Sold by: Jina AI
Deployed on AWS
ColBERT multi-vector embedding model for multilingual text input of size up to 8192 tokens
Overview
jina-colbert-v2 is an open-source multilingual ColBERT-style embedding model supporting 8192 sequence length.
This model produces vectors of size 128 for tokens in input documents.
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.
This state-of-the-art AI embedding model enables many applications, such as document clustering, classification, content personalization, vector search, or retrieval augmented generation.
Highlights
- Trained from scratch with support for 89 major world languages.
- Matryoshka embeddings, which allow users to trade between efficiency and precision flexibly.
- Ability to process significantly longer contexts (up to 8192 tokens) compared to the original ColBERT. This capability is crucial for handling documents with extensive content, providing more detailed and contextual search results.
Details
Sold by
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.g5.xlarge Inference (Batch) Recommended | Model inference on the ml.g5.xlarge instance type, batch mode | $2.50 |
ml.g5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.xlarge instance type, real-time mode | $2.50 |
ml.g5.8xlarge Inference (Real-Time) | Model inference on the ml.g5.8xlarge instance type, real-time mode | $18.25 |
ml.g5.12xlarge Inference (Real-Time) | Model inference on the ml.g5.12xlarge instance type, real-time mode | $27.50 |
ml.g5.2xlarge Inference (Real-Time) | Model inference on the ml.g5.2xlarge instance type, real-time mode | $4.75 |
ml.g5.4xlarge Inference (Real-Time) | Model inference on the ml.g5.4xlarge instance type, real-time mode | $9.30 |
ml.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $90.00 |
ml.g5.16xlarge Inference (Real-Time) | Model inference on the ml.g5.16xlarge instance type, real-time mode | $35.00 |
ml.g5.24xlarge Inference (Real-Time) | Model inference on the ml.g5.24xlarge instance type, real-time mode | $52.00 |
Dimensions summary
You pay by the hour for each host running the model, with no upfront commitment. Pricing scales with the instance size you choose across the ml.g5 family, from ml.g5.xlarge up to ml.g5.48xlarge. Larger instances carry more compute and a matching hourly rate. You also pick an inference mode. Real-time mode runs across all instance sizes for live query workloads. Batch mode is available on the ml.g5.xlarge instance for processing groups of inputs. Total cost depends on which instance size and mode you select, and how many hours each host runs.
Top-of-mind questions for buyers
One host-hour is one running ml.g5 instance for one hour of model inference. Charges accrue only while a host runs. Stopped instances stop software metering, though underlying AWS storage fees may still apply. You pay by the hour with no upfront commitment.
Both meter by host-hour on the running instance. Real-time mode serves live queries and runs across all ml.g5 sizes. Batch mode processes groups of inputs together and is offered on the ml.g5.xlarge instance. You pick the mode that fits your workload, and cost follows the hours each host runs.
This listing bills through AWS by the host-hour. The vendor also offers the model on other cloud provider marketplaces and through its own hosted API, but those are separate purchases outside this AWS Marketplace listing. For deployment on additional platforms, contact the vendor.
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 multi-embeddings model V2 - 128 dimensions
Additional details
Inputs
- Summary
The model accepts JSON inputs. Texts must be passed in the following format.
{ "data": [ { "text": "How is the weather today?" }, { "text": "What is the weather like today?" } ], "parameters": { "input_type": "document" } }
- Input MIME type
- text/csv
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-colbert-inference-input.json
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-colbert-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 strings for the model to embed. | Type: FreeText | Yes |
text | An array of strings for the model to embed. | Type: FreeText | Yes |
parameters | Type of input to get embedding, should be either 'document' or 'query'. | Default value: document
Type: FreeText
Limitations: Should be either 'document' or 'query'. | No |
input_type | Type of input to get embedding, should be either 'document' or 'query'. | Default value: document
Type: FreeText
Limitations: Should be either 'document' or 'query'. | 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
ColBERT multi-vector embedding model for multilingual text input of size up to 8192 tokens
ColBERT multi-embedding model for text input of size up to 8192 tokens
Text embedding model (base) for input of size up to 8192 tokens
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.