub.docker.com/r/coturn/coturn>`__
+- [Coturn Server](https://hub.docker.com/r/coturn/coturn)
   is a media traffic NAT traversal server and gateway.
-- `Open telemetry Collector <https://hub.docker.com/r/otel/opentelemetry-collector-contrib>`__
+- [Open telemetry Collector](https://hub.docker.com/r/otel/opentelemetry-collector-contrib)
   is a set of receivers, exporters, processors, connectors for Open Telemetry.
-- `Prometheus <https://hub.docker.com/r/prom/prometheus>`__
+- [Prometheus](https://hub.docker.com/r/prom/prometheus)
   is a systems and service monitoring system used for viewing Open Telemetry.
-- `Postgres <https://hub.docker.com/_/postgres>`__
+- [Postgres](https://hub.docker.com/_/postgres)
   is object-relational database system that provides reliability and data integrity.
-- `Minio <https://hub.docker.com/r/minio/minio>`__
+- [Minio](https://hub.docker.com/r/minio/minio)
   is high performance object storage that is API compatible with
   Amazon S3 cloud storage service.
 
-Features
-########
+## Features
 
 This sample application offers the following features:
 
@@ -73,33 +77,35 @@ This sample application offers the following features:
 - Interconnected warehouses deliver analytics for quick and informed tracking and
   decision making.
 
-
-.. toctree::
-   :hidden:
-
-   overview-architecture
-   system-requirements
-   get-started
-   troubleshooting-guide
-   how-to-change-input-video-source
-   how-to-deploy-using-helm-charts
-   how-to-deploy-with-edge-orchestrator
-   how-to-enable-mlops
-   how-to-manage-pipelines
-   how-to-run-multiple-ai-pipelines
-   how-to-scale-video-resolution
-   how-to-use-an-ai-model-and-video-file-of-your-own
-   how-to-use-opcua-publisher
-   how-to-run-store-frames-in-s3
-   how-to-view-telemetry-data
-   how-to-use-gpu-for-inference
-   how-to-start-mqtt-publisher
-   how-to-integrate-balluff-sdk
-   how-to-install-balluff-sdk-on-host
-   how-to-integrate-pylon-sdk
-   how-to-install-pylon-sdk-on-host.md
-   how-to-benchmark
-   api-reference
-   environment-variables
-
-   release_notes/Overview
+<!--hide_directive
+:::{toctree}
+:hidden:
+
+overview-architecture
+system-requirements
+get-started
+troubleshooting-guide
+how-to-change-input-video-source
+how-to-deploy-using-helm-charts
+how-to-deploy-with-edge-orchestrator
+how-to-enable-mlops
+how-to-manage-pipelines
+how-to-run-multiple-ai-pipelines
+how-to-scale-video-resolution
+how-to-use-an-ai-model-and-video-file-of-your-own
+how-to-use-opcua-publisher
+how-to-run-store-frames-in-s3
+how-to-view-telemetry-data
+how-to-use-gpu-for-inference
+how-to-start-mqtt-publisher
+how-to-integrate-balluff-sdk
+how-to-install-balluff-sdk-on-host
+how-to-integrate-pylon-sdk
+how-to-install-pylon-sdk-on-host.md
+how-to-benchmark
+api-reference
+environment-variables
+release_notes/Overview
+
+:::
+hide_directive-->