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

AI Ready Data

Provided By: S&P Global Commodity Insights

AI Ready Data

Provided By: S&P Global Commodity Insights

The AI Ready Data dataset encompasses a comprehensive array of textual content across Commodity Insights publications produced by in-house editorial and research teams, including market reports, news articles, rationales, commentaries, fundamentals analyses, outlooks, and more - all in an LLM-friendly format prepared for seamless integration with AI systems.

Product offers

The following offers are available for this product. Choose an offer to view the pricing and access duration options for the offer. Select an offer and continue to subscribe. Your subscription begins on the date that your request is approved by the provider. Additional taxes or fees might apply.

Public offer

Payment schedule: Upfront payment | Offer auto-renewal: Not supported
$0 for 2 months

Overview

AI Ready Data packages for LNG, Crude, Clean Energy Technology, Americas Gas and Power, EMEA Gas and Power, APAC Gas and Power, and Fuels and Refining are now available!

 

The offer comprises a sample data set containing approximately 100 dated records

 

The AI Ready Data dataset encompasses a comprehensive array of textual content across Commodity Insights publications produced by in-house editorial and research teams, including market reports, news articles, rationales, commentaries, fundamentals analyses, outlooks, and more - all in an LLM-friendly format prepared for seamless integration with AI systems.

Customers can effortlessly leverage AI Ready Data for their Retrieval-Augmented Generation (RAG) solutions, enhancing their analytical capabilities and driving informed decision-making. This dataset removes restrictions as you integrate your choice of large language models (LLMs), to uncover patterns, correlations, and insights across commodities. Our flexibility aids processing and understanding data to suit your organizations, and you can utilize the provided data embeddings or set your own as per your preference. Additionally, you can integrate with your own vector database and leverage various internal and external data sources to enrich the dataset.

 

This dataset includes:

  • Unstructured data in an AI-ready format broken down into documents and segments with LLM-friendly metadata
  • Flexible data delivery
  • Easy customization of your own search and relevancy-boosting algorithms
  • Ease of discovery of relevant content for your end users

 

Sample Fields:

DOCUMENT_METADATA
PUBLISHED
UPDATED
FILETYPE
FILESIZE
SOURCEURl
REPORTINGFREQUENCY
PRIMARYENTITYTYPE
PRIMARYENTITYNAME
DOCUMENT_PRIMARY_ENTITY_IDF
OTHERDOCUMENTMETADATA

 

SEGMENT_METADATA
DOCUMENTID
SEGMENTATIONSTRATEGY
SEGMENTID
SEGMENTTYPE
SEGMENTLOCATION
RAWSEGMENTCONTENT
PROCESSEDSEGMENTCONTENT
LANGUAGE
SEGMENTOVERLAP
OTHERSEGMENTMETADATA
SEGMENTEMBEDDINGS
SEGMENTORDER

 

Tables :

TABLE TITLETABLE DESCRIPTION
DOCUMENT_METADATAContains metadata about various documents such as id, name, file type, size, sourceURL, and reportingFrequency. Additionally, it includes related tags like primary entity, commodity, geography, and any additional metadata that helps in identifying the document.
SEGMENT_METADATAContains chunked segments from documents along with metadata such as related document id, segment id, type, location, along with the processed and raw content of the segment. Additionally, it contains information on the segmentation strategy used to chunk the data and the embedding ids for each segment.
Fulfillment Method
AWS Data Exchange

Data sets (1)

You will receive access to the following data sets

Revision access rules
All historical revisions | All future revisions
Name
Type
Data dictionary
AWS Region
ai-ready-data-cet
Not included
US East (N. Virginia)

Usage information

You’ll need an Amazon Redshift RA3 cluster or serverless endpoint to query this data. You can setup, manage, and view your Amazon Redshift infrastructure in the Redshift console. Learn more about Amazon Redshift serverless and how to start querying third-party data in Amazon Redshift. Learn more 

By subscribing to this product, you agree that your use of this product is subject to the provider's offer terms including pricing information and Data Subscription Agreement . Your use of AWS services remains subject to the AWS Customer Agreement  or other agreement with AWS governing your use of such services.

Support information

Support contact email address
Refund policy
Refunds are not offered for this product.
General AWS Data Exchange support