SAP Community - Document Information Extraction

Introducing Document Information Extraction Premium Edition - Unleashing the Power of Large Language Models and Generative AI

2023-09-04T15:59:05+02:00

December Update - General Availability

The GA of Document Information Extraction, premium edition took place on December 6th. The new service plan is now available on all productive BTP landscapes of the Document Information Extraction service.

The BTP Service Description Guide reflects the new service and the metric under section 7.

Official commercial and technical information can be found in SAP Discovery Center and on SAP Help Portal.

November Update - Trial Availability

Document Information Extraction, premium edition was featured at TechEd 2023 as part of a virtual jump-start session. Get a glimpse of the new features and to get enabled in only 25 min: Jump-Start Your Document Processing Use Case with Generative AI.

Here you will find a dedicated step-by-step tutorials to kick start on SAP BTP Trial.

Foundation Models, a technological breakthrough in AI, have ushered in a new paradigm with disruptive capabilities. The rise of applications like ChatGPT, built on these foundational models, has rapidly caught the world's attention. Particularly in the context of intelligent document processing (IDP) it allows to extend the pre-defined capabilities with emerging capabilities that have been either unforeseen or very difficult to implement.

Today, we are thrilled to announce the launch of the new version of our product lineup for IDP: Document Information Extraction, premium edition. It is a groundbreaking addition to our software suite that is set to revolutionize the way businesses extract valuable insights from unstructured data. With the power of Large Language Models (LLMs) and Generative AI (GenAI), the premium edition will unlock a whole new level of capabilities, enabling organizations to streamline their operations and further increase their process-related efficiency. The premium features in the new edition encompass:

Auto Extraction of Unstructured Data
Gone are the days of laborious annotation and template creation. The premium edition will offer a schema-based extraction of unstructured data by leveraging the unprecedented capabilities of LLMs. With a simple description of required fields, the solution will automatically extract and organize data, eliminating the need for manual intervention and drastically reducing time-to-value.

Extended Language Support
In an increasingly interconnected world, language barriers should never hinder adoption. That's why we will introduce extended language support for over 40 languages. Businesses will be able to effortlessly extract information from documents written in different languages, enabling faster go-to-market strategies, and expanding global coverage of their IDP functions.

Extensions of SAP Standard Schemas (roadmap outlook 2024)
To cater to the diverse needs of our customers, the premium edition will extend the support for SAP Standard Schemas. This enhancement will allow for a seamless integration with SAP systems and their data models, providing quick extensibility and higher business value.

Immediate Improvement (roadmap outlook 2024)
The premium edition will also come with immediate improvements in accuracy based on feedback data from users. By harnessing the power of LLMs and GenAI, the solution will ensure better accuracy in data extraction, minimizing errors and maximizing the reliability of extracted information. This will lead to higher automation rates and hence, greater operational efficiency and productivity.

The benefits of Document Information Extraction, premium edition are far-reaching. By drastically reducing time-to-value, businesses will be able to quickly extract insights from unstructured data. With the global coverage and faster go-to-market strategies, companies can stay ahead of the competition. Additionally, the quick extensibility and higher business value provide a solid foundation for further growth and innovation.

To give you a sneak preview of the remarkable capabilities of our upcoming release, we have prepared a demo video:

This launch represents a significant stride forward in our commitment to providing relevant, reliable, responsible business AI that delivers real-world results. Let's embark on this adventure together! Feel free to connect with us.

Disclaimer:
The intellectual property belongs to SAP and the content is copyrighted. We kindly remind you that the roadmap-related statements are not a commitment and are subject to change.

Learn more

Read more about the news of Document Information Extraction on the help portal!

What is Document Information Extraction?

Document Information Extraction is one of the SAP AI Business Services on the SAP Business Technology Platform (SAP BTP). This ML-enabled service is available through the Cloud Platform Enterprise Agreement (CPEA) and also in the Pay-As-You-Go (PAYGO) model.

Tutorials & Learnings

See all available tutorials here!

OpenSAP course for SAP AI Business Services

Blog posts:

Simplify Business Document Processing with SAP AI Business Services

Free Tier Option for Document Information Extraction

Business document processing through standard SAP integration

SAP Community Page:

SAP AI Business Services

Document Information Extraction Templates with SAP Business One

2023-09-05T15:53:01+02:00

As a user of SAP Business One you can consume the capabilities of Document Information Extraction (which is part of the SAP AI Business Services Portfolio) for importing documents to SAP Business One.

In this blog I would like to provide summary of how to better use its potential in connection to the newly delivered functionality.

The basic functionality is described in the relevant SAP Note 3060961 (and related SAP Notes) and this blog.

The additional functionality coming in the release of SAP Business One FP 2305 include the following template management feature:

Using the Templates as part of the Document Information Extraction service. The details of the template feature are provided in this blog. The advantage of the using of the templates is to specify for repeating layouts a template which will improve the extraction results for the documents of this type.

As part of the Template feature there is a possibility to define also a constant value for a specific output field. Therefore, for example if you know that template shall over the layouts of particular vendor you can specify its name or Tax ID as a constant value and then you can make sure that the specific value is always there.

The template can help to work for additional languages. For example the documents in Hebrew can be processed with better recognition result.

For standard integration between SAP Business One and Document Information Extraction service there is used in the background the feature of “autoselect” of the template. It means the following:
1. If there is no template used for a specific Document Information Extraction service account there is always used the standard model.
2. If there is a template used then service tries to match the particular document to the base template. However, if there is not any match the standard model is used for the data extraction.

The standard integration solution supports the templates created for the standard SAP scheme – “SAP_Invoice_Schema”. The scheme includes all standard fields included in the Document Information Extraction service.

The processing with template is similar to the basic functionality:

Prerequisites:

The Document Information Extraction protocol is setup and activated

The Electronic Document Service is running with "ConnectorDOX-1 (DOX)" processing

Steps:

The document in pdf (or other supported format) is taken from the predefined location by the Electronic Documents Service.

The document is processed to the Document Information Extraction service considering the above mentioned “autoselect” option.

The result is generated in a form of a JSON file. The processed document JSON file would include the following elements:

The results is stored in ECM8 table in the SAP Business One database and then it can be processed by wizard - Electronic Documents Import Wizard (EDIW) for Document Information Extraction protocol.

The completion process in the Electronic Documents Import Wizard was enhanced in version SAP Business One 2305, see the related blog.

What’s next?

This is a short summary of available functionality in SAP Business One. It should help you to get the better results from the integration between SAP Business One and Document Information Extraction service.

Regardless of the industry it’s undeniable that with the help of AI, specifically the Document information Extraction, can help you overcome various challenges in the area of data recognition.

I would like to ask you to share your feedback or thoughts in a comment or ask questions in the Q&A tag area here:

SAP Business One Community

The additional related materials can help you as well:

The template feature with own schema can be used for the SAP Build Process Automation automations. Please see the related documentation in Open SAP microlearning.

Related documentation for the set-up of an account on the SAP Business Technology platform can be viewed at the following Web link.

Integration of ChatPDF with S4HANA - New era of OCR with Generative AI

2023-09-22T11:29:39+02:00

The SAP Community is literally flooding now with AI and Generative AI-related blogs.

Organizations started to adopt ChatGPT for several generative or automation tasks.

Content - Suggestions, Rectification, Generation

Code - Suggestions, Rectification, Generation

JSON~XML Conversions and API Integrations

Data analysis with ChatGPT

& more….

Why I started to write this blog today, is the Idea of Generative AI is getting changed, and the business is trying to explore the new capabilities of ChatGPT and ChatGPT-powered tools.

To perform the dynamic OCR extraction from PDF and Automate the Business Process, you definitely need the below tools:

ChatGPT

ChatPDF

SAP Build Automation

If we want to place all these things into one place, it will look like below -

Introduction

The Idea of AI-enabled OCR was to help the business extract the information using OCR and contextualize the extracted attributes to the Business means. This happens with Cognitive AI. Which is an AI/ML-based Business entity recognition model, which identifies the coordinates from the Business Document with the field name attributes.

Drawbacks –

It generates a new contextualization on its own, as it has a rigid way of JSON generation.

Also, the mapping to the context is very painful – as it takes lots of time to map an output JSON, and also if the production JSON is missing some parameters we as a human need to train the Business document template to get the required outcome.

Not vastly trained to give predictive dynamic columns

Can not be used for a document that does not have a template

Now, what happened in GenAI is contextualization to the Business entity is going to happen very smoothly and intelligently and is dynamically generated. This is a basic diagram to understand the idea behind this approach:

Benefit –

Purely dynamic generations of the item, address entity recognitions, and JSON conversion capabilities

Flexible and can be integrated with each type of required JSON format. Less time to train and deploy.

Any type of PDF can be extracted with proper contextualization to the LLM Models

Drawbacks –

Security of LLM Model prompts

Not rigid of static outputs. The LLM models generally produce dynamic outputs. Which can be stabilized up to a certain point, not as a whole can be done.

ChatGPT & ChatPDF setup -

Only we need the API keys here.

To retrieve the ChatGPT API key, go to the URL - https://platform.openai.com/account/api-keys

To retrieve the Chat-PDF API Key, go to the URL - Chat-PDF. Then go to your Account Button at the left bottom and expand the Developers section. Developer's guide is available here.

Chat-PDF Time.

🔀 Upload a PDF File from the left pane -

🔀 Let's ask Some Basic Questions now -

🔀 Now Ask a Question to generate JSON data for you from the PDF extraction -

Now, I will try to predict the questions running through your mind and answer them..

⏩ What I am getting in this Blog?

An automated Tool for Customer Purchase orders to Sales order creation.

If your GMAIL receives a Vendor Invoice / Customer PO, this automation tool can process the PDF attachment and extract information from it to POST an event in SAP S4 HANA and revert to the Vendor / Customer Email.

⏩ This type of solution is already present, Boss? Then Why again?

It is there... But we will use Generative AI now.

⏩ What is the Business Value you have?

⏩ What is new you are doing here?

⏩ What is the benefit?

⏩ Why we will adopt and invest in this?

The main reason is that it will reduce your effort in Vendor Invoice or Customer PO PDF Mapping.

It can also adapt to all of your PDF onboarding and dynamic JSON and Mapping Generations. Auto adaptations to your environments.

⏩ How is that possible, Boss?

OKAY... Here is how...

Step 1 - SAPBuilders Pick up SAP Build - Process Automation, similar to the Hammer🔨 of Thor⚡⚡

Create an Automation Flow...

The all-in-one platform by SAP which is having all niche capabilities and is the tool for automating your SAP and other Automation Processes.

Sample JSON script for HTTP GET will look like this -

const url = 'https://ngrok-propagate.cfapps.us10-001.hana.ondemand.com/check_unread_email';

const headers = { 

};

const options = {

  'method': 'GET',

  'url': url,

  'headers': headers,

  'responseType':'json', 

  'resolveBodyOnly':true   

};

return options;

Step 2 - NodeNinjas Pick up Node-RED, Similar to Shield of Captain America ⍟⍟

Install the below Plugins for Node-RED.

node-red-contrib-simple-chatgpt

node-red-node-email

/check_unread_email

a. Read the email from your inbox

b. Categorize the Email and check for Customer PO

c. Save the POST the attachment to ChatPDF

d. Respond back with the sender's Email ID and sourceID

/get_pdf_data

a. Create a Chat Query to extract the information from PDF.

b. Prompt Used - "Fill the below json, with values from the document. Also wrap json code output in <code></code>, without json beautifying - >"

c. Also pass the Json expected output structure in the Content.

d. Now extract the json with magical function -

var mystring = msg.payload.content.toString();

var fromvalue = mystring.split("<code>");

var tovalue = fromvalue[1].split("</code>");

msg.payload = tovalue[0];

return msg;

/delete_pdf_file

a. Delete the PDF file from ChatPDF

/dummy_sales_order

a. Map your S/4 HANA API intelligently

b. Trigger your S4 HANA Sales Order API.

c. Return the Sales Order number as a return parameter

/send_email

a. Set up the Context to ChatGPT.- "Create an email body without any variables and within 100 Words."

b. Prompt ChatGPT to create an Email Body. Clearly mention and set the expectations. It's your Personal assistant. It will work for you...

msg.payload = 'We have Created Sales Order number: ' 

            + so 

            + 'Starting with Hi Team, ' 

            + 'Ending with: ' + 'Regards, sabarnapass@gmail.com'

            + 'If delay happens from our side. We will inform you'

msg.topic = 'Your Reference Sales Order:' + so;

return msg;

Step 3 - SAPBTPDeployX Pick up Ngrok, NodeJS, BAS, CF-CLI, similar to the Infinity Gauntlet🫰 of IRON Man🦾🤖

Ngrok -

Install and fire Ngrok

ngrok http 1880

BAS + NodeJS = ngrok-propagate

a. Install npm libraries

{

  "name": "ngrok-propagate",

  "version": "1.0.0",

  "description": "",

  "main": "index.js",

  "scripts": {

    "test": "echo \"Error: no test specified\" && exit 1",

    "start": "node index.js"

  },

  "author": "",

  "license": "ISC",

  "dependencies": {

    "axios": "^1.5.0",

    "express": "^4.18.2"

  }

}

b. Create an express server using NodeJS

c. Do not forget your .yaml file.

Now 🥁🥁🥁🥁......

CF PUSH - a wonderful document by dj.adams

And SNAP.....

🫰

((I had a wonderful IRON MAN Snapping Picture here from Avengers End Game. Due to community restrictions, I had to remove it. 😔😔😔 You can go to this URL to see the image.))

Now your system somewhat looks like -

I understand it's not the exact same one, what you have thought.

But if you go through the blog till now, I am sure you have everything in your hand to integrate ChatPDF and ChatGPT to your S4 HANA Suite.

⏩ This solution is GOOD, but it has problems...

Yes, using ChatGPT presents a number of challenges that organizations and individuals are discovering:

Inconsistency in output of LLM- Data generated

Contextual tuning time

Security of sensitive data

⏩ What's Next? What I can learn more?

Keep your eye on SAP AI Business Services to see how they are re-imagining Business Automation.

Also, similar Generative AI-based tools are being developed by SAP, I guess. Keep an eye on the blog, Document Information Extraction Premium Edition by tomasz.janasz.

Yes, you can create custom application using pytesseract and ChatGPT to perform kinda similar type of work.

There is a chance that you get the Customer PO, Vendor Invoices in different language. You can try to integrate Document Translation Service as well if required.

I got a chance to speak about SAP AI Business Service in one of the SAP Community Kolkata - Event. Here is the full code base if you want to scroll through.

Conclusion -

As you can see, all these AI tools are kind of Avengers.

I still remember that day when a TensorFlow Deep Learning model was trying to Play Mario and was learning from its own play score.

Although, the barriers will be there to adopt something new. Critical-Thinkers, Designers will be coming up a plan with have to draw the line of Data Sensitive and Security Aspects.

Do you know What's there in SAM Altman's Bag pack? Have a peek here -

https://www.mobileappdaily.com/news/sam-altmans-nuclear-backpack-holds-the-code-to-save-the-world-from-ai

The Generative AIs of this generation have started to generate a new Generation of Business Processes.

The Time is Here, the Time is Now...

Streamlining Data Extraction from PDFs: The Power of Document Information Extraction (DoX) and SAP Build Process Automation

2023-09-27T13:20:26+02:00

Managing the extraction and organization of data from numerous PDF files can be a laborious task, particularly when dealing with a large volume of documents. This process is prone to errors, which can have far-reaching consequences.

In this blog post, we will explore the integration of SAP Build Process Automation (SPA) with Document Information Extraction, offering a solution for automating the handling of PDF documents.

For those unfamiliar with Document Information Extraction, let me provide a brief overview. Document Information Extraction (referred to as DOX) is a valuable service designed to handle documents containing structured content, such as headers and tables. This service proves particularly useful for extracting data from documents like invoices or payment records. By leveraging this service, users can effortlessly upload a PDF document and receive the extracted data in the form of a JSON object.

Let’s Get Started

Navigate to SAP Build Process Automation Lobby and create a new automation.

Click on the Create dropdown and select Document Template

Click on Create a New Template

Give a name to the template and select the relevant invoice template from your system.

Choose from the existing schema or create a new one. I’ll proceed with creating a new custom schema.

Give a relevant name to the schema and add the required Header and Line Item Fields

Click on next and proceed with annotating the uploaded document.

Proceed with the relevant field mapping and click on save to save the template.

Now let’s create an automation to pick up documents from our local system and give the extracted information as the output.

Drag and Drop Extract Data (Template) from the Automation toolbar, then double-click to open its settings and click on Add Document Template

Click on Choose a template from the current project and select the template we created earlier.

Now scroll down to input parameters of Extract Data (Template) and add the document path.

Save the automation and do a test run.

Possibilities

This configuration offers endless possibilities. You can seamlessly connect your automation to source files from your Outlook inbox or local file system, processing them in a continuous loop. Furthermore, you can harness the extracted JSON responses to automate tasks such as entering data into Excel or generating SAP S/4HANA invoices, unlocking a wide range of automation opportunities.

Conclusion

In conclusion, the integration of SAP Build Process Automation (SPA) with Document Information Extraction (DOX) provides an effective solution for automating the extraction and organization of data from PDF documents, especially when dealing with a large volume of files. This integration streamlines a laborious and error-prone process.

AI in SAP BTP: Q3 2023 Highlights – SAP AI Business Services, SAP AI Core and SAP AI Launchpad

2023-10-02T09:27:58+02:00

Dear SAP Community,

As stated by SAP CTO’s Juergen Mueller, SAP Business Technology Platform acts as the enabler for SAP and partner applications to leverage AI capabilities, including generative AI, in an SAP context.

With SAP Business AI, your company can benefit from relevant, reliable, and responsible built-in AI for your core business processes.

SAP Business AI also enables companies to infuse AI capabilities available on SAP Business Technology Platform (SAP BTP) into their apps with scalability and responsibility in mind, so they can run business faster and smarter:

Build AI into your SAP applications with a library of pre-trained models using SAP AI Business Services

Deploy and run AI models at scale without compromising data privacy using SAP AI Core

Manage the AI model lifecycle in one central place using SAP AI Launchpad

Ready to ride the AI wave with us?

This quarter, our team introduced new product innovations for the AI portfolio of SAP Business Technology Platform, helping your IT teams to make your business applications and processes more intelligent.

Navigate to the corresponding sections by clicking on the product name.

SAP AI Core

Data Attribute Recommendation, part of SAP AI Business Services

Document Information Extraction, part of SAP AI Business Services

Personalized Recommendation, part of SAP AI Business Services

SAP AI Core 📲

Confidently deploy and integrate AI models designed for SAP applications, cost-efficiently at scale while preserving privacy and compliance.

Visual Studio Code extension for AI-driven development with SAP solutions

Streamline your AI development process by connecting your SAP AI Core instance directly with VS Code, eliminating the need for multiple tools. You can leverage your existing Docker, Git, and object storage setups for training data and trained models, speeding up your work by directly leveraging your content.

Main benefits include:

Connect to your instance of SAP AI Core directly from Visual Studio Code (VS Code)

Register your docker registry, synchronize your AI content from your Git repository, and register your object store for training data and trained models

Manage your AI scenarios by:
- Creating and registering artifacts in SAP AI Core from your object store connector
- Creating configurations and running and managing executions as well as deployments

Try now

New SAP AI Core Learning Journey

Designed for intermediate users, this brand-new SAP AI Core learning journey is now available on SAP Learning for free. In just 4 hours, learn step-by-step how to:

Embed AI into SAP solutions

Configure SAP AI Core and SAP AI Launchpad on SAP BTP

Train an AI model

Serve an AI model

Get started

Explore SAP AI Core and SAP AI Launchpad product roadmaps

Data Attribute Recommendation 📲

Perform classification and regression tasks.

*All the new product features listed below for Data Attribute Recommendation are limited to the usage of the AI API and can’t be used with the Data Attribute Recommendation API.

Enablement of transfer learning*

We introduced a new model lifecycle where it is no longer necessary to upload the whole dataset for model retraining. It enables users to upload only a delta dataset to the service to decrease the training time to update an existing trained model.
This feature helps to:

Increase usability by only uploading new training data for model retraining

Decrease training time

Explainable AI: Exposing feature contribution after model training*

Get feedback on how features contribute to a model, such as not increasing the model performance and indicating how well individual features correlate to defined labels of a model.
This feature helps to:

Expose feature contribution after model training gives insights on trained features

Enable transparency featuring a high and low correlation for specific labels

Decrease debugging time after training a model as the feature contribution for more insights

Updated batch file upload for inference*

Users can now expand the current maximum batch file upload size of 50 for an inference call, and send more inference requests in a single call.
This feature helps to:

Increase inference batch file upload size

Decrease the need to split inference calls into multiple batch files

Explore the product roadmap

Document Information Extraction (SAP AI Business Services) 📲

Automate and scale your business document processing for a wide range of document types using machine learning.

Availability of API end points for creating schemas

Users can now connect directly to the corresponding dedicated API end points for schema creation and create schemas from custom applications.

Schema versioning – edit, update, and create new schemas using an existing schema name

Users can now able to create a new schema under an existing schema name, edit and update an existing schema through versioning, leverage an optional parameter as a version in all schema API calls and add version parameters when specifying a template.
This feature helps to:

Obtain a better overview of what you are doing, by eliminating the need to create multiple copies of the same schema

Use the latest version of the schema to process documents, which is possible through one schema with multiple versions.

Improved SAP managed global model for processing supplier invoices

The machine learning model for the extraction of invoice documents has been improved and yields better extraction accuracies for many fields.
In addition to the better handling of new layouts, the processing of the following fields has been optimized:

Better cleansing of bank account numbers simplifies and improves the business partner matching in downstream applications or when using the enrichment feature in Document Information Extraction

Better processing of amounts with non-standard formats

Better parsing of dates, in particular numerical dates with whitespaces

Improved SAP managed global model for processing payment advice notes

A new machine learning model for the extraction of payment advice notes has been rolled out providing a higher accuracy for all fields on a variety of layouts.

The results are more consistent within tables and across pages of multi-page documents, especially for amount fields. Smaller fixes for tax IDs and bank account numbers improve the business partner matching in downstream applications or when using the enrichment feature in Document Information Extraction.

New schema property to define user friendly names for your schema fields

Users can select the "label" property in Schema API payload to set the property for the fields.
If the label is available for your schema fields, it will be used for displaying extraction results in the Document UI.

Embedded support in the UI

Users can submit "Service Now" tickets directly through the Document Information Extraction UI.
They have to submit a short description of the ticket and have the UI code automatically collect the information required for the ticket.

Explore the product roadmap

Personalized Recommendation 📲

Get accurate recommendations based on users’ browsing history and/or item description using machine learning.

Complementary recommendations for end users

We introduced a new API endpoint allowing administrators to provide additional options to their end users based on items often selected together to:

Improve retention and engagement with end users and meet KPIs more quickly

Recommend extra items on top of other items already recommended, through the upselling channel

Watch this video to learn more 👇

Support for consideration of the types of user interactions in boosting items

This new feature enables administrators to define a weight for interaction events during recommendation inferences, take the end-user's reactions to browsed items into account, and then change the prioritization of specific items in the recommendation results.

Be able to manage recommendations at a finer level of granularity

Tailor items being pushed to end users to better fit the business strategy

Explore the product roadmap

Stay tuned for AI at SAP TechEd – November 2-3, 2023

As every year, SAP TechEd brings together developers, practitioners, enterprise architects, and global IT leaders.

Joined by SAP experts and partners, they'll unite to explore the latest innovations in AI, app development tools, clean core for cloud ERP – and much more.

Register now for the in-person event in Bangalore, India, or the interactive virtual event not to miss anything about latest SAP Business AI innovations.

Dive into the session catalog and build your own agenda, with topics like the upcoming Document Information Extraction Premium Edition, the generative AI assistant Joule and more.

In the meantime, follow our AI tags on SAP Community and start interacting with your peers today.
👩🏻‍💻👨🏼‍💻

Artificial Intelligence / Machine Learning

SAP AI Core

SAP AI Launchpad

SAP AI Business Services

Document Information Extraction (SAP AI Business Services)

Data Attribute Recommendation (SAP AI Business Services)

Personalized Recommendation (SAP AI Business Services)

Build Relevant, Reliable and Responsible AI for Business at SAP TechEd 2023

2023-10-06T09:00:00.019000+02:00

Remember how the internet literally changed everything in the early ‘90s? I still remember the unmistakable chirp of my first modem slowly connecting to some great unknown – the worldwide web! I’d wait patiently for the famous voice of AOL to tell me, “You’ve got mail!”

Believe it or not, artificial intelligence is disrupting industries in the same way today – quite literally revolutionizing the way we interact and do business.

What do both have in common? People.

Whether you’re a developer or not, AI has democratized access to information at a large scale.

It is reshaping a world where enterprise systems discover unexpected opportunities to improve business process efficiency while reducing carbon footprints, where we can focus on our biggest challenges without wasting time on tedious and repetitive tasks.

With SAP Business AI, we have already entered this exciting future thanks to our deep business process knowledge. Built on 50 years of experience generating 87% of the world’s commerce, SAP delivers a unique focus on integration, data quality and trust that our customers have come to expect.

The fact is: more than 26,000 customers of cloud solutions from SAP now use SAP Business AI across multiple scenarios and partner solutions.

At SAP TechEd this November, we’re thrilled to reconnect and get you up to speed with SAP Business AI with insights from SAP experts, customers and partners.

You can join us:

in-person at SAP TechEd Bangalore, to connect directly with SAP experts, industry influencers, and our vast developer and IT practitioner community or,
online at SAP TechEd Virtual, our interactive event including live and on-demand educational sessions as well as an engaging Q&A.

At both events, our dedicated AI track will be divided into two sub-tracks, offering sessions in lecture or interactive formats such as keynotes or jump-start sessions, to deliver the learning experience that works best for you.

Within these sub-tracks, you’ll learn how SAP delivers Business AI that is relevant and responsible, taking enterprise software into the generative AI age and supporting our customers along their own AI transformation journey.

Subtrack #1: AI Built for Business
What is in it for you?

Unlock valuable insights and make agile business decisions with AI built into your SAP applications.
Learn how to responsibly accelerate development with AI models pretrained on business-relevant data.
Discover ways to deploy and run AI models at scale and manage the entire AI lifecycle in one central place.

Subtrack #2: Generative AI and Large Language Models
What is in it for you?

Discover how to responsibly combine the power of generative AI with the context of your business data for tailored business results in your SAP applications.
Explore how you can develop and extend applications using generative AI.
Learn about SAP's generative AI strategy and how this powerful technology can help you remain agile.

After just two days at TechEd, you'll leave with the skills, solutions, and confidence you need to stay relevant and ahead of the curve in the fast-paced AI environment.

Join us in Bangalore or online at the AI track! We can’t wait to learn, share, and grow with all of you. Your AI ideas get real at SAP TechEd.

Register now

See you in November!

In the meantime, visit our AI/ML topic page on the SAP Community for additional learning resources and join our new community group to interact with AI enthusiasts.

Capturing Data for Your Sustainability Report with SAP Build

2023-10-09T17:00:22+02:00

Sustainability has become an inescapable priority while sustainability reporting is a requirement in many jurisdictions and sectors. Governments, consumers, investors, and even competitors are demanding greater transparency and accountability in environmental, social, and governance (ESG) practices.

As organizations grapple with this paradigm shift towards sustainability, they must navigate a complex terrain of regulations, metrics, and data collection methods to accurately measure and communicate their sustainability efforts. Fortunately, SAP Sustainability Solutions are here to help and there's a powerful ally in this journey: SAP Business Technology Platform (SAP BTP).

In this blog post, we'll delve into how SAP Build can empower your organization to not only meet regulatory obligations but also thrive in capturing, managing, and leveraging sustainability data for your organization's sustainability report.

Imagine this real-world scenario where a company needs to prepare their sustainability report, including metrics of the energy consumption, renewable energy utilization, water consumption... To accomplish this task, they must extract data from two distinct invoice types - Energy Invoices (e.g., Iberdrola) and Water Invoices (e.g., Acciona & Aigües de Sagunt):

With today's technology, it simply doesn't make sense to have people spending countless hours manually sifting through documents and data to gather the information needed. The traditional approach to data collection not only consumes valuable time and resources but also introduces the risk of errors and inconsistencies.

This is where SAP Build steps in, with its robust capabilities for process automation and data extraction, SAP Build can transform the way you handle data collection tasks. SAP Build can transform your data collection process, rendering manual efforts obsolete. This means your employees can shift their focus to higher-value activities from the tedious and error-prone aspects of the process.

Watch the video to see how SAP Build can automate the data collection requirements:

With SAP Build & SAP BTP, you're not just keeping up with the demands of sustainability reporting; you're setting the pace. Imagine a future where sustainability data collection is not a burdensome task but an automatic, intelligent process. Thanks to the embedded AI services within SAP BTP, this future is within your grasp. Hyperautomation is no longer a buzzword; it's your reality.

If you have any questions, doubts, or concerns, don’t hesitate to post them in the comments or reach out to the community. We’re always here to help you make the most of SAP BTP!

Sales Order Creation using DOX and SAP Build Process Automation

2023-10-26T21:14:30+02:00

Are you interested in automating the creation of sales orders by extracting data from PDFs?

In this blog, we will explain how we used SAP proprietary OCR DOX and SAP Build Process Automation to create a sales order from an incoming purchase order PDF in a step-by-step process

We will go through following steps.

Create an Automation to get the data using Document Information Extraction and trigger the process.

Create a Process for following.

1. Approval form
2. Decision --- to fetch sales org data from vendor name.
3. Automation to create sales order.
4. Sends mail.

1.Create an Automation to get the data using Document Information Extraction and trigger the process.

Refer this blog post to know how to trigger process

When the Bot starts running, it checks the mail having particular subject in Microsoft outlook. Once it finds the mail saves all the attachments from that mail into the local file path.

Now, it goes to each attachment it downloaded from mail and checks the file is PDF. If it not PDF moves to another file.

For pdf file using Document Information Extraction will extract the required fields from the pdf and pass this fields as an input to the process and it triggers the process.

2.Create a Process for Sales order creation.

Once the process triggered.

If overall confidence extraction is more than 75 %, then it sends approval form to superior by providing extracted data in the form.

Superior will check the information provided in the form, if it was rejected then it sends mail to the customer and ends the process, if it was approved then it moves to the next step.

We Create a Decision to check Sender name is as same as purchase order PDF then we give appropriate values to (Sales Org, Division, Distribution channel)

Now we use Automation, which will create Sales order.

Drag and Drop Activity

- - Now in this Automation, first it will set SAP connection by providing (username, password, message server, client, language, System ID, instance).

- - In “GetInternalCustomer” Automation we will execute BAPi by passing import as sender Name, table with structure and as output it returns "Internal customer".

- - In “GetInternalCustomer - 2” Automation we will execute BAPi by passing import as ship To Name, table with structure and as output it returns "Internal customer".

- - Now will execute BAPI(BAPI_SALESORDER_CREATEFROMDAT2) by passing.

Import- (all the sales Area input fields)

Table - (as internalSenderName,internalShipToName,all internalMaterialnumber, quantity)

Returns - Sales Order number.

- - As an output we will get Sales order number from this Automation.

Sending Mail

Using the condition, we will check the sales order number which is coming from automation is valid or not. we send appropriate mail to the customer depending on sales order creation.

Conclusion:

I hope you found this blog post informative and helpful.With the power of Document Information Extraction(DOX), Build process Automation and decision intelligence, you can automate sales order creation. Please share your feedback, it would be helpful to learn and explore more.

SAP Build and Build Apps can help organizations automate processes that are currently manual, freeing up time and resources for other tasks.SAP Build Process Automation can help organizations automate tasks that are repetitive or time-consuming, freeing up employees to focus on more strategic work.By integrating SAP Build Process Automation with Generative AI, organizations can automate tasks that were previously impossible to automate, such as identifying and extracting data from documents or images.This can help organizations to improve efficiency, reduce costs, and better serve their customers.

Check this blog to get an idea how to use Generative AI in SAP Build Process Automation.

Thanks for taking your time & going through the blog.

– SAP Build Process Automation Topic Page : https://community.sap.com/topics/process-automation

Ask questions about SAP Build Process Automation: https://answers.sap.com/tags/696134d1-d791-44ba-9c1e-015db339e9a9

Read other SAP Build Process Automation blog posts: https://blogs.sap.com/tags/696134d1-d791-44ba-9c1e-015db339e9a9

Automated Supplier Invoice Upload using SAP Build Process Automation

2023-11-06T23:31:34+01:00

Introduction – Use Case

We are introducing a simpler and faster way to enhance business efficiency and agility with confidence using SAP Build Process Automation. The SAP Build Process Automation gives an opportunity to develop a solution to automatically fetch supplier invoices from five Microsoft 365 email accounts, push them to SAP Business ByDesign and scan for verification and validation. This solution helps to manage labor-intensive, error-prone manual processing of invoices from suppliers.

Challenge

Monitoring five email accounts and downloading a large number of attachments manually from emails and saving them on the computer as well as entering suppliers' invoices into SAP Business ByDesign one by one is a tedious task. The current process is wasting resources while keeping manual processes alive. Additionally, there is a high probability of committing mistakes, while performing repetitive tasks.

In this blog, we are describing a few important aspects that we learned while developing a solution to automate supplier invoice processing with SAP Build Process Automation and setting up a Desktop Agent to run the automation in unattended mode.

Solution

Solution Diagram

The following setup was crucial for this automation to work:

Enabling the invoice scanning in SAP ByDesign project scope

Enabling external authentication for accessing multiple Microsoft 365 email accounts

Creating a service Agent in SAP Business ByDesign

As a first step, we enabled integration with SAP Build Process Automation in the Business Configuration and Implementation Project questions.

We also enabled supplier invoices via PDF scanning. However, we didn’t select the automated invoice creation as we wanted the user to review scanned files before creating an invoice.

To use Microsoft 365 Cloud SDK in our automation and create external authentication for the Desktop Agent to access emails, we first configured an Azure application. In the Azure Active Directory, we created an application registration. We ensured the following:

Under Certificates & Secrets, we created a new client secret.

Under API Permissions, we added ‘Mail: Mail.ReadWrite’ as a delegated permission and application permission.

Under Authentication, we added the following URL as a redirect URI:https://login.microsoftonline.com/common/oauth2/nativeclient

Under App roles, we created a default app role with a value ‘Agent’.

Finally, we checked that in the admin section of My apps, in the email apps management, ‘Authenticated SMTP’ was selected.

We created new authentications separately for five email accounts in the Control Tower in SAP BPA using relevant IDs (Client ID, Client Secret, Tenant ID) when configuring the Azure application. The following scope was selected for all authentications: User Read, Offline Access, Open ID, Mail Read/ Write, Mail Send, Files Read/ Write.

Once created, we registered each external authentication on the Desktop Agent. Under Settings/ External Authentication, we entered email addresses of each identity to authenticate and verified the identities with a password.

To use these external authentications in the automation, we added authentication name for each email account in a configuration excel file and used authentication name as part of the input parameter in the 365 online authentication step of the automation.

We discovered that a business user is needed for pushing the PDF attachment to SAP Business ByDesign and kicking off the content recognition, triggered by an API call. As this automation is running in unattended mode, we wanted to create logins that do not expire. Therefore, we created a new Service Agent in the Business Partner Data Work Center in ByDesign and requested a user.

Once saved, we created a new security policy for the newly created business user. In this security policy we left the password validity field blank.

Also, we made sure to give the new business user the appropriate access rights.

Outcome

With the automated supplier invoice scanning process, we reduced the manual invoicing process and the risk of human errors associated with repetitive tasks.

Processing a ©Pokémon Card in 90 seconds with Document Information Extraction powered by generative AI

2023-11-17T16:12:36+01:00

Recently, my six-year-old son came to me with a challenge. As a product manager for a leading tech company, I often find myself lost in the world of business talk, and my son, like any other child whose dad is not a firefighter or a ninja, had no idea what I did for a living. He asked me to explain my work in a way that his kindergarten friends would understand.

"Alright, kiddo," I said, "Give me a challenge!"

With a cheeky grin he handed me his favourite Pokémon card - "PikachuV it is”, he announced. "I want you to tell me everything about this card - its name, hit points, thunderbolt attack, and the V-Rule."

I smiled back at him, "Challenge accepted!" and decided to raise the stakes. "I'll do it in under 90 seconds by using artificial intelligence" - to allow for keeping up to a six-year-old child’s attention span.

First, I explained what AI is and how it can resemble human characteristics such as seeing, understanding, painting or speaking. Then I told him that in my work I make computers see and read, and that they are so powerful to read even his trading cards. Bringing him on track took longer than 90 seconds but he flabbergasted me by saying "dad, it's like Zane from Ninjago" 🙂 (author: Zane is the amazing nindroid ninja).

So, with the powers of Generative AI and large language models (LLMs) now included into our Document Information Extraction, I set forth on this fun quest. So check this out:

This is the power of AI. Thanks to our latest GenAI-based advancements, you can now process basically any document type, even a Pokémon trading card. The ability to streamline document-based processes, enhance users’ productivity, and boost customer satisfaction is unparalleled. No data annotation, no template creation, no ML training required, whatsoever. The only thing is to describe what information you want to collect from the document and the service will pick it up for you.

During the whole exercise I came to the following learning for me: my son is smart to want to see the evidence on his own scenario. And this is exactly the same like our customers would want to experience it, too.

So, here's my question to you - are you ready to pitch it to your children or... board members? If so, here is how you can set up Document Information Extraction on BTP Trial in 40 seconds and try it out on your own 🙂

We've prepared some starter assets for you - enjoy:

Jump-start session at TechEd 2023 (25 min).

Tutorial: Use Trial to Extract Information from Custom Documents with Generative AI and Document Information Extraction.

Deep-dive blog: Introducing Document Information Extraction Premium Edition – Unleashing the Power of Large Language Models and Generative AI.

The future of Document Information Extraction is here, and it's more powerful, efficient, and innovative than ever before.

Learn more

Read more about the news of Document Information Extraction on the help portal!

What is Document Information Extraction?

Document Information Extraction is one of the SAP AI Services on the SAP Business Technology Platform (SAP BTP). This ML-enabled service is available through the Cloud Platform Enterprise Agreement (CPEA) and also in the Pay-As-You-Go (PAYGO) model.

Tutorials & Learnings

See all available tutorials here!

OpenSAP course for SAP AI Business Services

Blog posts:

Simplify Business Document Processing with SAP AI Business Services

Free Tier Option for Document Information Extraction

Business document processing through standard SAP integration

SAP Community Page:

SAP AI Business Services

SAP BTP Innobytes – December 2023

2023-12-14T20:31:53+01:00

SAP Business Technology Platform brings together application development, automation, data and analytics, integration, and AI capabilities into one unified environment optimized for SAP applications. Learn more: sap.com/btp

I feel like it was yesterday when we were releasing the first edition of 2023 and then I blinked and it’s already time for our SAP BTP Innobytes December video. Oh, how the innovations fly 😊

This month brings back some OG Innobyters, like thomas.hammer3, sharing new updates in the world of SAP HANA Cloud, new faces with brand new topics, like wolfgang.theilmann, who is announcing the new SAP Cloud Logging service and new faces, but familiar topics, with tomasz.janasz, talking about the new Document Information Extraction premium edition with GenAI capabilities.

Data & Analytics Innovations on SAP BTP

SAP HANA Cloud: fairness support with decision-making based on machine learning models

As we increase the usage of artificial intelligence in different business scenarios, we need to make sure our models and algorithms are as “fair” as possible. SAP BTP wants to provide this support out-of-the-box. With this innovation, we are taking big steps in that direction.

What’s it all about?

We have added fairness support for decision-making based on machine learning models to SAP HANA Cloud within SAP BTP. The new FairML function, now integrated into our Predictive Analysis Library, takes a proactive stance against biases commonly found in sensitive data attributes like gender, race, and age. FairML seamlessly pairs with the Hybrid Gradient Boosting Tree models for binary classification and regression.

How does this enhancement benefit you?

Data scientists and application developers gain the power to construct machine learning models that actively counter unfairness. Picture scenarios where AI decisions need to be fair and unbiased, like college admissions or job candidate selections. This feature steps in to ensure fairness across all groups.

There have been several discussions in the past year about ethical AI. This innovation aligns with crucial standards to prevent discrimination by AI against specific demographic groups.

If you want to find out more about how you can ensure ethical and responsible AI practice using the new capabilities in SAP HANA Cloud, check out the links below:

Fairness in Machine Learning – A New Feature in SAP HANA PAL

SAP HANA Cloud on sap.com

What’s New in SAP HANA Cloud – December 2023

Application Development Innovations on SAP BTP

General Availability of SAP Cloud Logging service

Calling all SAP BTP developers who want to monitor their application’s performance and detect bugs or deficiencies before their end users – this update is for you.

We are happy to announce the general availability of the SAP Cloud Logging service. This new service allows application developers and operators to analyze their BTP workloads and check performance, errors, usage, and other characteristics of their cloud applications.

Cloud Logging service provides a comprehensive observability solution expanding the scope of its predecessor, Application Logging.

Use the service to ingest, store, and analyze application logs, metrics, and traces. Ingest data from Cloud Foundry or Kyma runtimes and benefit from pre-built managed analytical dashboards.

Here are a few examples:

Do you want to learn more? Check out:

SAP Discovery Center: DevOps services

SAP Cloud Logging: documentation

BTP Developers Guide

Artificial Intelligence Innovations on SAP BTP

Document Information Extraction, premium edition

If you’ve made it this far, you deserve a special treat.

Navigating the world of document processing can often feel like a labyrinth, with the potential to inflate costs and increase manual work, with overall operational costs reaching up to 10 Euros per single document. Let’s imagine that we can process different types of documents across the enterprise without increased costs or more manual work. Delivery notes, order confirmations, certificates, returnable packaging – you name it.

If that puts a smile on your face, you’ll be delighted with the new Document Information Extraction, premium edition, powered with new generative AI capabilities!

What’s included?

Auto extraction of unstructured data from any kind of a document - simply describe the piece of information that you need, and watch the solution do the heavy lifting.

Multilingual support covering over 40 languages out of the box, catering to global businesses.

Extension of existing extraction routines, for example, for supplier invoices by adding additional data points to be extracted.

How can you learn more?

SAP Discovery Center: Document Information Extraction

SAP TechEd session + exercises

Tutorial

Reach out to our experts tomasz.janasz and tobias.weller

Share Your Thoughts 

That’s a wrap for 2023! We would love to hear what you think about the series. How do you like the video? Are there any SAP BTP topics that you’d like us to share more about? Leave your comments down below and we’re happy to connect with you.

Thank you for your support and happy viewing, sharing, and enjoying!

What's New with SAP BTP - Quarterly Live Series

2024-01-03T10:16:38+01:00

2023 was quite a year for SAP Business Technology Platform. We released innovations across our portfolio, from major product announcements like SAP Datasphere or SAP Build Code, to enhancements in our AI portfolio with new features for Data Attribute Recommendation and Document Information Extraction, to launching new capabilities like SAP Graph in SAP Integration Suite and SAP Cloud Logging. These are just some examples, as listing them all out would make this a book instead of a blog post 🙂

We realized that keeping up with all these innovations and understanding how they can benefit your development projects could be challenging. Which is why we started a quarterly series in July 2023 to connect you with our product experts and hear about the innovations directly from them. The format is quite simple:

Our product experts set the stage and share the recent innovation highlight
They show a demo or a practical implementation of the feature or innovation
You can submit your questions in the chat to get answers from our experts
Rinse and repeat every 3 months with new faces and new innovations

I am happy to confirm that will continue this series throughout 2024!

Watch the Replays

What's New with SAP BTP - Q12024 Innovation Highlights - April 25, 2024 at 4PM CET

Join this session to learn about some of the latest innovations delivered in Q1 2024 for SAP Business Technology Platform:

New vector engine in SAP HANA Cloud
Release of the generative AI hub in SAP AI Core
General availability of SAP Build Code.

The session also includes a slot for an open Q&A at the end of the presentations. Our experts are excited to interact with you, so bring your questions!

Meet our Experts

@shabana - Product Manager - SAP HANA Cloud Multi-Model

Shabana is part of the SAP HANA product management organization and responsible for SAP HANA Cloud. She's excited to share the details of the latest SAP HANA Cloud innovation - the new Vector Engine. Curious? Check out her blog post and join our session to get all the details!

Pierpaolo Vezzosi - AI Solution Management and Marketing

Pierpaolo is part of the AI Marketing team and has been product and solution manager of various artificial intelligence SAP offerings in the past 10 years. He'll be joining us to share the latest innovation in SAP AI Core - the new generative AI Hub. You can find more details in this blog post from Hadi. Join us live in April and see #GenAI in action.

@MarcHuber- Product Manager - SAP Build

Marc is ready to share why SAP Build Code is the right tool for application development on SAP BTP. Packed with #GenAI capabilities and many more intuitive features, developers can benefit from an improved experience when building their extensions. Some might call it a "game-changer". Read more here.

What's New with SAP BTP - Q42023 Innovation Highlights - January 25, 2024 at 4PM CET

For our first episode of 2024, we'll be diving into the release of the Edge Integration Cell for SAP Integration Suite, the Document Information Extraction premium edition (one of the SAP AI Business Services) and the SAP BTP Guidance Framework, or “your compass” for building and running apps on the platform.

Meet our Experts

@finny_babu (Lead Product Manager, SAP Integration Suite)

Finny drives Product experience initiatives to improve the end-to-end experience for customers & partners. Leading product strategy, design-led product definition, customer engagement initiatives and beta programs to ensure customer and business success.

@tomasz_janasz (Director, Product Management for AI)

Tomasz is a Director in the Product Management unit for AI at SAP. His focus lies on shaping the strategy and driving the adoption of Business AI across SAP portfolio and in enterprises. His background is in business administration. He holds a PhD in economics.

With Tomasz get ready to dive deep into the world of Generative AI, the game-changing titan in the AI arena! This revolutionary technology is redefining boundaries, particularly in the realm of Intelligent Document Processing (IDP), enabling us to explore new horizons that once seemed impossible to reach. We will decode the mysteries of how Generative AI can supercharge your business document processing, become your ultimate Pokémon detector, and connect the dots between all this and the Mount Everest.

@KonstantinHeine konstantin.heine (Product Manager, SAP BTP)

Konstantin Heine is a product manager for SAP Business Technology Platform within SAP’s Technology & Innovation board area. His focus is on methodologies and frameworks like SAP Integration Solution Advisory Methodology and SAP BTP Guidance Framework. Konstantin has over 13 years of experience in product management, integration architecture, and enterprise architecture.

Related Series and Events

For more SAP BTP content, check out:

SAP BTP Innobytes - bite-sized monthly video series, sharing the latest hits and top SAP BTP innovations: https://blogs.sap.com/2023/06/09/sap-btp-innobytes-do-you-have-3-minutes/
SAP BTP Garage - monthly LIVE webinar with hands-on use case walkthroughs and demos: https://webinars.sap.com/2021-12-31-sap-btp-customer-value-network-global/en/garage1
SAP BTP Talk - monthly podcast covering all things SAP BTP: https://podcast.opensap.info/cloud-platform/

AI Foundation on SAP BTP: Q4 2023 Release Highlights

2024-01-09T13:42:06+01:00

Dear SAP Community,

Did you get the chance to get your hands on the AI Foundation on SAP Business Technology Platform (SAP BTP) yet?

AI Foundation is SAP’s all-in-one AI toolkit, offering developers AI that’s ready-to-use, customizable, grounded in business data, and supported by leading generative AI foundation models. It is also the basis for AI capabilities that SAP embeds across its portfolio.

For more information about the different layers of the AI Foundation stack represented below, we suggest you reading this blog post.

In Q4 2023, our teams delivered a set of product innovations for the AI Foundation so you can build relevant, reliable and responsible AI-infused business applications and extensions with security, governance and trust in mind. Let's delve into the highlights!

AI Services – Document Information Extraction

General availability of Document Information Extraction, premium edition

We have supercharged our existing Document Information Extraction service with generative AI capabilities and launched Document Information Extraction, premium edition.

Users can now process documents intelligently across their entire business, with:

The automatic extraction of unstructured data by simply describing the required fields that you need, and watching the solution do the heavy lifting for nearly every document type.

The multilingual support for over 40 languages, catering to global businesses with diverse document types.

With no manual annotation and resource-intensive ML training required anymore, business document processing use cases can be onboarded in days, not weeks or months, reducing the time-to-value drastically.

To get started, read this blog post by our product manager and complete this tutorial.

AI Services – SAP Translation Hub

Consumption of the machine translation service using a user interface

Users can now use an intuitive user interface to consume the Document Translation service from SAP Translation Hub. This comes in addition to the existing API and makes it quick and easy for users to machine translate their documents and texts.

The service can be enabled using a booster, which allows users with an SAP Translation Hub license to configure the service without having to technically interact with SAP Business Technology Platform. Document Translation from SAP Translation Hub is already available on the multi-cloud Foundation for SAP BTP, and we are working to complete our migration of the remaining SAP Translation Hub functionalities from the Neo environment in early 2024.

Get started with this blog post and watch the video below.

Generative AI Management – Generative AI Hub

General availability of Generative AI Hub

You can now fast-track your generative AI development of SAP BTP apps with the new Generative AI Hub, giving you instant access to a broad range of large language models (LLMs) from different providers, such as GPT-4 by Azure OpenAI or OpenSource Falcon-40b.
With this access, you’ll be able to orchestrate multiple models, whether programmatically via SAP AI Core or via the playground within SAP AI Launchpad.

The generative AI hub provides tooling for prompt engineering, experimentation, and other capabilities to accelerate the development of BTP applications infused with generative AI, in a secure and trusted way. AI development teams can submit a prompt to multiple LLMs, compare the generated outcomes to identify the best-suited model for the task, and gain greater control and transparency with the built-in prompt history.

Read this blog post from our product manager to learn more or start the tutorial right away.

Business Data & Context – SAP HANA Cloud

New fairness support with decision-making based on ML models using the Predictive Analysis Library (PAL) for SAP HANA Cloud

We introduced a FairML function for PAL algorithms, to mitigate unfairness in machine learning model predictions related to affected groups identified by features such as gender, race, age, or other protected classes. This new FairML function supports hybrid gradient boosting tree (HGBT) binary classification and regression models.

It enables data scientists and application developers using SAP HANA Cloud to:

Build ML models that mitigate unfairness with respect to human sensitive data to decrease disparities, avoid harm, and ensure fairness in decision-making

Avoid unfairness to any group in AI-augmented decisions on humans such as college admission, job candidate selection, or personal credit evaluation

Comply with AI ethics to prevent discrimination by AI systems against specific demographic groups

This example shows how to build a FairML classifier model and how the model mitigates harm to affected age-groups indicated by balancing the false positive rage (FPR) of the model

If you want to find out more about how you can ensure ethical and responsible AI practice using the new capabilities in SAP HANA Cloud, check out the links below:

Technical Blog - Fairness in Machine Learning a new feature in SAP HANA PAL

SAP Blog - SAP HANA Cloud introduces fairness in machine learning

SAP Blog - What’s New in SAP HANA Cloud December 2023

New features in SAP HANA Cloud PAL 2023 Q4, Machine learning client 2.19

Build business-ready AI applications with SAP and stay updated!

▶︎ Get started with the AI Foundation on SAP Discovery Center, by comparing and selecting the service that fits most to your business needs.

▶︎ Explore the AI Foundation roadmap to discover our past and upcoming product innovations in 2024 and beyond.

▶︎ Engage with our community of SAP experts through blog posts and the SAP Answers platform.

▶︎ Don't miss this session on February 8 to get an overview of how AI is infused into SAP BTP, as well as the capabilities for developers, administrators, and users at your company.

See you next quarter!

Automate BPMN Diagrams and Note-taking in Cloud ALM with LLM

2024-01-10T23:10:46+01:00

AI Text Generation

Large Language Models (LLM) have gained great momentum in 2023, particularly in the Text generation field. In a few months, summarizing and translating large volumes of content with AI models became somewhat common - no matter your industry or size. They perform especially well when the task is straightforward, a clear example of the expected result is given, and the context does not need to be fully understood.

This blog post describes an experiment with a more obscure type of text content - Process diagrams. In essence, diagrams are indeed sentences put together in a drawing: "Step 1" (goes to) "Step2" (goes to/or to) "...". No context is really needed, besides the sequencing that needs to be followed. It is also easy to provide a model with the general BPMN specifications (XML elements everyone follows), and accurate examples (SAP provides BPMN files for every single S/4 business process in Signavio Process Explorer - free of charge).

On one hand, SAP quickly released AI Foundation, the all-in-one AI toolbox where you can freely choose a model and datacenter and start building your apps and services directly in SAP BTP. The obvious advantage is the integration with your SAP systems, as well as BTP itself. However, the product is still very new and this blog will use direct APIs instead, but you can technically leverage AI Foundation to achieve the same result.

On the other hand, SAP Cloud ALM is a project toolbox with numerous implementation capabilities: task management, transport execution, automated testing and.. process modeling. The latter is extremely useful during Fit workshops, where the business analyst can simply modify the relevant S/4 process diagram live, add requirements or notes, assign individuals, and more.

Now, let's say you don't use of Cloud ALM during the workshop, need to start a process from scratch or simply want to retroactively document your changes. Could LLMs build a process diagram for you? Or create a requirement in the tool directly from your handwritten piece of paper?

Disclaimer: These are almost thought experiments, not productive solutions or even prototypes.

Use Case 1 - From Text to Diagram

You are a business analyst documenting a process for your company. The objective is easy: explain how to order a pizza (no pineapple variant). First, you navigate to Cloud ALM, create a new requirement and describe the steps in the Description section:

Notice the ###CREATE BPMN###? That's because your company is AI-powered, and this command will generate a business diagram automatically for you.

The workflow is as follow:

Setup the Cloud ALM webhook. This will send a request whenever a task is created. See this post (and the others) from xavier.dupeyrat to learn more.

Create a requirement in SAP Cloud ALM with your AI trigger. The ###*### command is just an example. You could use any field from the requirement to act as filters instead.

Prompt the LLM. There are many ways to do so. For example, you can point the Tasks webhook to an integration in SAP CPI to do the heavy lifting: map the request body, add your prompt to the request, send it to the LLM API and reply back with its answer.
- First, choose your LLM provider. OpenAI and LLama are major contenders, but I like using Cohere because it's currently free for development, can access the web and is a genuinely good (Canadian 🍁) alternative. The API documentation to create a chat is here: Chat (Beta) (cohere.com).
- Wait for a task request matching your command, and map the id and description (e.g., regex looking for "Start, Check pizza price, Order pizza Quattro formaggi, Wait for delivery, Tip driver, Eat pizza 🍕."):
```
// GET /api/calm-tasks/v1/tasks/123

{

    "id": "123",

    "projectId": "456",

    "title": "Establishing the pizza process",

    "type": "CALMREQU",

    "status": "CIPREQUOPEN",

    "description": "Notes from 20240501 meeting.</p>\n<p>##CREATE BPMN##</p>\n<p>Start, Check pizza price, Order pizza Quattro formaggi, Wait for delivery, Tip driver, Eat pizza .",

    ...

}
```
- Send your prompt to the LLM (below is not the actual body):
```
// POST https://api.cohere.ai/v1/chat

{

    "message": "### Context\nYou are an expert at writing BPMN files with XML. I will give you a list of steps and you will return the BPMN to me. Here is an example with the steps ***(insert example step)*** and Withdraw ***(insert example step 2)***: ***(insert BPMN XML sample)***.\n\n###My Request\nReturn a BPMN for the following steps: ***(insert mapped description)***"

}
```
- Of course, the result of this query will greatly vary based on the provider, embeddings and the prompt itself. However, with minimal model optimization, the results were perfectly fine for our pizza process.

Take the returned XML code (= BPMN), and send it back to Cloud ALM. If you want to create a a process object, you would need to convert it into SVG first. In this example, we will simply generate a URL for the diagram and reference it in the requirement.

A free tool for BPMN hosting is Cawemo, the collaborative platform for modelling, versioning and sharing processes with anyone. Again, send a request with the BPMN to upload the process and generate a public link such as this one: Pizza process (cawemo.com).

Attach the link as a Reference to your initial Cloud ALM requirement through API:

// POST /api/calm-tasks/v1/tasks/123/references

{

  "name": "LLM - Pizza process BPMN",

  "url": "https://cawemo.com/share/7d764acf-99d0-4b6a-914e-45000a0977df"

}

You now have a BPMN diagram the Project team can access and share within minutes:

Use Case 2 - From Image to Requirement

Still here, I see? Let's change persona. You are now an old-school note-taker, paper and pencil, with a questionable hand-writing. This is the end of your day, after a quick meeting about what needs to be changed in the current S/4 solution, and you have a few requirements to enter in Cloud ALM.

Optical Recognition (OCR) solutions are not new, but you will mostly find SAP examples talking about Invoices. Why? Because it's very useful and you probably have a lot of them, which is a great use case for automation. However there are also plenty of consumer apps converting whatever you write on paper into digital documents, and that's the topic of our second example.

SAP AI Core is not the only SAP tool using LLMs. Another example is BTP's Document Information Extraction. With DCE, you can extract information from documents and scenes (e.g., a car plate number) at scale directly in SAP BTP, and send the result to other SAP products for further processing. According to SAP, the extraction relies on OCR and LLM, but it is not clear how things work in the background.

Our workflow goes as follow:

Setup your DCE instance (e.g., BTP Free Trial + booster).

Create a new schema configuration. It contains the fields you want to extract as structured data. The head is generally the top section of a document, while line items would belong to a a a table.

Take a picture of your paper notes and send them to the Document Information Extraction API: Document API | SAP Help Portal.

The document will be automatically analyzed. The quality of the results tend to increase over time but there is definitely room for experimentation. I tried my worse, and it came back okay.

Before proceeding with the requirement creation, you can first provide the result to another LLM, similarly to Use Case 1, by asking "###Instructions\nThis is a JSON view of my notes from today. Summarize the information and format your reply with bullet points.\n###JSON\n***(insert result)***".

Take the JSON output (also available as CSV), and create a new requirement in Cloud ALM through API.

// POST /api/calm-tasks/v1/tasks/

{

  "projectId": "456",

  "title": "Note-taking - Requirements from ABC",

  "type": "CALMST",

  "externalId": "789",

  "dueDate": "",

  "priorityId": 30,

  "assigneeId": "abc",

  "description": "***(insert result here)***"

}

And we are done! If you're looking for more, search for the tag "ai" here on SAP blogs, or check out the posts from mario.defelipe4 for RAG specifically!

SAP BTP Ask Me Anything Series: Artificial Intelligence

2024-02-02T10:43:43.316000+01:00

We have the second edition of SAP BTP: Ask Me Anything coming up and this time the spotlight is shining over the topic of Artificial Intelligence.

In the past few months, we’ve released new features and capabilities within SAP Business Technology Platform to support the infusion of AI in development projects. It’s only fitting that for our February episode, we put you in contact with some of the experts behind these innovations. We’ll focus on 3 major announcements:

Generative AI Hub in SAP AI Core

If you haven’t seen the blog post, let me summarize some of the benefits provided to development teams:

Instant access to large language models (LLMs) from different providers
Possibility to orchestrate multiple AI models
Tooling for prompt engineering and experimentation

You can try it out for yourself by following this tutorial.

@HadiHares, from the SAP AI Core PM team will join this session to walk you through the key capabilities and answer your questions. You might recognize him from SAP TechEd sessions in Bangalore last year and his engagement in the SAP Community.

Document Information Extraction, premium edition

We’ve infused generative AI capabilities into our Document Information Extraction service and released the premium edition in December 2023. In a nutshell, users can process documents intelligently across their entire business, with:

Automatic extraction of unstructured data by just describing the required fields.
Multilingual support for over 40 languages, supporting global business requirements.
Quicker onboarding of business document processing use cases as there is no manual annotation or resource-intensive ML training required.

You can get some hands-on experience by following this tutorial.

@tomasz_janasz will share the latest and greatest and, of course, answer your questions. Another well-known face in the SAP TechEd context as well as an avid SAP Community blogger

SAP Analytics Cloud - Just Ask

Just ask is the new natural language query feature powered by AI in SAP Analytics Cloud. With just ask, any user can query SAC data models by asking questions in everyday English. It supports SAP Analytics Cloud acquired data models and SAP Datasphere models. If you have not heard about this latest feature, check out this blog post

@francois_imberton, our resident expert on the topic, will join this session to demonstrate how it works and answer your questions. You might recognize him from other community engagements or from reading his posts.

When: February 21 at 4PM CET

If you already have related questions, drop them in the comments below. We’ll bring them to the session, so our experts can answer them LIVE.

Learn more about SAP BTP and Artificial Intelligence:

SAP BTP Innobytes: bite-sized monthly video series, sharing the latest hits and top SAP BTP innovations.
What’s New with SAP BTP: quarterly LIVE series for SAP BTP innovation highlights, with demos and time for Q&A
SAP BTP Garage: monthly LIVE webinar with hands-on use case walkthroughs and demos
SAP BTP Talk: monthly podcast covering all things SAP BTP
SAP BTP Community topic page
SAP AI Services Community topic page
SAP AI Core Community topic page

Generative AI-powered Contract document processing with Large Language Models

2024-02-19T03:54:18.101000+01:00

Introduction

Contract Document Processing Use Case

Automate the extraction of relevant information from contract documents with Document Information Extraction with Generative AI (premium edition) by leveraging the capabilities of Large Language Models, ensuring faster, more accurate document processing with significantly reduced processing costs.

Process Supply Contract using Generative AI

Document Information Extraction Service does not come pre-configured with support for custom document type - Contract. So, let us create a custom schema utilising Large Language Models (LLMs) to specify the fields we wish to extract from the supply contract document.

Schema Creation for Supply Contract

Access Document Information Extraction Application as described in the tutorial Use Trial to Set Up Account for Document Information Extraction and Go to Application and create new schema.

Create Supply Contract Schema

Supply Contract Schema

Addition of Fields

Access the supply contract schema and add fields at header and line item level.

Add Data Field

Note:

LLMs are used to extract the data from the document when you use setup type auto.

Added Fields

Tip:

When adding field names and descriptions, consider yourself explaining what you want to extract to someone who doesn't know anything about it already.

The better you describe the information that you want to extract using generative AI, the better your results will be.

Similarly, fields can be added at line item level.

Schema Activation

Now, activate the supply contract schema.

Activated Schema

Obtaining Extraction Results

Upload the contract document (sample below) using the newly created supply contract schema.

Sample Supply Contract

Supply Contract Schema associated Document Upload

Extraction Results

Conclusion

With the Schema Configuration feature from Document Information Extraction and LLMs, we have now successfully extracted information from a supply contract document without the need to create any templates.

Similarly, Document Information Extraction with Generative AI can be utilised for extracting structured information from other types of contracts.

Further Information

Please feel free to add a comment, should you have any queries.

Best Regards,
Anuradha Dhingan

Top Picks: Innovations Highlights from SAP Business Technology Platform (Q4/2023)

2024-02-20T21:19:27.745000+01:00

The innovation highlights blog for SAP BTP (Business Technology Platform) is back in 2024. I´m excited to see which innovations are coming up in 2024 for SAP BTP. But isn´t it worthwhile reviewing the top Q4 2023 highlights of our recent deliveries out of the SAP BTP product roadmap as well?

Join me to take a closer look at a subset of my personal innovation highlights of SAP BTP in Q4 2023 and an outlook of what´s coming up next.

SAP BTP Innovation Highlights Q4 2023

Application Development and Automation:

With Q4 2023, SAP Build Apps is now available with the SAP BTP Trial Account. Trial Accounts allow to experience and evaluate the key functions of SAP Build Apps, the low-code application development tool. If you ready to experience SAP Build Apps then activate your Trial Account right now following a few simple steps. Learn how to get started with the blog post of @EsmeeX.
SAP Build Work Zone got some new features and enhancements as well. A new site experience for SAP Build Work Zone, standard edition, import and export of site menu for the advanced edition are just two new features for a smooth admin experience. Business users can be happy as well as they also got a new improvement for the guided experience with wizard layout. Check out also the integration of Joule, our digital assistant, in SAP Start. Read the blog post of @Vera_Gutbrod to get all updates.
In Q4 2023 SAP Build Process Automation released a new set of 19 content packages - 12 business content and 7 learning content crafted for IT, Sales, Services, Sourcing, Finance, and Procurement. A detailed list on the new content can be found here. Check out also the blog post of @JesseSukhbayar to get more insights on what´s new with SAP Build Process Automation. If you have found interesting content and need to know how to deploy the pre-built content in SAP Build Process Automation I can highly recommend to watch the video demonstrating it. Learn how easy it is and configure step by step to fine-tune the content before deploying it in your project.

Integration:

Concentrating on our flagship integration product, SAP Integration Suite, we released a flexible hybrid integration runtime: Edge Integration Cell. The new extension of SAP Integration Suite as Kubernetes based solution provides the option of a local, customer-managed environment of the SAP Integration Suite. With this we provide customers with hybrid or private environment the flexibility to choose the runtime for the execution of ground-to-ground or hybrid integration scenarios depending on their use cases. Edge Integration Cell supports for example the execution of integrations between local on premise systems without any data leaving the local datacenter and without loosing the comfort of having a central design and management solution for all integration scenarios. It helps a lot of customers in certain industries to meet region specific laws and regulations. Check out the announcement blog post of @piyush_gakhar and the FAQ blog post of @finny_babu to get more insights. For 2024 there are already several innovations on our Road Map Explorer for Edge Integration Cell.
To provide enhanced B2B integration, Trading Partner Management capability enables now support for validating and converting the Tradacoms message format by introducing a new flow step. It provides the full end-to-end support for Tradacoms messages in Trading Partner Management and you are able to use the type system for modelling guidelines in Integration Advisor. Check out the blogpost of @joerg_ackermann for more information.

Data and Analytics:

The data lake realational engine in SAP HANA Cloud has with Q4 2023 the ability to read and write data from nearly any files instance of SAP HANA Cloud data lake. This significantly improves the integration between instances of SAP HANA Cloud and broaden access to data sources from the relational engine of the data lake for SAP HANA Cloud. You will benefit from expanded access to diverse data sources, fostering improved data utilization and reinforcing the synergy between various SAP HANA Cloud instances. If you want to learn more check out the blog post of @thomashammer to get more highlights on what´s new for SAP HANA Cloud in December.
Additionally with Q4 2023 you have new options of data center availability and hyperscaler options for SAP Analytics Cloud through the deployment of Google Cloud Platform (GCP) in the Asia and Europe region.

Artificial Intelligence:

At TechEd 2023 in November we did not only announce the generative AI hub - it also got released just a few weeks later. The generative AI hub provides instant access to a broad range of large language models (LLMs) from different providers and partners like GPT-4 by Azure OpenAI or OpenSource Falcon-40b. With this access, developers can orchestrate multiple models, whether programmatically via SAP AI Core or via the playground within SAP AI Launchpad. Check out the blog post of @HadiHares.
With the Q4 2023 release the new Document Information Extraction, premium edition supercharged by AI capabilities, makes the process of different types of documents without increased costs or more manual work possible. It automates all business document use cases in most languages end to end, provides built-in support for 40+ languages with extensions for virtually any kind of document and makes extensions of exisiting extraction routines possible. To get more information read the blog post of @tomasz_janasz.
If you are interested in a deep-dive of SAP´s Generative AI strategy make sure you read the blog post of @philipp_herzig. The blog post is the first of a series that dives deeper into various aspects of SAP’s approach to generative AI and its technical underpinnings.

Cross SAP BTP:

Guidance on the best way to develop extensions and applications on SAP BTP is a topic everyone is lacking for. Our in Q4 2023 released SAP BTP Guidance Framework is the compass for architecting, implementing, and operating solutions on SAP BTP. It includes elements like decision guides, reference architectures, methodologies, recommendations and DevOps. One resource within the SAP BTP Guidance Framework which was also released in the last quarter of 2023 is the SAP BTP Developer´s Guide. The guide helps on how to implement business applications on SAP BTP and explains the building blocks for developing, delivering, and integrating business applications.
Our famous SAP Discovery Center also got some updates. In addition to missions and services the SAP Discovery Center cosmos now includes reference architectures. As of now you can find integration, data and analytics and hyperscaler references architectures in our catalog. Each reference architecture provides you guiding information which helps to understand its scope, mechanics, how it relates to SAP business applications and guidance when to choose a particular reference architecture. The SAP BTP reference architectures are also part of the just mentioned SAP BTP Guidance Framework.
With Q4 2023 we also announced the availability of the SAP Application Extension Methodology version 2.2. The SAP Application Extension Methodology supports and guides you by providing a structured, technology agnostic approach to define an organization specific extension strategy. Version 2.2 offers now a full documentation on the SAP Help Portal, improved technology agnostic extension tasks and a refined extension technology mapping. Check out the blog post of @MarcoMatha to learn more.

SAP BTP Innovation Highlights - outlook:

Please find here my personal innovation highlights outlook coming up:

Application Development and Automation: SAP Build Code
Application Development and Automation: Generating a business service of ABAP RESTful application programming model
Integration: AdvancedEventMesh adapter for event mediation
Integration: Support for custom SOA messages in Integration Advisor
Data and Analytics: Next-generation natural language query (NLQ) powered by AI for SAP Analytics Cloud
Data and Analytics: Support for storage and retrieval of vector embeddings in SAP HANA Cloud
SAP Identity and Access Management: Identity Authentication service integration with SAP Cloud ALM

Check out all upcoming innovations in our SAP Road Map Explorer to learn more.

Check out more on innovation highlights:

Follow the Roadmap Explorer, which is updated on a regular basis to always stay on top of the latest innovations 🔊
Subscribe to our monthly newsletter to get all SAP BTP product news 📫
Check out the next blog post beginning of Q2/2024 summarizing the highlights of the previous quarter 🗒
If you want to be up to date on the latest SAP BTP news and innovations check out the new monthly SAP Innobytes video series 📹
Want to get a recap on what´s new in SAP BTP then check out the What´s New in SAP BTP quarterly series
Mark your calendar for the latest SAP events coming up 📅

👉 Read other SAP Business Technology Platform blog posts and check the SAP Business Technology Platform Topic Page where you can also ask questions. Feel free to follow my profile stephanie.stang that you do not miss my next personal view of innovation highlights for SAP BTP for Q1 2024.

Information Archeology, A Journey Through Historic Data Content

2024-03-05T14:05:54.895000+01:00

Recently, I've researched drinking water quality in nearby rural areas, documenting historic "haves" and "have-nots" for an environmental equity study. Viewing government documents obtained via public information requests, I spotted column numbers between 1 and 80, as we would have done in the 1960s and 1970s before tape and disk storage arrived.

Deck of Cards

For the benefit of future application developers who may "inherit" similar legacy workflow methods, I will share what I can discern from those sparse numbers and other clues, and ways to pull past data into future systems.

Location data then

Starting with "you want to drill where?," the above clip shows "B3" in a small rectangle, and "B4" in another section below. Believe it or not, these are 80-column "IBM punch card" record formats, where, for instance the local county would be punched between columns 8 and 21 (just long enough for the longest name in the set). Yes, Imperial measurements of miles not kilometers, and for some odd reason the multi-part carbonless paper form has "hard-coded" the letters MI for miles, in columns 77 and 78.

Location data now

A more recent form has nearly identical information fields, except the "paper" form is now a fillable PDF.

Orientation Then and Now

Besides the where-is-it question there is the in-reference-to-what question.

Distance from the nearest road can be entered as either feet or miles, and the cool compass rose is supposed to point in a direction. If you fill it in.

The newer data collection method is not that different.

I don't think the ordinal points look as nice as before; the column 32 on the punch card is still with us, getting one character: NSE or W.

Workflow: Driller

Since the work must be done only be a certified driller, the form includes their contact and license information. Not too many punch card columns here (76-81 for license). Beyond the margin!

Now, it's like this:

Nicely done calendar in the PDF. Some algorithm was inserted in the form that allows easier selection, less transcription, and probably deals with leap years correctly.

Card B2: Approximate Pumping Rate, in Gallons per Minute. This is before the well is drilled, so an educated guess. The government records your guess for posterity in columns 8 to 12; the card letter/number go into columns 1 and 2. Somewhere in time, a FORTRAN (or COBOL) program once crunched those data into some type of report. The paper hanging chad content lives on, somewhere in an SAP or Oracle system.

Card B4: Water sources (up to 3), no punches.

Quantity Needed

In classic American post-WW2 affluence, everyone (* with exceptions) was awarded a 100 gallon (400 liters) stipend as an expected privilege of suburbia. People that live on boats or other small footprints know this is absurd. We can't know why this question is necessary or important other than being yet another educated guess. I've seen the value 300 (so a 3-consumer space) in this field, for single residential use. For agriculture or mass residential (towns), you can enter up to 20-14+1 digits.

The provenance of legacy data can be established if the original systems were documented and you can find the docs, or if meta-data chain of custody is visible. Definitely not block chain tech here, just fill in the boxes.

What can be added to the historic record are errors and omissions found reviewing the previous data archives. I've posted elsewhere using the key "blue pencil" as a nod to the days of paper copy editing before publication. Reversing the north and south values was one example, corrected by crossing out since getting a new form and starting over is frustrating. One land record change had to be recorded for posterity because numbers were reversed on the first try (so if you only looked there you'd get bad data).

Future Proofing

Okay, stop laughing now. We can't predict the future but can learn from the past. Supposing our new project assignment is taking the data collection and approval workflow into a mobile app so QR codes and pin drops take the place of "Please Type."

Once you grasp the provenance of historic data points and collections, look at the implicit or explicit data constraints, whether that is a data domain or range, or a field constraint, for example:

enum Level {
  LOW,
  MEDIUM,
  HIGH
};
/* reference: https://www.w3schools.com/c/c_enums.php */

The idea of using 2 digits for a year should have gone out of the style at, say, the turn of the century, however this anachronism continues on local government forms:

After collecting the 2 digits for the year, an algorithm stores the guessed 4-digit year for archival storage. Using a data collection mechanism like the PDF calendar form is an option, as is requiring 4 for digit years (and doing a sanity check that someone doesn't select the year 0042, say).

Hidden biases, not to mention oversights by developers, may be exposed in user testing. The sooner the better after noting areas to be addressed, such as accessibility, multiple language support, low-or-no vision options, and addressing environmental equity should past practices need attention.

My focus on gathering historic data is not research as much as prediction and a basis for action to mitigate climate change impacts on the double jeopardy of low-cost structures/infrastructure aligned with literal low-lands, sinking into coastal waters in some cases. I've envisioned the flat page data as having multiple dimensions of data collection, that can be woven together into stories using maps.

If you've reached this far, below is the SAP HANA hook for GIS data which you might be able to use after prototyping like I've done with other databases.

Deliver Real-World Results with SAP Business AI: Q4 2023 & Q1 2024 Release Highlights

2024-03-27T09:51:25.335000+01:00

Artificial intelligence (AI), and above all, generative AI, marks a paradigm shift on how computer systems learn from data, solve complex problems, and even provide creativity when it’s needed. We believe this paradigm shift will fundamentally change work, business, and society.
The impact that AI is expected to have on the global economy of the next three years is tremendous. Morgan Stanley estimate that the impact will be about $4.1 trillion dollars, about the size of the GDP of Germany.

SAP is committed to helping organizations through this transformative moment by creating business outcomes that were unimaginable before through SAP Business AI. Tailored to your unique data landscape and industry nuances, SAP Business AI enables smarter decisions and efficiencies at scale:

AI delivered in the context of your business processes
AI trained on the industry’s broadest business datasets
AI built on leading ethics and data privacy standards

SAP Business AI is relevant, reliable, and responsible. It’s deeply embedded in our business processes and analytics. Already today, more than 27,000 of our customers are seeing the benefits of AI that is built for business every day across every business function. No other technology company can combine the power of AI with the processes and data that run the business world. SAP is helping change how people interact with business software and make work more efficient and more delightful than ever before.

Let’s delve into the newest SAP Business AI capabilities made available for SAP customers helping them deliver real-world results.

Joule

Conversational Search

Introduced last year, Joule, SAP’s natural language generative AI copilot, revolutionizes the way people interact with SAP business systems, making every touchpoint count and every task simpler.

SAP customers can now get quick and seamless access to the exact SAP Help Portal content they need when asking a question in Joule, without ever having to leave the application they are working on. This generative AI-powered feature will be available in all SAP cloud solutions. We started with SAP SuccessFactors and SAP Start in 2023, continued with SAP S/4HANA Cloud Public Edition early 2024, and this will be followed by additional product integrations planned throughout this year.

Using Joule, SAP SuccessFactors and SAP Start users can save up to 10 minutes for an inquiry without leaving the UI and search in different content repositories, including search engines. This is another step towards helping our customers to become more productive and efficient. It drives product adoption, creates business value, and saves our users time and effort in accessing information quickly.

Joule Delivers Seamless Access to SAP Help Portal Content from SAP Solutions

Learn more on the product page.
Get started with the product documentation.

Cloud ERP

SAP S/4HANA Cloud, public edition

We have built Joule directly into SAP S/4HANA Cloud Public Edition, redefining user interaction, streamlining business processes, and enhancing productivity.
Joule can offer quick, contextual access to content and applications; users can simply ask Joule for guidance and get pointed in the right direction.

Looking for help to execute certain finance operations or looking for guidance how to change sales document entries? Joule provides quick and easy access to SAP Help Portal content and creates a summary leveraging generative AI. No need to browse through long search result lists anymore and reading into several topics to find the correct information.
Not sure which application could help to check the status of sales orders? Just express the need in natural language and Joule will propose the most reasonable applications for the required business operation.
Want to quickly check the status of a specific purchase order? Joule can also assist in providing insightful information about specific business objects. Once Joule shows up the required business information directly in the natural language user panel, users can directly jump into the business application from there.

Joule in SAP S/4HANA Cloud Public Edition

Learn more on the product page.
Register for the SAP Early Adopter Care program to test this feature before anyone else.

Are you tired of manually inputting incomplete sales order data? Filling in these missing details requires significant manual data management effort.
The sales order autocompletion capability in SAP S/4HANA Cloud Public Edition eliminates this hassle by providing smart recommendations for seamless data input. Missing fields are automatically populated,
simplifying incomplete sales order handling, delivering cost savings and boosting sales expert productivity.

Sales Order Autocompletion in SAP S/4HANA Cloud Public Edition

Read the blog post.
Get started with the product documentation.

SAP Enterprise Service Management

Shared service centers drive business value by enabling organizations to provide fast and reliable service cost-efficiently. However, too often organizational silos, distributed data and duplicated processes cause complexity and reduce the productivity and quality of service.

With generative AI capabilities in SAP Enterprise Service Management, shared service teams can:

summarize text in email interactions for cases with Case Summary
draft email replies or interactions for cases with Email Draft Recommender
get all the information related to an account that helps the sales representatives with Account Synopsis

Implementation results in significant reductions in overdue items ultimately enhancing customer satisfaction and streamlining processes. By implementing SAP Enterprise Service Management, businesses can save up to 70% of the cost for across various service scenarios or processing service requests 30% faster, like one of our global customers in the automotive industry has achieved for their accounts payable shared-services teams.

SAP Enterprise Service Management Homepage

Get started with the product documentation.

SAP Transportation Management

Imagine the chaotic scene at a freight clearing dock. Freight logistics providers arrive with stacks of manual papers, causing delays, inefficiencies, and the need for manual rework. Anomalies in freight orders are often detected late, leading to even longer processing times. It's a frustrating and time-consuming process for anyone involved.

Generative AI capabilities have been infused as part of SAP Transportation Management to expedite freight verification and documentation seamlessly. Businesses can automate the processing of tens of thousands of goods receipts and delivery notes in SAP Transportation Management, avoiding data entry errors and processing many types of document layouts without needing to do any training.

The benefits of this solution are immense. First and foremost, there's faster processing time with greater accuracy, minimizing errors and reducing the need for manual checks. This means less waiting time for logistics carriers and the potential for reduced yard space through optimized turnaround times. Additionally, the entire operation experiences enhanced operational efficiency and improved data quality for subsequent processes. Delivery notes are processed 50% faster, saving valuable time and resources. And the cost for truck delivery processing is reduced by an impressive 50%.

This capability is available as pilot phase for SAP customers, with a general availability planned for Q4 2024, including new features.

Expedite Freight Verification in SAP Transportation Management

Learn more about SAP Transportation Management.

SAP Digital Manufacturing

Visual inspection for SAP Digital Manufacturing is now available as a redesigned beta release for SAP Digital Manufacturing customers and will be generally available in the second quarter of 2024. This feature transforms human visual inspection experience to overcome human cognitive limits and empowers production engineers to enable AI models to visual inspections.

AI is leveraged to simplify and optimize visual inspection processes, assisting workers in finding defects earlier, faster, and more accurately. Operator productivity, product quality, and user experience are all improved at the same time. According to the first customer pilots, visual inspection can reduce the time to visually inspect parts by 60% when AI-assisted.

Visual Inspection - Detect Product Defects Faster on the Shop Floor

Learn more about SAP Digital Manufacturing.
Get started with the product documentation.

Human Capital Management

SAP SuccessFactors

Joule is integrated natively in SAP SuccessFactors, enabling employee and managers to quickly complete tasks in natural language such as requesting a wide range of record updates, providing feedback, checking and viewing your payment statement, approving time off requests, and much more.
You can access Joule via SAP Start and all pages in the SAP SuccessFactors HXM Suite.
Let's enable a future-ready workforce with our AI copilot that truly elevates every employee's experience.

Access Joule on the SAP SuccessFactors Homepage

Start the product tour to test Joule capabilities in SAP SuccessFactors yourself.
Get started with the product documentation.

In addition, SAP SuccessFactors Recruiting customers can now create compelling job descriptions and interview questions with the help of generative AI.

Attracting the right talent begins with the right job description. That’s why our generative AI-powered assistant gives hiring managers and recruiters a huge jump start to write non-biased, compelling job descriptions in seconds, while still allowing them to edit and improve it afterwards. Not only does it save a significant amount of time – from 2 hours to 5 minutes – as well as costs in creating job descriptions, but it also improves the quality of interviews and preparation. This, in turn, increases attractiveness as employer of choice, because potential applicants can sense the professionalism and attention to detail that the company brings to the hiring process.

Writing Job Descriptions in SAP SuccessFactors Recruiting

Conducting an effective interview is crucial to ensuring you’re making the best hiring decision. Interviewers can now generate interview questions based on the job description using generative AI capabilities and evaluate applicants in Microsoft Teams after they complete their interviews. AI-powered questions will make it easier for you to create an insightful discussion that dives deep into a candidate’s skills and potential. Your hiring process becomes more streamlined and ultimately leads to better hiring decisions.

Generating Interview Questions in SAP SuccessFactors Recruiting

See how these new capabilities help organizations attract, develop and retain top talent:

Put Your People and Their Experiences First with SAP Business AI

Customer Experience

SAP CX AI Toolkit

Available for existing SAP CX users with SAP Sales Cloud, SAP Service Cloud or SAP Commerce Cloud (standard edition) solution licenses, SAP CX AI Toolkit empowers your sales, service and e-commerce teams with proactive and contextual generative AI:

Apply AI models to data from sales, service, and e-commerce, along with operational data, to help your teams make more intelligent decisions.
Enable your teams to use AI to automate routine tasks from right where they work using a stand-alone app or Joule.
Understand customers and answer their questions faster than ever before with proactive insights and answers derived from enterprise data.

Capabilities available for e-commerce teams:

Product Tagging: Unlock the full potential of your products by harnessing the power of AI to extract and enrich your product tags. Take your catalog to new heights.
Personalized Product Descriptions: Let generative AI transform your customer experience with personalized product descriptions that enrich your catalog data.
Visual Search: Improve product discovery - simplifying the process and delivering quick and accurate search results based on AI image detection.
Commerce AI Tools: Commerce role specific prompts utilizing CX data to generate a blog post, social media posts and more.

Capabilities available for sales teams:

Intelligent Customer Profile: Uncover insights with a 360-degree view of every customer through Customer Data Platform integration. Quickly view segment data and profile summarization contextually on top of email and Sales Cloud.
Sales AI Tools: Create your own AI Tools for unique business needs or utilize our standard sales role specific prompts utilizing CX data to generate discovery questions, emails and more.
Intelligent Q&A: Proactively identify questions within your conversations and deliver trusted answers from company knowledge.
Smart Scheduling: Streamline and optimize your calendar management, saving you time and ensuring efficient allocation of appointments with personalized AI responses.

Capabilities available for service teams:

Intelligent Customer Profile: Uncover insights with a 360-degree view of every customer through Customer Data Platform integration. Quickly view segment data and profile summarization contextually on top of Service Cloud.
Service AI Tools: Create your own AI Tools for unique business needs or utilize our standard service role specific prompts utilizing CX data to generate responses, case overviews and more.
Intelligent Q&A: Proactively identify questions within your conversations and deliver trusted answers from company knowledge.
CX Record Summarization: Align your organization on customer issues, pathway to resolution, sentiment, and responsiveness with service and leadership specific case summaries.

Drive Profitable Growth with SAP CX AI Toolkit

Learn more on the product page.
Get started with the product documentation.
Additional AI-powered functionalities are planned to be released as part of SAP CX AI Toolkit throughout 2024.

SAP Sales & Service Cloud Version 2

Generative AI-powered capabilities have also been introduced as part of SAP Service Cloud Version 2 and SAP Sales Cloud Version 2, enhancing sales & service teams productivity:

Account Synopsis (in SAP Sales Cloud Version 2 & SAP Service Cloud Version 2) summarizes all the information related to an account that helps the sales representatives, such as the business, the culture or the competitive landscape. It ensures that your team is always equipped with the latest information, enabling them to make well-informed decisions and deliver a superior customer experience.
Case Summary (in SAP Service Cloud Version 2) automatically fetches a text-based interaction (e.g. email) and pre-processes it. Display summary to customer service rep to quickly grasp the topic and simplify the agent experience.
Email Draft Recommender (in SAP Sales Cloud Version 2 & SAP Service Cloud Version 2) generates a response email based on the previous email reply and purpose selected by the user for which an email needs to be drafted.
Lead Booster (in SAP Sales Cloud Version 2) provides tailored information that enhances the sales team’s understanding of the account’s needs and increases the likelihood of successful sales conversion.

Learn more on SAP Sales Cloud and SAP Service Cloud product pages.
Get started with SAP Sales Cloud Version 2 and SAP Service Cloud Version 2 product documentation pages.

Watch the video below to see how SAP Business AI provides the backbone for understanding and responding to customer needs - helping you get from issue to resolution faster.

Provide Customer Service That’s Personalized and Fast with SAP Business AI

SAP Emarsys Customer Engagement

Make the creation of subject lines intuitive for your email campaigns based on your natural language prompts! As part of SAP Emarsys Customer Engagement, Emarsys’ AI Subject Line Generator – currently in its pilot phase – uses AI to analyze your campaign content and generate multiple engaging and contextually relevant subject line options.

It saves time and effort by enabling marketers to create subject lines more efficiently, enhances creativity with a range of new subject-line ideas and enable data-driven decisions with the ability to A/B test AI-generated and traditional subject lines.

AI Subject Line Generator in SAP Emarsys Customer Engagement

Explore additional capabilities on Emarsys’ website that empower marketers to build, launch, and scale personalized cross-channel campaigns that drive business outcomes.

Intelligent Spend and Business Network

SAP Ariba Category Management

Gone are the days of painstakingly updating category management tools manually. Category managers can now expedite the development of their category strategy with contextual insights and recommendations using generative AI and large language model (LLM) integration in SAP Ariba Category Management tools, such as Category Segmentation, Market Dynamics, and Cost Structure.

It normally takes 12 weeks to manually create a strategy for a new purchasing category, but with SAP Ariba Category Management, research on category specific information is available with a single click. This new generative AI-powered feature accelerates strategy and planning processes across multiple categories, reduces onboarding time and reliance on more senior category managers and helps adapt to market change with insight and agility.

Powering Strategy Planning with Generative AI in SAP Ariba Category Management

Learn more on the product page.
Get started with the product documentation.

SAP Business Network

For suppliers, invoice creation can be one of your most inefficient and redundant processes. Every day, employees are manually keying data to submit invoices to customers.
The introduction of the intelligent invoice conversion feature of SAP Business Network reduces the need for this error-prone manual approach to invoice data entry.

The feature automatically converts your invoices from PDF and other scanned image files into an electronic format in SAP Business Network. It extracts your invoice data and automatically maps it to relevant fields in the electronic invoice and simplifies onboarding by providing a self-service setup process that guides supplier administrators through a streamlined workflow.

With intelligent invoice conversion, improve operational efficiency, reduce errors and rejected invoices, and receive payments faster.

Intelligent Invoice Conversion in SAP Business Network

Learn more on the product page.
Get started with the product documentation.

SAP Concur

AI is only as good as the quality and breadth of the data it draws upon, and SAP Concur is the global market leader in travel and expense solutions, with more than 92 million end users booking travel and/or processing expenses. For a decade, we have been infusing AI into SAP Concur solutions including ExpenseIt, Verify, Intelligent Audit, and Concur Invoice.

This quarter, we are excited to debut new Business AI capabilities in SAP Concur solutions:

Concur Request: Now uses generative AI to provide intelligent cost estimates for trip planning, saving employees time and effort. When the user creates the request, they enter their trip details such as the length of the trip and the destination. They will have the option to select from the following services that they want cost estimates for: flight or train; hotel; taxi. Request Assistant uses generative AI and the trip details provided by the user to provide estimated costs with explanations for the pricing.

The user can adjust, based on their needs for the trip, such as flight class, number of connections, hotel ratings, and then regenerate the estimated cost. The estimated costs are automatically added to the request as expected expenses. Subsequently, the user can choose to add additional expected expenses if needed or submit the request for approval.

Intelligent Cost Estimates for Trip Planning in Concur Request

ExpenseIt: We’ve also brought capabilities from ExpenseIt on mobile to the web interface so customers can upload receipt images to ExpenseIt web, where it taps AI to automatically create a new expense with several key fields prepopulated.

Expense itemizations for hotel folios are cumbersome for end users to manually enter, and inaccurate itemizations can cause returned expense reports and rework. In fact, the median time to complete a report with manual hotel itemizations entries is about 17 minutes longer than an expense report with no manual hotel itemizations.

Using ExpenseIt, hotel itemizations can be processed for the end user in under 30 seconds, saving employee time while increasing accuracy. The recent generative AI update to the traditional AI ExpenseIt models increases the accuracy of hotel itemizations by 30% (as measured by 100% accurate itemizations) in pre-production testing.

Hotel Itemization in Concur ExpenseIt

Learn more about travel and expense with SAP Business AI.
Get started with the Concur Expense and Concur Request product documentation pages.

SAP Business Technology Platform (SAP BTP)

Document Information Extraction, premium edition

The existing Document Information Extraction service on SAP BTP has been supercharged with generative AI capabilities, introducing Document Information Extraction, premium edition.
Businesses can now process documents intelligently across their entire business, with:

The automatic extraction of unstructured data by simply describing the required fields that you need, and watching the solution do the heavy lifting for nearly every document type.
The multilingual support for over 40 languages, catering to global businesses with diverse document types.

With neither manual annotation nor resource-intensive machine learning training required, business document processing use cases can now be onboarded in days instead of weeks or months, reducing the time-to-value drastically.

Learn more on the SAP Discovery Center.
Get started with this tutorial.

Generative AI Hub in SAP AI Core and SAP AI Launchpad

SAP developers can expedite their generative AI development of SAP BTP applications in a secure and trusted way with the new Generative AI hub. This new capability gives streamlined access to a broad range of large language models (LLMs) from different providers (such as GPT-4 by Azure OpenAI or OpenSource Falcon-40b), facilitated in a more secure, harmonized, and orchestrated manner; thereby boosting efficiency and productivity.

Developers can orchestrate multiple models, whether programmatically via SAP AI Core or via the playground within SAP AI Launchpad, and ensure high-quality output by choosing the large language model that best aligns with their unique use case. They can leverage all features while relying on a data privacy policy and robust measures, ensuring secure and trusted operations.

Each generative AI model yields unique qualities and strengths. To meet customers’ needs for their business, SAP has made a strategic move to provide enterprise-grade access to the most common models through its generative AI hub as part of SAP AI Core. This includes leading cloud vendors as well as SAP-managed third-party models deployed on SAP’s own infrastructure for highest compliance standards.
All available and upcoming generative AI-powered capabilities from SAP are running on the generative AI hub.

Generative AI Hub via SAP AI Launchpad

Learn more on the SAP Discovery Center.
Get started with this tutorial.
See why the generative AI hub plays a core role in how SAP's generative AI architecture redefines business applications.

Just ask feature in SAP Analytics Cloud

Just ask is a natural language query interface available in SAP Analytics Cloud used to retrieve data that applies generative AI to search-driven analytics. Users can quickly access trusted insights in their preferred language regardless of expertise, helping to increase data literacy and analytics adoption for more fact-based decision-making.

By providing knowledge workers with self-service access to timely analytics, companies can improve their productivity by up to 5%. Instead of spending hours searching for data, they can focus on more strategic tasks that move their business forward.

Jusk ask users can search data easily and efficiently using business terms they are familiar with, by simply asking questions using natural language. Just ask will instantly provide answers as simple charts and tables. Working with data from acquired models or SAP Datasphere, users can query just ask to get quick answers to questions and incorporate the results into a story, export to CSV or Excel files, or for further exploration using the Data Analyzer tool.

Just ask in SAP Analytics Cloud

Learn more on the product page.
Get started with the product documentation.

SAP Build Code

SAP Build Code, our generative AI-based code development solution, is now generally available.
With its integration of Joule, optimized for Java and JavaScript application development, it provides a turn-key environment for coding, testing, integrations, and application lifecycle management.

Developers can use generative AI to generate code and app logic aligned with SAP-centric programming models from natural language descriptions, create data models and sample data conforming to apps with the help of Joule, and produce rapid unit tests with AI for existing code to increase quality and precision.

The solution is also tailored for SAP development and secure collaboration across SAP Build low-code solutions and ABAP Cloud. It provides rapid extensibility of SAP S/4HANA and other SAP as well as non-SAP systems. It prebuilds integrations, APIs, and business services via the service center. Furthermore, it ensures proven security from SAP BTP for authentication, authorization, and SAP data protection.

With up to 30% faster application development and up to 30% improvement in application development cost, this is a game-changer for your enterprise. Say goodbye to the days of spending endless hours on code development and maintenance. Say hello to a more efficient and productive future with SAP Build Code.

Pro-code App Development with SAP Build Code

Take the product tour to experience the next generation of application development.
Get started with the product documentation.

SAP HANA Cloud vector engine

SAP HANA Cloud vector engine can natively store and search vector embeddings, which are numerical representations of objects, along with business data as part of its industry-leading multi-model processing capabilities to power intelligent data applications.

With these vector capabilities, SAP HANA Cloud will enable Retrieval Augmented Generation (RAG), facilitating the combination of LLMs with private business data. These applications learn and adapt to new information, enabling automated decision-making.

Key benefits of the SAP HANA Cloud vector engine include:

Multi-model: Users can unify all types of data into a single database to build innovative applications using an efficient data architecture and in-memory performance. By adding vector storage and processing to the same database already storing relational, graph, spatial, and even JSON data, application developers can create next-generation solutions that interact more naturally with the user.
Enhanced search and analysis: Businesses can now apply semantic and similarity search to business processes using documents like contracts, design specifications, and even service call notes.
Personalized recommendations: Users can benefit from an improved overall experience with more accurate and personalized suggestions.
Optimized large language models: The output of LLMs is augmented with more effective and contextual data.

Retrieval Augmented Generation (RAG) and GenAI with SAP HANA Cloud Vector Engine

Succeed Now with SAP Business AI

AI plays a pivotal role in SAP’s commitment to enable every organization to become a network of intelligent and sustainable enterprises.

With a focus on ethical and responsible AI, we are not only driving efficiency and productivity, but also ensuring that AI is used for the betterment of society. Our uniquely holistic perspective on the demands of global businesses continues to inspire us as we define the future of business AI.

Accelerate your SAP Business AI journey today:

Visit SAP.com/AI and our AI SAP Community page for all SAP Business AI updates and announcements.
Explore the SAP Roadmap Explorer for a detailed view of upcoming product innovations.

Extract blob data (PDF) from CAPM using python library of Document information extraction service.

2024-04-26T13:59:46.787000+02:00

Hi All,

In this blog, I am going to talk about the Python client library for the SAP AI Business Services: Document Information Extraction.

Introduction:

Document Information Extraction helps you to process large amounts of business documents that have content in headers and tables. You can use the extracted information, for example, to automatically process payables, invoices, or payment notes while making sure that invoices and payables match. After you upload a document file to the service, it returns the extraction results from header fields and line items.

Use case:

Extract the documents (invoice detail) from an application where it is maintained as an attachment, and it is stored as a blob object in HANA database tables.
Before the data is imported into a HANA database, transform the information that was retrieved from the blob object into a format that can be utilized for further analysis.

Key services used in this solution:

SAP Document extraction service – AI Business Service.
SAP Cloud foundry - Runtime Environment
SAP Business Application Studio – Development Environment.
SAP HANA Cloud – Database to store extracted information.

In this blog, primarily we will focus on how to read the invoice file stored as Blob and extract required information using python client library for SAP AI business service: Document information extraction.

CAPM (Cloud Application Programming Model) Application:

Create a simple CAPM application with UI to upload and maintain invoice file as an attachment. This application's objective is to show how to define a field as an attachment which can be used to upload and maintain file as blob object in backend HANA table.

Prerequisite:

Log on to BTP trial cockpit. -> Click on "Go to Your Trial Home" -> Click on the subaccount, "trial”.
Click on the "Services" option in the left-hand panel and further click on "Instances and Subscriptions.”
Under the "Subscription", you can now see the SAP Business Application Studio. Click the link to open the same. Business application studio (BAS) will now open in another tab of your browser.
Access BAS with your login credentials and click “Create Dev Space.,” here I am using dev space name as “Local” and application type selected is “Full Stack Cloud Application.”
Now the dev space is up and running, and the business application studio for application development is ready.

Step1: Create Project

Click on the three-line button. -> Choose option File -> Select “New Project from Template”.
Select template as “CAP PROJECT” and click next.
Enter project name and add features “Configuration for HANA deployment”, “MTA based BTP deployment” and click finish to create CAPM Project (CAPMDOCEXT).

Step2: Create DB, Service and UI Artifacts

Create a file with extension .cds under DB folder to maintain database related content. Here I am using “docext_schema” as file name.
Add code as shown in below image in file “docext_schema.cds”

Document_uploaded is the column/attribute which holds file uploaded via UI as blob in HANA table.
The Filename column holds the name of the file uploaded.
Mediatype column holds the format/extension of the file uploaded.
Add code as in below screenshot in docext_service.cds file under SRV folder to create service for the application.

capmdocext-db is the HANA HDI service created for this application.
Bind the application to HANA HDI service.
Create fiori application by following the steps : right click on mta.yaml file ---> select create mta module from template ---> click sap fiori application --> select “list report page”.
Configure source and deployment target for fiori application as shown in below screenshot.

Step3: Run and Test the CAPM application from Local.

Run command cds watch –profile hybrid to launch the application from local (This will start the CAP service locally by binding the application to remote HANA instance).
Click create button to upload the invoice file into CAPM application as shown in below screen shot. Here sampleinvoice.pdf has been considered for testing.

Below screenshot shows the file uploaded via fiori, which is stored as blob in backend table of HANA HDI container.

Add deployment configuration for CAPM and deploy the application to cloud foundry.

Document Information Extraction using python library:

Step4: Setup Document extraction service, upload sample file and validate the fields.

Go to BTP account and click Booster from Navigation side bar.
Select “Set up account document information extraction” and click start to create the service.

Confirm that Document Information Extraction service and Document Information Extraction Trial UI is available in subaccount.
Add Document extraction service-related roles (Document_Information_Extraction_UI_End_User_trial ,
Document_Information_Extraction_UI_Document_Viewer_trial & Document_Information_Extraction_UI_Templates_Admin_trial ) to the user.

In below steps we will see how to manually upload the file and validate the extracted information using document information extraction UI service.
Click “Document information Extraction Trial” to open the UI service.
Click + button at right top of UI application to upload the invoice file selected for validation.
Choose the document type as Invoice and upload the file (Sampleinvoice.pdf)
Select the fields/column to be extracted in Header and Line item of invoice and click confirm.
Once the status changes from pending to ready, click “Extraction Results” to preview the value extracted from file and confirm it is same as PDF content.

Step5: Get the value from Document extraction service key to establish connectivity.

DOX API python library is the library used to establish connectivity to document extraction service. Import the service in python program using command” from sap_business_document_processing import DoxApiClient”.
Below 4 values are needed for communicating with the Document Classification REST API
1. url: The URL of the service deployment provided in the outermost hierarchy of the service key json file.
2. uaa_url: The URL of the UAA server used for authentication provided in the uaa part of the service key json file.
3. clientid: The clientid used for authentication to the UAA server provided in the uaa part of the service key json file.
4. clientsecret: The clientsecret used for authentication to the UAA server provided in the uaa part of the service key json file.
Click view credentials of document extraction instance to get parameter values from service key.

Step6: Create a python application to read the invoice file maintained as blob in application db.

Create a folder in your CAPM project to maintain Python microservice artifacts. Here I am using “pythonapp” folder to maintain all artifacts related to python app.
Create a manifest.yml file as mentioned in below screenshot. HANA HDI Service created in CAPM application is configured as service in yml file and application name is maintained as “blobextract”.

Create blobextract.py file and maintain python code to read blob object and extract invoice detail from file.
1. Import the libraries required to connect, upload the file into document extraction service, connect to HANA DB, Flask web framework, panda’s libraries, etc.
2. Add below code to connect HANA HDI container (capmdocext-db), query the Table column where files uploaded are maintained as blob object and preview the file in web browser.

Create a runtime.txt file and specify the Python runtime version that your application will run on.

Create requirements.txt and maintain all dependencies as mentioned in below screen shot.

Deploy the python application using command “cf push” from pythonapp root folder to get application deployed in cloud foundry.

https:// ********.cfapps.eu10.hana.ondemand.com is the URL of application deployed in cloud foundry.
Open browser and paste below URL with extension as preview and input parameter as filename uploaded in CAPM to preview the file https://********.cfapps.eu10.hana.ondemand.com/preview/filename=sampleinvoice.pdf

Step7: Extend the python code to upload the invoice file maintained as blob into document information extraction service and load extracted information into HANA schema.

Add code as in below screen shot to open the file maintained as blob, connect to Document information extraction service, upload the file into Document information extraction service , extract the header and line item defined to be read, connect to HANA Staging schema, load the extracted information in HANA table.
Establish connection to document extraction service by passing (url, client_id, client_secret, uaa_url) to DoxApiClient. (Refer step 5 to get details on how to get the parameter to establish connection to document extraction service)

Define the columns to be extracted as shown in below screenshot.

Pass the filename, header fields, line items fields and document type as in below screen shot to extract information of invoice file.

Connect to HANA schema to load extracted information into HANA table.

Here we considered only header information extracted for data load and the same logic can be applied to load invoice line-item data.

Add below code to load extracted data into HANA schema.

Please refer below screenshot for complete code to extract file information using document information extraction service ,load extracted data into HANA table and return the data stored in table as an output.

Push the python application with newly added code to perform Document upload into document information extraction service, extract invoice detail and load into HANA DB.

Open browser and paste below URL with extension as extract and input parameter as filename uploaded in CAPM to upload document into document extract service and to load extract data into Invoice table maintained in HANA DB https://********.cfapps.eu10.hana.ondemand.com/extract/filename=sampleinvoice.pdf

Sampleinvoice.pdf maintained as an attachment in CAPM application is read and uploaded into document information extraction service using python microservice.

Information extracted through document information extraction service is loaded into HANA DB through python code.

References:

Summary:

In this blog, we have seen how to extract the invoice attachment maintained in CAPM application using python client library of Document extraction service. This solution can be extended to read any file format & Document Types that are supported by Document extraction service with an option to extract the information immediately from an attachment once it gets uploaded by user in application layer.

SAP Community - Document Information Extraction

Introducing Document Information Extraction Premium Edition - Unleashing the Power of Large Language Models and Generative AI

Document Information Extraction Templates with SAP Business One

What’s next?

Integration of ChatPDF with S4HANA - New era of OCR with Generative AI

The SAP Community is literally flooding now with AI and Generative AI-related blogs.

Organizations started to adopt ChatGPT for several generative or automation tasks.

Content - Suggestions, Rectification, Generation

Code - Suggestions, Rectification, Generation

JSON~XML Conversions and API Integrations

Data analysis with ChatGPT

& more….

Why I started to write this blog today, is the Idea of Generative AI is getting changed, and the business is trying to explore the new capabilities of ChatGPT and ChatGPT-powered tools.

To perform the dynamic OCR extraction from PDF and Automate the Business Process, you definitely need the below tools:

If we want to place all these things into one place, it will look like below -

Introduction

ChatGPT & ChatPDF setup -

Chat-PDF Time.

🔀 Upload a PDF File from the left pane -

🔀 Let's ask Some Basic Questions now -

🔀 Now Ask a Question to generate JSON data for you from the PDF extraction -

Now, I will try to predict the questions running through your mind and answer them..

⏩ What I am getting in this Blog?

⏩ This type of solution is already present, Boss? Then Why again?

⏩ What is the Business Value you have?

⏩ What is new you are doing here?

⏩ What is the benefit?

⏩ Why we will adopt and invest in this?

The main reason is that it will reduce your effort in Vendor Invoice or Customer PO PDF Mapping.

It can also adapt to all of your PDF onboarding and dynamic JSON and Mapping Generations. Auto adaptations to your environments.

⏩ How is that possible, Boss?

Step 1 - SAPBuilders Pick up SAP Build - Process Automation, similar to the Hammer🔨 of Thor⚡⚡

Step 2 - NodeNinjas Pick up Node-RED, Similar to Shield of Captain America ⍟⍟

Step 3 - SAPBTPDeployX Pick up Ngrok, NodeJS, BAS, CF-CLI, similar to the Infinity Gauntlet🫰 of IRON Man🦾🤖

Ngrok -

CF PUSH - a wonderful document by dj.adams

And SNAP.....

🫰

((I had a wonderful IRON MAN Snapping Picture here from Avengers End Game. Due to community restrictions, I had to remove it. 😔😔😔 You can go to this URL to see the image.))

⏩ This solution is GOOD, but it has problems...

⏩ What's Next? What I can learn more?

Conclusion -

The Generative AIs of this generation have started to generate a new Generation of Business Processes.

Streamlining Data Extraction from PDFs: The Power of Document Information Extraction (DoX) and SAP Build Process Automation

Let’s Get Started

Possibilities

Conclusion

AI in SAP BTP: Q3 2023 Highlights – SAP AI Business Services, SAP AI Core and SAP AI Launchpad

SAP AI Core 📲

Visual Studio Code extension for AI-driven development with SAP solutions

New SAP AI Core Learning Journey

Data Attribute Recommendation 📲

Enablement of transfer learning*

Explainable AI: Exposing feature contribution after model training*

Updated batch file upload for inference*

Document Information Extraction (SAP AI Business Services) 📲

Availability of API end points for creating schemas

Schema versioning – edit, update, and create new schemas using an existing schema name

Improved SAP managed global model for processing supplier invoices

Improved SAP managed global model for processing payment advice notes

New schema property to define user friendly names for your schema fields

Embedded support in the UI

Personalized Recommendation 📲

Complementary recommendations for end users

Support for consideration of the types of user interactions in boosting items

Stay tuned for AI at SAP TechEd – November 2-3, 2023

Build Relevant, Reliable and Responsible AI for Business at SAP TechEd 2023

Subtrack #1: AI Built for Business What is in it for you?

Subtrack #2: Generative AI and Large Language Models What is in it for you?

Capturing Data for Your Sustainability Report with SAP Build

Sales Order Creation using DOX and SAP Build Process Automation

1.Create an Automation to get the data using Document Information Extraction and trigger the process.

2.Create a Process for Sales order creation.

Conclusion:

Automated Supplier Invoice Upload using SAP Build Process Automation

Introduction – Use Case

Challenge

Solution

Solution Diagram

Outcome

Subtrack #1: AI Built for Business
What is in it for you?

Subtrack #2: Generative AI and Large Language Models
What is in it for you?

SAP Business Technology Platform brings together application development, automation, data and analytics, integration, and AI capabilities into one unified environment optimized for SAP applications. Learn more: sap.com/btp

Share Your Thoughts 