Skip to content

Commit

Permalink
Merge pull request #194 from ssmmoo1/main
Browse files Browse the repository at this point in the history
Add JPS Page
  • Loading branch information
dusty-nv authored Aug 15, 2024
2 parents 9a6f6b5 + f7b1055 commit 4baced8
Show file tree
Hide file tree
Showing 5 changed files with 44 additions and 0 deletions.
Binary file added docs/images/jps_vlm_workflow.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/jps_vlm_workflow.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
1 change: 1 addition & 0 deletions docs/tutorial-intro.md
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,7 @@ Give your locally running LLM an access to vision!
| :---------- | :----------------------------------- |
| **[ROS2 Nodes](./ros.md)** | Optimized LLM and VLM provided as [ROS2 nodes](./ros.md) for robotics |
| **[Holoscan SDK](./tutorial_holoscan.md)** | Use the [Holoscan-SDK](https://github.com/nvidia-holoscan/holoscan-sdk) to run high-throughput, low-latency edge AI pipelines |
| **[Jetson Platform Services](./tutorial_jps.md)** | Quickly build microservice driven vision applications with [Jetson Platform Services](https://developer.nvidia.com/embedded/jetpack/jetson-platform-services-get-started) |
| **[Gapi Workflows](./tutorial_gapi_workflows.md)** | Integrating generative AI into real world environments |
| **[Gapi Micro Services](./tutorial_gapi_microservices.md)** | Wrapping models and code to participate in systems |
| **[Ultralytics YOLOv8](./tutorial_ultralytics.md)** | Run [Ultralytics](https://www.ultralytics.com) YOLOv8 on Jetson with NVIDIA TensorRT. |
Expand Down
42 changes: 42 additions & 0 deletions docs/tutorial_jps.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
# Tutorial - Jetson Platform Services

Jetson Plaform Services (JPS) provide a platform to simplify development, deployment and management of Edge AI applications on NVIDIA Jetson. JPS is a modular & extensible architecture for developers to distill large complex applications into smaller modular microservice with APIs to integrate into other apps & services. At its core are a collection of AI services leveraging generative AI, deep learning, and analytics, which provide state of the art capabilities including video analytics, video understanding and summarization, text based prompting, zero shot detection and spatio temporal analysis of object movement.

![VLM Workflow](images/jps_vlm_workflow.gif)
*VLM Alert Workflow built with JPS*

!!! abstract "What you need"

1. One of the following Jetson devices:

<span class="blobDarkGreen4">Jetson AGX Orin (64GB)</span>
<span class="blobDarkGreen5">Jetson AGX Orin (32GB)</span>
<span class="blobLightGreen3">Jetson Orin NX (16GB)</span>
<span class="blobLightGreen4">Jetson Orin Nano (8GB)</span>

2. Running one of the following versions of [JetPack](https://developer.nvidia.com/embedded/jetpack):

<span class="blobPink2">JetPack 6 (L4T r36.x)</span>
3. Sufficient storage space (preferably with NVMe SSD).

To get started with Jetson Platform Services, follow the quickstart guide to install and setup JPS. Then explore the reference workflows to learn how to use DeepStream, Analytics, Generative AI and more with JPS:

1) [Quick Start Guide](https://docs.nvidia.com/jetson/jps/setup/quick-start.html)
2) [AI Powered Network Video Recorder](https://docs.nvidia.com/jetson/jps/setup/ai-nvr.html)
3) [Zero Shot Detection with NanoOWL](https://docs.nvidia.com/jetson/jps/workflows/zero_shot_detection_workflow.html)
4) [Visual Language Model Alerts](https://docs.nvidia.com/jetson/jps/workflows/vlm_workflow.html)


The reference workflows demonstrate how to use the microservices provided in JPS to build full end to end systems on your Jetson.

![JPS VLM Workflow](images/jps_vlm_workflow.png)
*VLM Alert Workflow Architecture*

View the links below to learn more about Jetson Platform Services:
* [VLM Alert Blog](https://developer.nvidia.com/blog/develop-generative-ai-powered-visual-ai-agents-for-the-edge/)
* [JPS Product Page](https://developer.nvidia.com/embedded/jetpack/jetson-platform-services-get-started)
* [JPS Documentation](https://docs.nvidia.com/jetson/jps/moj-overview.html)
* VLM Alert Demo Video
<div><iframe width="500" height="280" src="https://www.youtube.com/embed/0ZbDzaBfsrw" style="display: inline-block;" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
</div>
1 change: 1 addition & 0 deletions mkdocs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,7 @@ nav:
- API Integrations 🆕:
- ROS2 Nodes: ros.md
- Holoscan SDK: tutorial_holoscan.md
- Jetson Platform Services: tutorial_jps.md
- Gapi Workflows: tutorial_gapi_workflows.md
- Gapi Micro Services: tutorial_gapi_microservices.md
- Ultralytics YOLOv8: tutorial_ultralytics.md
Expand Down

0 comments on commit 4baced8

Please sign in to comment.