Sold by: Voyage AI
Deployed on AWS
Free Trial
General-purpose reranker optimized for latency & quality with multilingual support. Context length: 8K for queries & docs (2K for queries).
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-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/
Highlights
- 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).
- Natively multilingual, beating Cohere multilingual v3 by 6.24% on 51 datasets across 31 languages.
- 8K token context length for queries and documents, with up to 2K token context length for queries; well-suited for applications on long documents. Latencies are 565 ms (1 GPU), 170 ms (4 GPUs), and 120 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. 160M tokens per hour at $0.02 per 1M tokens on an ml.g6.xlarge.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 7 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.12xlarge Inference (Batch) Recommended | Model inference on the ml.g5.12xlarge instance type, batch mode | $0.00 |
ml.g6.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6.xlarge instance type, real-time mode | $1.69005 |
ml.g6.12xlarge Inference (Real-Time) | Model inference on the ml.g6.12xlarge instance type, real-time mode | $5.752 |
ml.g6.24xlarge Inference (Real-Time) | Model inference on the ml.g6.24xlarge instance type, real-time mode | $8.344 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.xlarge instance type, real-time mode | $2.112 |
ml.g6.48xlarge Inference (Real-Time) | Model inference on the ml.g6.48xlarge instance type, real-time mode | $16.688 |
ml.g5.12xlarge Inference (Real-Time) | Model inference on the ml.g5.12xlarge instance type, real-time mode | $7.09 |
ml.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $20.36 |
ml.g5.24xlarge Inference (Real-Time) | Model inference on the ml.g5.24xlarge instance type, real-time mode | $10.18 |
Vendor refund policy
Refunds to be processed under the conditions specified in EULA. Please contact contact@voyageai.com for further assistance.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
We are excited to announce the initial release of rerank-2-lite.
Additional details
Inputs
- Summary
- query: str - The query as a string. Maximum of 2K 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 query and any document must not exceed 8K tokens. Total tokens ("query tokens × documents + sum of all document tokens") are capped at 320K × # GPUs. Supported instances—xlarge, 12xlarge/24xlarge, and 48xlarge—provide 1, 4, and 8 GPUs, respectively.
- Input MIME type
- text/csv, application/json, application/jsonlines
https://github.com/voyage-ai/voyageai-aws/blob/main/sample_reranker_input.json
https://github.com/voyage-ai/voyageai-aws/blob/main/sample_reranker_input.json
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
query | The query as a string. The query can contain a maximum of 2000 tokens. | Type: FreeText | Yes |
documents | The documents to be reranked as a list of strings.
- The number of documents cannot exceed 1000.
- The sum of the number of tokens in the query and the number of tokens in any single document cannot exceed 8000.
- The total number of tokens, defined as "the number of query tokens × the number of documents + sum of the number of tokens in all documents", cannot exceed 320K x # GPUs. The supported xlarge, 12xlarge/24xlarge, and 48xlarge instances come with 1, 4, and 8 GPUs each, respectively. | Type: FreeText | Yes |
top_k | The number of most relevant documents to return. If not specified, the reranking results of all documents will be returned. | Default value: None
Type: Integer | No |
truncation | Whether to truncate the input to satisfy the "context length limit" on the query and the documents. | Default value: True
Type: Categorical
Allowed values: True, False | No |
Resources
Vendor resources
Support
Vendor support
Please email us at contact@voyageai.com for inquiries and customer support. Join our Discord channel: https://discord.gg/zAU7GQEmvT
AWS infrastructure support
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.
Similar products
General-purpose reranker optimized for both latency and quality. Context length: 4K for queries & documents with up to 1K for queries.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.