Sold by: Isaacus
Deployed on AWS
A first-of-a-kind enrichment model, capable of transforming unstructured documents into rich, highly structured knowledge graphs.
Overview
Kanon 2 Enricher is the first enrichment and hierarchical graphitization model. It transforms unstructured documents of almost any length into rich, highly structured knowledge graphs with sub-second latency.
In all, Kanon 2 Enricher is capable of:
- Entity extraction, disambiguation, classification, and hierarchical linking: extracting references to key entities such as individuals, organizations, governments, locations, dates, citations, and more, and identifying which real-world entities they refer to, classifying them, and linking them to each other (for example, linking companies to their offices, subsidiaries, executives, and contact points; attributing quotations to source documents and authors; classifying citations by type and jurisdiction; etc.).
- Hierarchical segmentation: breaking documents up into their full hierarchical structure of divisions, articles, sections, clauses, and so on.
- Text annotation: tagging headings, tables of contents, signatures, junk, front and back matter, entity references, cross-references, citations, definitions, and other common textual elements.
Kanon 2 Enricher is different from generative models in that it natively outputs knowledge graphs rather than tokens. Consequently, Kanon 2 Enricher is architecturally incapable of producing the types of hallucinations suffered by general-purpose generative models.
Kanon 2 Enricher's native context window is 16,384 tokens; however, it supports documents of almost any length thanks to a novel context extension algorithm that chunks documents and intelligently stitches results back together to form a single enriched document.
On a g6e.xlarge instance, Kanon 2 Enricher can enrich up to 1 billion tokens per hour, equivalent to 250k average-sized documents.
Like all other Isaacus SageMaker model deployments, your Kanon 2 Enricher deployment will be fully air-gapped--no data will enter or leave your AWS account.
Conveniently, Isaacus SageMaker model deployments are also compatible with the standard Isaacus Python SDK via the Isaacus SageMaker Python integration (https://docs.isaacus.com/integrations/amazon-sagemaker ).
You can negotiate a discount to Kanon 2 Enricher by contacting us: https://isaacus.com/support .
Highlights
- Transforms unstructured documents into rich, highly structured knowledge graphs, performing entity extraction, hierarchical entity linking, entity and document classification, hierarchical document segmentation, and text annotation.
- Natively outputs knowledge graphs rather than tokens, making it architecturally incapable of producing the types of hallucinations suffered by general-purpose generative models.
- Throughput of one billion tokens per hour on a single g6e.xlarge, equivalent to 250k average-sized documents.
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
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.g6e.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.xlarge instance type, real-time mode | $11.99 |
ml.g5.2xlarge Inference (Batch) Recommended | Model inference on the ml.g5.2xlarge instance type, batch mode | $11.99 |
ml.g5.xlarge Inference (Batch) | Model inference on the ml.g5.xlarge instance type, batch mode | $11.99 |
ml.g6e.2xlarge Inference (Real-Time) | Model inference on the ml.g6e.2xlarge instance type, real-time mode | $11.99 |
ml.g6e.4xlarge Inference (Real-Time) | Model inference on the ml.g6e.4xlarge instance type, real-time mode | $11.99 |
ml.g6e.8xlarge Inference (Real-Time) | Model inference on the ml.g6e.8xlarge instance type, real-time mode | $11.99 |
ml.g6e.16xlarge Inference (Real-Time) | Model inference on the ml.g6e.16xlarge instance type, real-time mode | $11.99 |
ml.g6.xlarge Inference (Real-Time) | Model inference on the ml.g6.xlarge instance type, real-time mode | $11.99 |
ml.g6.2xlarge Inference (Real-Time) | Model inference on the ml.g6.2xlarge instance type, real-time mode | $11.99 |
ml.g6.4xlarge Inference (Real-Time) | Model inference on the ml.g6.4xlarge instance type, real-time mode | $11.99 |
Dimensions summary
You pay by the hour for each host running the model, billed per usage with no upfront commitment. Pricing splits into two inference modes. Batch mode runs on ml.g5.xlarge and ml.g5.2xlarge instances for processing groups of documents. Real-time mode runs on ml.g6 and ml.g6e instance families in sizes from xlarge up to 16xlarge. Within each family, larger instance sizes carry higher hourly rates and provide more compute. You choose the instance type and mode that fit your workload, and the hourly rate follows that choice.
Top-of-mind questions for buyers
One HostHrs unit is one hour that a single model host runs. Each running inference host accrues charges by the hour. You pay based on how long the endpoint stays active, multiplied by that instance type's hourly rate. Stopping the endpoint stops the hourly software charges.
Both meter running host-hours, but they run on different instances. Batch mode uses ml.g5.xlarge and ml.g5.2xlarge to process groups of documents together. Real-time mode uses ml.g6 and ml.g6e instances to serve requests as they arrive. You choose the mode that fits your workload timing.
Charges accrue per hour only while a host runs. A stopped endpoint stops the software charges. Because billing follows actual usage, subscribing to the model does not create an immediate charge on its own. Underlying AWS infrastructure fees may still apply separately depending on your setup.
isaacus.com
Helpful?
Vendor refund policy
To the maximum extent permitted by law, there are no refunds for consumption of this product.
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
Added support for g6 instances.
Additional details
Inputs
- Summary
For a user-friendly walkthrough of how to get started deploying Isaacus models on SageMaker, check out the Isaacus SageMaker quickstart guide on our docs.
This model runs on the fully air-gapped Isaacus SageMaker Model Server, which supports all the same functionality as the standard Isaacus API except that requests to the server must be proxied through the /invocations endpoint.
For example, if you wanted to send a POST request to /v1/enrichments with the data {"model": "kanon-2-enricher", "texts": ["Clause 5 - Confidentiality. Both parties agree to keep certain information ('Confidential Information') confidential."], "overflow_strategy": "auto"}, you would do so by sending /invocations the payload {"path": "/v1/enrichments", "method": "POST", "data": {"model": "kanon-2-enricher", "texts": ["Clause 5 - Confidentiality. Both parties agree to keep certain information ('Confidential Information') confidential."], "overflow_strategy": "auto"}}.
This means that minimal code changes are necessary to switch between the online Isaacus API and your own private Isaacus model deployments.
In fact, Python users can use the Isaacus SageMaker Python integration to automatically forward requests to the Isaacus API to SageMaker deployments using the standard Isaacus SDK.
Given that this is a private deployment and that authentication is managed by AWS, Isaacus API keys are not needed and are ignored.
As an enrichment model, Kanon 2 Enricher currently only supports the /v1/enrichments endpoint. For more information on the arguments accepted and returned by that endpoint, please consult our API reference documentation .
- Limitations for input type
- All the same limitations applicable to the Isaacus API except for the need for an API key.
- Input MIME type
- application/json
{
"path": "/v1/enrichments",
"method": "POST",
"data": {
"model": "kanon-2-enricher",
"texts": [
"Clause 5 - Confidentiality. Both parties agree to keep certain information ('Confidential Information') confidential."
],
"overflow_strategy": "auto"
}
}
{
"path": "/v1/enrichments",
"method": "POST",
"data": {
"model": "kanon-2-enricher",
"texts": [
"Clause 5 - Confidentiality. Both parties agree to keep certain information ('Confidential Information') confidential."
],
"overflow_strategy": "auto"
}
}
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
path | The path of the API endpoint being invoked (e.g., `/v1/enrichments`). | As an enrichment model, Kanon 2 Enricher currently only supports the `/v1/enrichments` endpoint. | No |
method | The HTTP method used for the invocation (e.g., `POST`). Defaults to `POST`. | One of `POST`. | No |
headers | The HTTP headers to include in the invocation request. Defaults to `null`/`None`, in which case no additional headers are sent. | Must be a mapping of strings to strings. | No |
data | The data to be sent as the body of the invocation request. This can be any serializable object. Defaults to `null`/`None`, in which case no body is sent. | - | No |
Resources
Vendor resources
Support
Vendor support
To get in touch with our support team, you can reach out via the support form on our website: https://isaacus.com/support . We endeavor to respond within 24 hours.
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
Best-in-class legal enrichment, reranking, and embedding models, optimized for legal knowledge graphs and legal RAG.
A state-of-the-art legal embedding model optimized for semantic search, RAG, and document classification, ranked first on the Massive Legal Embedding Benchmark.
A state-of-the-art reranking model optimized for legal RAG, research, and classification, ranked first on Legal RAG Bench and the Massive Legal Embedding Benchmark (MLEB).
State-of-the-art legal embedding and reranking models optimized for legal research, legal RAG, and legal document classification.
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.