Amazon Sagemaker
Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.
rerank-lite-1 Reranker Free trial
By:
Latest Version:
v1
General-purpose reranker optimized for both latency and quality. Context length: 4K for queries & documents with up to 1K for queries.
Product Overview
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-lite-1 is a reranker optimized for both latency and quality. Over a comprehensive evaluation encompassing 27 datasets across diverse topics—ranging from technical docs and code to law, finance, web reviews, long documents, medicine, and conversations—rerank-lite-1 consistently outperformed alternatives, such as bge-reranker-large and Cohere’s rerank-english-v2.0 on average by 14.43% and 9%, respectively. Moreover, rerank-lite-1 improves recall over only a first-stage search in almost all cases. Latency is 445 ms for 25K tokens, and throughput is 202M tokens per hour at $0.01 per 1M tokens on an ml.g6.xlarge. Learn more about rerank-lite-1 here: https://blog.voyageai.com/2024/03/15/boosting-your-search-and-rag-with-voyages-rerankers/
Key Data
Version
Type
Model Package
Highlights
Optimized for both latency and quality.
rerank-lite-1
emerges as the consistently superior reranker across all domains and first-stage search methods (e.g., BM25, OpenAI v3 large, voyage-large-2), outperforming alternatives, such as bge-reranker-large and Cohere’s rerank-english-v2.0 on average by 14.43% and 9%, respectively.4K token context length for queries and documents, with up to 1K token context length for queries; well-suited for applications on long documents. Latencies are 445 ms (1 GPU), 135 ms (4 GPUs), and 90 ms (8 GPUs) for 25K tokens. We recommend using multiple GPUs to reduce latency. The supported 12xlarge and 24xlarge instances come with 4 GPUs each, while the 48xlarge instances are equipped with 8 GPUs. 202M tokens per hour at $0.01 per 1M tokens on an ml.g6.xlarge
Not quite sure what you’re looking for? AWS Marketplace can help you find the right solution for your use case. Contact us
Pricing Information
Use this tool to estimate the software and infrastructure costs based your configuration choices. Your usage and costs might be different from this estimate. They will be reflected on your monthly AWS billing reports.
Contact us to request contract pricing for this product.
Estimating your costs
Choose your region and launch option to see the pricing details. Then, modify the estimated price by choosing different instance types.
Version
Region
Software Pricing
Model Realtime Inference$2.112/hr
running on ml.g5.xlarge
Model Batch Transform$0.00/hr
running on ml.m5.large
Infrastructure PricingWith Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
With Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
SageMaker Realtime Inference$1.408/host/hr
running on ml.g5.xlarge
SageMaker Batch Transform$0.115/host/hr
running on ml.m5.large
About Free trial
Try this product for 7 days. There will be no software charges, but AWS infrastructure charges still apply. Free Trials will automatically convert to a paid subscription upon expiration.
Model Realtime Inference
For model deployment as Real-time endpoint in Amazon SageMaker, the software is priced based on hourly pricing that can vary by instance type. Additional infrastructure cost, taxes or fees may apply.InstanceType | Realtime Inference/hr | |
---|---|---|
ml.g5.xlarge Vendor Recommended | $2.112 | |
ml.g5.8xlarge | $4.59 | |
ml.g5.2xlarge | $2.2725 | |
ml.g5.4xlarge | $3.045 | |
ml.g5.16xlarge | $7.68 |
Usage Information
Model input and output details
Input
Summary
query
:str
- The query as a string. Maximum of 1K tokens.documents
:List[str]
- The documents to be reranked as a list of strings. Maximum of 1K documents.top_k
:int
, optional (default=None
) - The number of most relevant documents to return. If not specified, the reranking results of all documents will be returned.truncation
:bool
, optional (default=True
) -True
: Truncates.False
: raises error if any given text exceeds the context length.
Limitations for input type
The sum of the number of tokens in the query and any single document cannot exceed 4K. The total number of tokens ("num of query tokens × num of documents + sum of the number of tokens in all documents") cannot exceed 300K.
Input MIME type
text/csv, application/json, application/jsonlinesSample input data
Output
Summary
results (List[RerankingResult]) - A list of RerankingResult, with format specified below, sorted by the descending order of relevance scores. The length of the list equals to top_k if this argument is specified, otherwise the number of the input documents. Each element contains attributes: index (int) - The index of the document in the input list. document (str) - The document as a string. relevance_score (float) - The relevance score of the document with respect to the query.
Output MIME type
application/json, text/csv, application/jsonlinesSample output data
Sample notebook
Additional Resources
End User License Agreement
By subscribing to this product you agree to terms and conditions outlined in the product End user License Agreement (EULA)
Support Information
rerank-lite-1 Reranker
Please email us at contact@voyageai.com for inquiries and customer support. Join our Discord channel: https://discord.gg/zAU7GQEmvT
AWS Infrastructure
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Learn MoreRefund Policy
Refunds to be processed under the conditions specified in EULA. Please contact contact@voyageai.com for further assistance.
Customer Reviews
There are currently no reviews for this product.
View allWrite a review
Share your thoughts about this product.
Write a customer review