Add Metropolis NIM Workflows as submodule (#237)

* add vision worfklow assets

* add metropolis workflows submodule to track main

* update top level readme

* fix formatting

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "vision_workflows/metropolis-nim-workflows"]
+	path = vision_workflows/metropolis-nim-workflows
+	url = https://github.com/NVIDIA/metropolis-nim-workflows
+	branch = main

README.md

@@ -16,6 +16,7 @@ This repository is a starting point for developers looking to integrate with the
   * [Knowledge Graph RAG](#knowledge-graph-rag)
   * [Agentic Workflows with Llama 3.1](#agentic-workflows-with-llama-31)
   * [RAG with Local NIM Deployment and LangChain](#rag-with-local-nim-deployment-and-langchain)
+  * [Vision NIM Workflows](#vision-nim-workflows)
 * [Try it Now!](#try-it-now)
 * [RAG](#rag)
   * [RAG Notebooks](#rag-notebooks)
@@ -50,6 +51,23 @@ This example implements a GPU-accelerated pipeline for creating and querying kno
 
 For more information, refer to the [Generative AI Example releases](https://github.com/NVIDIA/GenerativeAIExamples/releases/).
 
+### Vision NIM Workflows
+A collection of Jupyter notebooks, sample code and reference applications built with Vision NIMs.
+
+To pull the vision NIM workflows, clone this repository recursively:
+```
+git clone https://github.com/nvidia/GenerativeAIExamples --recurse-submodules
+```
+
+The workflows will then be located at [GenerativeAIExamples/vision_workflows](vision_workflows/README.md)
+
+Follow the links below to learn more:
+- [Learn how to use VLMs to automatically monitor a video stream for custom events.](nim_workflows/vlm_alerts/README.md)
+- [Learn how to search images with natural language using NV-CLIP.](nim_workflows/nvclip_multimodal_search/README.md)
+- [Learn how to combine VLMs, LLMs and CV models to build a robust text extraction pipeline.](nim_workflows/vision_text_extraction/README.md)
+- [Learn how to use embeddings with NVDINOv2 and a Milvus VectorDB to build a few shot classification model.](nim_workflows/nvdinov2_few_shot/README.md)
+
+
 ## Try it Now!
 
 Experience NVIDIA RAG Pipelines with just a few steps!

vision_workflows/README.md

@@ -0,0 +1,47 @@
+# Vision Workflows with NVIDIA NIM
+
+This submodule includes NIM based workflows for vision applications. To get access to this submodule, do one of the following: 
+
+1) Clone nvidia/GenerativeAIExamples recursively
+```
+git clone https://github.com/nvidia/GenerativeAIExamples --recurse-submodules
+```
+
+2) If you have already cloned the repository without the ```--recurse-submodules``` flag then you can manually pull the submodule
+```
+git submodule update --init
+```
+
+3) You can also clone the vision workflow repository directly
+```
+git clone https://github.com/NVIDIA/metropolis-nim-workflows.git
+```
+
+Once the submodule is pulled or you have cloned the repository directly you can explore the available vision NIM workflows. 
+
+## Available Workflows
+
+### [VLM Alert System](https://github.com/NVIDIA/metropolis-nim-workflows/blob/main/nim_workflows/vlm_alerts/README.md)
+<p float="left">
+<img src="readme_assets/vlm_alert.gif" alt="" width="800"/>
+</p>
+
+### [Structured Text Extraction](https://github.com/NVIDIA/metropolis-nim-workflows/tree/main/nim_workflows/vision_text_extraction)
+<p float="left">
+<img src="readme_assets/text_extraction.gif" alt="" width="800"/>
+</p>
+
+### [NVCLIP Multimodal Search](https://github.com/NVIDIA/metropolis-nim-workflows/tree/main/nim_workflows/nvclip_multimodal_search)
+<p float="left">
+<img src="readme_assets/nvclip_multimodal.gif" alt="" width="800"/>
+</p>
+
+### [NV-DINOv2 Few Shot Classification](https://github.com/NVIDIA/metropolis-nim-workflows/tree/main/nim_workflows/nvdinov2_few_shot)
+<p float="left">
+<img src="readme_assets/few_shot.gif" alt="" width="800"/>
+</p>
+
+
+To learn more, view [this page](https://github.com/NVIDIA/metropolis-nim-workflows)
+
+