Generate Embeddings for Text Retrieval

The best embedding models to connect chat-based LLMs with your proprietary enterprise data

nvidia / 
nv-embedqa-e5-v5PREVIEW

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

Embeddings
Retrieval Augmented Generation
nvidia / 
nv-embedqa-mistral-7b-v2PREVIEW

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

Embeddings
Retrieval Augmented Generation
nvidia / 
embed-qa-4PREVIEW

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

Embeddings
Retrieval Augmented Generation
nvidia / 
nv-embed-v1PREVIEW

Generates high-quality numerical embeddings from text inputs.

Embeddings
Retrieval Augmented Generation

Reranking Models

Identify the right chunks of data from your diverse business data to improve accuracy of responses

new york
PREVIEW
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.
new york
PREVIEW
nvidia
rerank-qa-mistral-4b
ranking
retrieval augmented generation
GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.