rerank-2-lite Reranker
Purchase this listing from Webvar in AWS Marketplace using your AWS account. In AWS Marketplace, you can quickly launch pre-configured software with just a few clicks. AWS handles billing and payments, and charges on your AWS bill.About
Rerankers are neural networks that predict the relevancy scores between a query and documents and rank them based on the scores. They are used to refine search results in semantic search/retrieval systems and retrieval-augmented generation (RAG). rerank-2-lite is a cutting-edge reranker optimized for latency while still preserving strong quality, improving the accuracy atop OpenAI v3 large by an average of 11.86%—1.7x the improvement attained by the latest Cohere reranker (English v3). rerank-2-lite is also natively multilingual, beating Cohere multilingual v3 by 6.24% on 51 datasets across 31 languages. It supports a 8K-token combined context length for a query-document pair, with up to 2K tokens for the query. Latency is 565 ms for 25K tokens, and throughput is 160M tokens per hour at $0.02 per 1M tokens on an ml.g6.xlarge. Learn more about rerank-2-lite here: https://blog.voyageai.com/2024/09/30/rerank-2/
Related Products
show moreHow it works?
Search
Search 25000+ products and services vetted by AWS.
Request private offer
Our team will send you an offer link to view.
Purchase
Accept the offer in your AWS account, and start using the software.
Manage
All your transactions will be consolidated into one bill in AWS.
Create Your Marketplace with Webvar!
Launch your marketplace effortlessly with our solutions. Optimize sales processes and expand your reach with our platform.