Sold by: Jina AI
Deployed on AWS
ColBERT reranking model for text documents
Overview
jina-colbert-reranker-v1-en is an open-source English ColBERT-based reranking model.
ColBERT (Contextualized Late Interaction over BERT) leverages the deep language understanding of BERT while introducing a novel interaction mechanism. This mechanism, known as late interaction, allows for efficient and precise retrieval by processing queries and documents separately until the final stages of the retrieval process.
Use-cases: Vector search, retrieval augmented generation.
Highlights
- Jina-colbert-reranker-v1-en's main advancement is its backbone, jina-bert-v2-base-en, which enables processing of significantly longer contexts (up to 8192 tokens) compared to the original ColBERT that uses bert-base-uncased. This capability is crucial for handling query and documents with extensive content, providing more detailed and contextual search results.
- Use-cases: Fine-grained vector search, retrieval augmented generation.
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 hour for each host running the model. Pricing splits into two modes: batch inference for offline document ranking and real-time inference for live requests. Within each mode, you choose from GPU instance types across the p2, p3, g4dn, and g5 families. Hourly cost scales with the instance you pick, since more capacity generally means a higher rate. Batch mode covers p2, p3, and g4dn instances. Real-time mode adds the g5 family. Pick the mode and instance size that match your workload, and billing accrues per host-hour used.
Top-of-mind questions for buyers
One host-hour is one running instance billed for each hour it stays active. Charges accrue while the model host runs, regardless of how many ranking requests you send. A stopped host does not accrue software charges, though underlying AWS storage or compute fees may still apply.
Both bill per host-hour. Batch mode runs the model to rank stored documents in scheduled jobs, so you run hosts only during processing. Real-time mode keeps a host running to answer live ranking requests as they arrive, so charges continue for the whole time the endpoint stays up.
No. You pay per host-hour, not per document or request. There is no hard limit on documents per query; the model batches inputs internally. Sending more documents may extend processing time, which can raise host-hours in batch jobs, but the per-hour rate stays fixed.
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
ColBERT reranking model
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-colbert-reranking-inference-input.json
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-colbert-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 | An array of texts for reranking. | Type: FreeText | Yes |
documents | An 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: Number of top-ranked documents to be returned
Type: Integer | No |
top_n | Top n documents to rerank. | Default value: Number of top-ranked documents to be returned
Type: Integer | No |
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
Text embedding model (base) for input of size up to 8192 tokens
Jina ColBERT v2 Reranker model for Multilingual Documents
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.