Try NVIDIA NIM APIs

models

Reasoning Vision Visual Design Retrieval Speech Biology Simulation Climate & Weather Safety & Moderation

industries

Gaming Healthcare Industrial

Essentials for Retrieval Augmented Generation

The getting started kit to connect chat-based reasoning models with your proprietary enterprise data

retrieval augmented generation

GPU-accelerated generation of text embeddings used for question-answering retrieval.

RUN ANYWHERE

nvidia

nv-embedqa-mistral-7b-v2

embeddings

retrieval augmented generation

GPU-accelerated generation of text embeddings used for question-answering retrieval.

retrieval augmented generation

GPU-accelerated generation of text embeddings.

RUN ANYWHERE

nvidia

nv-rerankqa-mistral-4b-v3

ranking

retrieval augmented generation

GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.

The Best Reasoning Models

Talk to your enterprise data with the leading large language models

RUN ANYWHERE

meta

llama-3.1-70b-instruct

chat

language generation

Powers complex conversations with superior contextual understanding, reasoning and text generation.

RUN ANYWHERE

meta

llama-3.1-8b-instruct

chat

language generation

Advanced state-of-the-art model with language understanding, superior reasoning, and text generation.

RUN ANYWHERE

meta

llama-3.1-405b-instruct

synthetic data generation

chat

Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks.

RUN ANYWHERE

mistralai

mistral-7b-instruct-v0.3

chat

language generation

This LLM follows instructions, completes requests, and generates creative text.

Augment Your RAG Pipeline

Enhance your retrieval-augmented generation pipeline

Shutterstock Generative 3D service for 3D asset generation. Trained on NVIDIA Edify using Shutterstock’s licensed creative libraries

Getty Images’ API service for 4K image generation. Trained on NVIDIA Edify using Getty Images' commercially safe creative libraries.

A fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation

retrieval augmented generation

GPU-accelerated generation of text embeddings used for question-answering retrieval.

RUN ANYWHERE

nvidia

nv-embedqa-mistral-7b-v2

embeddings

retrieval augmented generation

GPU-accelerated generation of text embeddings used for question-answering retrieval.

retrieval augmented generation

GPU-accelerated generation of text embeddings.

RUN ANYWHERE

nvidia

nv-rerankqa-mistral-4b-v3

ranking

retrieval augmented generation

GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.

Shutterstock Generative 3D service for 3D asset generation. Trained on NVIDIA Edify using Shutterstock’s licensed creative libraries

Getty Images’ API service for 4K image generation. Trained on NVIDIA Edify using Getty Images' commercially safe creative libraries.

A fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation

RUN ANYWHERE

meta

llama-3.1-70b-instruct

chat

language generation

Powers complex conversations with superior contextual understanding, reasoning and text generation.

RUN ANYWHERE

meta

llama-3.1-8b-instruct

chat

language generation

Advanced state-of-the-art model with language understanding, superior reasoning, and text generation.

RUN ANYWHERE

meta

llama-3.1-405b-instruct

synthetic data generation

chat

Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks.

RUN ANYWHERE

mistralai

mistral-7b-instruct-v0.3

chat

language generation

This LLM follows instructions, completes requests, and generates creative text.