Select your cookie preferences

We use essential cookies and similar tools that are necessary to provide our site and services. We use performance cookies to collect anonymous statistics, so we can understand how customers use our site and make improvements. Essential cookies cannot be deactivated, but you can choose “Customize” or “Decline” to decline performance cookies.

If you agree, AWS and approved third parties will also use cookies to provide useful site features, remember your preferences, and display relevant content, including relevant advertising. To accept or decline all non-essential cookies, choose “Accept” or “Decline.” To make more detailed choices, choose “Customize.”

Sign in
Your Saved List Become a Channel Partner Sell in AWS Marketplace Amazon Web Services Home Help

Amazon Sagemaker

Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.

product logo

AI21 Contextual Answers Free trial

Top-performing Q&A tool that answers questions grounded solely in the context you define.
  • This product has been removed and is no longer available to new customers.

Product Overview

Contextual Answers is a task-specific model (TSM) by AI21 Labs that specializes in instant and grounded question answering and generating answers in natural language based on a corpus of documents, like an organizational knowledge base. By indicating when an answer is not available within the text, the model avoids hallucinations and inaccuracies and can be used to reliably power customer support chatbots, virtual assistants, and smart search tools. With no prompt engineering needed, this model is ready to be seamlessly integrated into existing systems.

Key Data

Type
Model Package
Fulfillment Methods
Amazon SageMaker

Highlights

  • No prompting needed – Simply input your question, and the model will instantly return an answer grounded in the context you’ve specified.

  • Avoid hallucinations, inaccuracies, and potential liability and compliance issues. The model's responses are grounded solely in the context you provide.

  • Accurately answer customer questions with responses grounded in your organization’s knowledge base. The provided context may contain up to 40,000 characters, and the question up to 160 characters.

Not quite sure what you’re looking for? AWS Marketplace can help you find the right solution for your use case. Contact us

Usage Information

Model input and output details

Input

Summary

See the API reference for full specifications.

Input MIME type
application/json
Sample input data
{
  "context": "RETURN POLICY\n\nIf you’re looking to return or exchange your order for whatever reason, we’re here to help! We offer free returns within 30 days of purchase. You can return your product for store credit, a different product, or a refund to the original payment method.\n\nPlease note the following exceptions to our return and refund policy:\n* Discounted items are final and cannot be returned or exchanged.\n* Returned items must have tags still on and be returned in original product packaging.\n* Returned items must have no visible signs of wear or use.\n\nTo initiate a return, please complete the following steps:\n1. Reply to your order confirmation email to request which products you would like to return.\n2. Print the prepaid return shipping label that you will receive by email.\n3. Send all items back to us using the label provided.",
  "question": "Can I return a pair of business shoes that I only got to wear once (with a barely noticeable crease)?"
}

Output

Summary

See the API reference for full specifications.

Output MIME type
application/json
Sample output data
{
  "id": "00000000-0000-0000-0000-000000000000",
  "answer": "No, the returned items must have no visible signs of wear or use.",
  "anwerInContext": true
}

End User License Agreement

By subscribing to this product you agree to terms and conditions outlined in the product End user License Agreement (EULA)

Support Information

AI21 Contextual Answers

Talk to our experts: support@ai21.com

AWS Infrastructure

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.

Learn More

Refund Policy

As a general rule, we do not offer refunds. If you feel that your specific case merits a refund, please contact us at support@ai21.com and provide all relevant details. Any decision by us to grant a refund shall be in our sole discretion.

Customer Reviews

There are currently no reviews for this product.
View all