> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# NVIDIA NIM Embeddings

> Generate embeddings using NVIDIA NIM inference microservices

## Overview

NVIDIA NIM provides optimized inference for embedding models with GPU acceleration.

## Quick Start

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import embedding

result = embedding(
    input="Hello world",
    model="nvidia_nim/NV-Embed-QA"
)
print(f"Dimensions: {len(result.embeddings[0])}")
```

## CLI Usage

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai embed "Hello world" --model nvidia_nim/NV-Embed-QA
```

## Setup

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
export NVIDIA_NIM_API_KEY="your-nvidia-api-key"
```

## Available Models

| Model                                | Dimensions |
| ------------------------------------ | ---------- |
| `nvidia_nim/NV-Embed-QA`             | 1024       |
| `nvidia_nim/nvidia/nv-embedqa-e5-v5` | 1024       |

## Related

* [Embedding Providers Overview](/docs/embeddings/index)