# Extension for ChatGPT

**URL:** <https://forums.developer.nvidia.com/t/extension-for-chatgpt/258177>\
**Category:** ChatGPT and Omniverse: AMA June 28th, 2023\
**Tags:** kb, ama\
**Created:** [June 28, 2023, 4:06pm UTC](https://forums.developer.nvidia.com/t/extension-for-chatgpt/258177 "2023-06-28T16:06:39Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![nadeemm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nadeemm/32/367020_2.png) [@nadeemm](https://forums.developer.nvidia.com/u/nadeemm)\
**Post date:** [June 28, 2023, 4:06pm UTC](https://forums.developer.nvidia.com/t/extension-for-chatgpt/258177/1 "2023-06-28T16:06:39Z")

</div>

[  
jcass358](https://forums.developer.nvidia.com/u/jcass358)  
Posted this question as a reply - so I am re-posting it here so everyone can see.

Hello, I am definitely interested in using a tool like ChatGPT, would this event show us how to buld the extension? also how feasible would it be to perform transfer learning on the LLM with all of the NVIDIA information and software publicly available to finetune a model to help out beginners like myself.  
thank you

---

<div class="post-metadata">

**Author:** ![jcass358](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@jcass358](https://forums.developer.nvidia.com/u/jcass358)\
**Post date:** [June 28, 2023, 4:09pm UTC](https://forums.developer.nvidia.com/t/extension-for-chatgpt/258177/2 "2023-06-28T16:09:58Z")

</div>

thank you

---

<div class="post-metadata">

**Author:** ![nadeemm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nadeemm/32/367020_2.png) [@nadeemm](https://forums.developer.nvidia.com/u/nadeemm)\
**Post date:** [June 28, 2023, 4:11pm UTC](https://forums.developer.nvidia.com/t/extension-for-chatgpt/258177/3 "2023-06-28T16:11:31Z")

</div>

Your are most welcome - sorry for any confusion - our guys will have a response for you very soon

---

<div class="post-metadata">

**Author:** ![paulcutsinger](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@paulcutsinger](https://forums.developer.nvidia.com/u/paulcutsinger)\
**Post date:** [June 28, 2023, 4:12pm UTC](https://forums.developer.nvidia.com/t/extension-for-chatgpt/258177/4 "2023-06-28T16:12:23Z")

</div>

Hi, while we will not be presenting today, there is a GitHub project that demonstrates how to implement the ChatGPT + Omniverse integration. You can find it here: [GitHub - NVIDIA-Omniverse/kit-extension-sample-airoomgenerator: A tool used to create 3D content for rooms by calling OpenAI's API](https://github.com/NVIDIA-Omniverse/kit-extension-sample-airoomgenerator). As per the question on fine-tuning the model, while you can’t fine-tune GPT-4, you can fine tune other LLMs and then connect your fine-tuned model into Omniverse in a similar way we did in our Github project.

---

<div class="post-metadata">

**Author:** ![nadeemm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nadeemm/32/367020_2.png) [@nadeemm](https://forums.developer.nvidia.com/u/nadeemm)\
**Post date:** [July 12, 2023, 4:12pm UTC](https://forums.developer.nvidia.com/t/extension-for-chatgpt/258177/5 "2023-07-12T16:12:25Z")

</div>

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.