Marketplace For Buyers For Vendors For Partners

voyage-large-2 Embedding Model

General-purpose text embedding model designed for general semantic retrieval tasks. 16K context length.

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

Text embedding models are neural networks that transform texts into numerical vectors. They are a crucial building block for semantic search/retrieval systems and retrieval-augmented generation (RAG) and are responsible for the retrieval quality. voyage-large-2 is a cutting-edge embedding model designed for general semantic retrieval tasks, showing consistent enhancements across general-purpose corpora and outperforming alternatives including voyage-2, OpenAI v3 large (by 3.03%), and Cohere English v3 (by 4.93%). Latency is 90 ms for a single query with at most 100 tokens, and throughput is 12.6M tokens per hour at $0.22 per 1M tokens on an ml.g6.xlarge.

Related Products

Sedai for ECS: Autonomous Optimization & Remediation

Sedai for ECS is an autonomous cloud management platform powered by AI/ML delivering continuous optimization for cloud operations teams to reduce costs by 40%, improve performance by 35%, reduce FCIs by 50% and improve ops productivity 6x

AI based Intelligent Document Processing

Our product is an advanced artificial intelligence solution designed to streamline document processing workflows for businesses of all sizes. Leveraging cutting-edge machine learning algorithms, it automates the extraction, analysis, and interpretation of valuable information from a variety of documents, including invoices, contracts, forms, and more. With this powerful tool, businesses can significantly reduce manual effort, minimize errors, and accelerate decision-making processes.

Automated SAS to Pyspark Conversion

SAS workloads come with high costs, scalability challenges, and limited flexibility. Hexaware’s Amaze® accelerates SAS-to-PySpark migration using Gen AI and LLM-powered automation, ensuring a 70-80% conversion accuracy, 3x-5x faster execution, and up to 40% cost savings.

Vectra Cognito for Service Delivery Partners (Billed Monthly)

Vectra Threat Detection and Response for Partner Provided Consulting Engagements

Real-time & Historical Datafeeds | Global Post-War Contemporary Auctions

This dataset is prepared for statistical factor pricing models and standardized across variables including country, region, currency, vendor, artist for seamless data filtering. It contains 20+ years of all items in the Post-War & Contemporary art category sold on auction by Christie’s, Sotheby’s, Bonhams and Phillips from 2000 to date.

Philter

Philter deidentifies and redacts sensitive information, such as Personally Identifiable Information (PII) and Protected Health Information (PHI), in text.

Tuberculosis - Total number of cases in the US | CDC

Centers for Disease Control and Prevention provides free and open access to various health related data. This release contains total number of Tuberculosis cases reported in the United States, by region and by states, in accordance with the current method of displaying WONDER data. Data on United States will exclude counts from US territories. The data is available for past 2 years.

AWS Security Review

An AWS Security Review is an opportunity to ensure that your cloud infrastructure is optimized for performance, security, reliability, and cost-effectiveness. Our certified AWS architects will identify any potential issues or areas for improvement in your AWS environment and make recommendations to get your back on track.