# NVIDIA NIM

## Prerequisitos

1. Inicia sesión o regístrate en [Nvdia](https://build.nvidia.com/).
2. Desde la barra de navegación superior, haz clic en NIM:

<figure><img src="/files/NpstkbQeHlMzqw3kwwFs" alt=""><figcaption></figcaption></figure>

3. Busca el modelo que te gustaría usar. Para descargarlo localmente, usaremos Docker:

<figure><img src="/files/t3kPFJPY8vh9CTHAkdHo" alt=""><figcaption></figcaption></figure>

4. Sigue las instrucciones de la configuración de Docker. Primero debes obtener una API Key para descargar la imagen de Docker:

<figure><img src="/files/y2x5l9E915EpuWi40e0e" alt="" width="563"><figcaption></figcaption></figure>

## Flowise

1. **Chat Models** > arrastra el nodo **Chat NvdiaNIM**

<figure><img src="/files/L4sbhUZo4RrOStXv3iE3" alt=""><figcaption></figcaption></figure>

2. Si estás usando un endpoint alojado en Nvdia, debes tener tu API key. **Connect Credential** > haz clic en **Create New**. Sin embargo, si estás usando una configuración local, esto es opcional.

<div align="left"><figure><img src="/files/eNjDLwFiSiNKle9N4gQ2" alt=""><figcaption></figcaption></figure> <figure><img src="/files/bmt8NjLW1nXtSdzoCdZy" alt=""><figcaption></figcaption></figure></div>

3. Ingresa el nombre del modelo y ¡voilà [🎉](https://emojipedia.org/party-popper/), tu **nodo Nvdia NIM** está listo para ser usado en Flowise!

<figure><img src="/files/vHnLgT08Hx0aUViabGcS" alt=""><figcaption></figcaption></figure>

## Recursos

* [Nvida LLM Getting Started](https://docs.nvidia.com/nim/large-language-models/latest/getting-started.html)
* [Nvdia NIM](https://build.nvidia.com/microsoft/phi-3-mini-4k?snippet_tab=Docker)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/chat-models/nvidia-nim.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.