Sold by: Jina AI
Deployed on AWS
New state-of-the-art neural text reranking model for 100+ languages
Overview
Jina Reranker v2 model is a neural text reranking model, designed to enhance the relevance of search results. It complements text embedding models and refines search results by prioritizing documents relevant to a query. This state-of-the-art reranker model enables a variety of applications that rely on precise search results across different languages, improved information retrieval, and high document throughput.
Use-cases: Vector search, retrieval augmented generation.
Highlights
- High multilingual performance across the board: This reranker model ranks at the top compared to its competitors, in terms of 'Mean Reciprocal Rank' (MRR), recall and NDCG, according to BEIR, MKQA and AirBench.
- Agentic RAG: This reranker model supports function-calling and text-to-SQL aware document reranking for agentic RAG.
- Ultra-fast: 15x more documents throughput than bge-reranker-v2-m3, and 6x more than jina-reranker-v1-base-en.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.
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
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.g4dn.xlarge Inference (Batch) Recommended | Model inference on the ml.g4dn.xlarge instance type, batch mode | $1.50 |
ml.g5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.xlarge instance type, real-time mode | $2.50 |
ml.p2.xlarge Inference (Batch) | Model inference on the ml.p2.xlarge instance type, batch mode | $2.30 |
ml.p3.8xlarge Inference (Batch) | Model inference on the ml.p3.8xlarge instance type, batch mode | $25.00 |
ml.g4dn.4xlarge Inference (Batch) | Model inference on the ml.g4dn.4xlarge instance type, batch mode | $4.00 |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $7.00 |
ml.g4dn.16xlarge Inference (Batch) | Model inference on the ml.g4dn.16xlarge instance type, batch mode | $14.50 |
ml.p2.8xlarge Inference (Batch) | Model inference on the ml.p2.8xlarge instance type, batch mode | $18.00 |
ml.g4dn.8xlarge Inference (Batch) | Model inference on the ml.g4dn.8xlarge instance type, batch mode | $7.60 |
ml.g4dn.12xlarge Inference (Batch) | Model inference on the ml.g4dn.12xlarge instance type, batch mode | $11.25 |
Dimensions summary
You pay by the host hour for running this reranking model on your chosen AWS instance. Pricing is organized two ways. First, by inference mode: batch mode processes documents in bulk, while real-time mode serves live requests. Second, by instance type across the g4dn, g5, p2, and p3 families. Each instance size carries its own hourly rate, so larger instances with more compute cost more per hour. Batch mode covers g4dn, p2, and p3 instances. Real-time mode adds g5 instances. You select the mode and instance that fit your workload.
Top-of-mind questions for buyers
One HostHrs unit is one hour that your chosen instance runs the model. Billing meters running time on the instance you select. Charges accrue while the instance is active. Stopped instances stop the software charge, though underlying AWS storage or infrastructure fees may still apply separately.
Both meter by host hour on the running instance. Batch mode processes documents in bulk, so you run instances for job duration then stop them. Real-time mode serves live requests, so instances stay running to handle traffic. Continuous real-time serving accrues more hours than short batch jobs.
There is no hard limit on documents per request. Inputs batch internally by token count for GPU use. This model handles 1,024 tokens per document, with automatic chunking for longer documents. The hourly instance rate does not change based on document count within a request.
jina.ai
Helpful?
Vendor refund policy
Refunds to be processed under the conditions specified in EULA.
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
Reranker v2 Multilingual
Additional details
Inputs
- Summary
The model accepts JSON inputs. Texts must be passed in the following format.
{ "data": { "documents": [{"text": "the dog is in my house"}, {"text": "he likes dog"}, {"text": "hello world"}], "query": "where is the dog", "top_n": 2 } }
- Input MIME type
- text/csv
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-reranking-inference-input.json
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-reranking-batch-input.csv
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
data | A unranked array of texts for reranking. | Type: FreeText | Yes |
documents | A unranked array of texts for reranking. | Type: FreeText | Yes |
data | The query used for reranking. | Type: FreeText | Yes |
query | The query used for reranking. | Type: FreeText | Yes |
data | Top n documents to rerank. | Default value: Same number of documents as input
Type: Integer | No |
top_n | Top n documents to rerank. | Default value: Same number of documents as input
Type: Integer | No |
Resources
Vendor resources
Support
Vendor support
We provide support for this model package through our enterprise support channel.
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
Jina ColBERT v2 Reranker model for Multilingual Documents
Text embedding model (base) for input of size up to 8192 tokens
Embedding model for cross-modal and multimodal retrieval for text and image data
New State-of-the-Art Multilingual Embeddings With Task LoRA
Text embedding model (small) for input of size up to 8192 tokens
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.