Build Your First RAG Pipeline
The getting started kit to connect chat-based reasoning models with your proprietary enterprise data
snowflake / arctic-embed-lpreview
GPU-accelerated generation of text embeddings.
Embeddings
Retrieval Augmented Generation
nvidia / embed-qa-4preview
GPU-accelerated generation of text embeddings used for question-answering retrieval.
Embeddings
Retrieval Augmented Generation
nvidia / rerank-qa-mistral-4bpreview
GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
Ranking
Retrieval Augmented Generation