# Userprompt Node - Agent Studio

**URL:** <https://forums.developer.nvidia.com/t/userprompt-node-agent-studio/328376>\
**Category:** Jetson AGX Orin\
**Tags:** generative\_ai\
**Created:** [March 26, 2025, 11:12pm UTC](https://forums.developer.nvidia.com/t/userprompt-node-agent-studio/328376 "2025-03-26T23:12:16Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![bjoshi01](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@bjoshi01](https://forums.developer.nvidia.com/u/bjoshi01)\
**Post date:** [March 26, 2025, 11:12pm UTC](https://forums.developer.nvidia.com/t/userprompt-node-agent-studio/328376/1 "2025-03-26T23:12:16Z")

</div>

Hello NVIDIA,

As described in the Agent Studio AI labs page, how can I use the UserPrompt node to add files from the terminal for the model to interpret? This is the UserPrompt within the Agent Studio Node Editor.

 ![image](https://global.discourse-cdn.com/nvidia/original/4X/2/f/3/2f353ad9cac987036d3afe60d1c319764e113c68.png)

Thank you in advance!

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [March 31, 2025, 6:02am UTC](https://forums.developer.nvidia.com/t/userprompt-node-agent-studio/328376/3 "2025-03-31T06:02:21Z")

</div>

Hi,

You can find an example to use the plugin below:  
[https://github.com/dusty-nv/NanoLLM/blob/main/nano\_llm/agents/chat.py](https://github.com/dusty-nv/NanoLLM/blob/main/nano_llm/agents/chat.py)

Or this can be tested with _nano\_llm.chat_ directly:

> **[Installation — NanoLLM 24.7 documentation](https://dusty-nv.github.io/NanoLLM/install.html#running-models)**

```bash
$ git clone https://github.com/dusty-nv/NanoLLM
$ jetson-containers run -v ${PWD}/NanoLLM:/opt/NanoLLM $(autotag nano_llm)

```

```auto
$ python3 -m nano_llm.chat --model meta-llama/Llama-2-7b-chat-hf --api=mlc --quantization q4f16_ft
...
05:51:18 | INFO | using chat template 'llama-2' for model Llama-2-7b-chat-hf
05:51:18 | INFO | model 'Llama-2-7b-chat-hf', chat template 'llama-2' stop tokens: ['</s>'] -> [2]
>> PROMPT: 

```

Thanks.

---

<div class="post-metadata">

**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\
**Post date:** [April 22, 2025, 12:47pm UTC](https://forums.developer.nvidia.com/t/userprompt-node-agent-studio/328376/5 "2025-04-22T12:47:21Z")

</div>

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