Introduction to Gen AI at SAP

Generative AI has the potential to significantly impact businesses in today’s world. It refers to AI systems that can not only analyze data and make predictions, but also create new content, designs, and solutions across a wide range of applications, from automating repetitive tasks to creating personalized customer experiences. GenAI can help streamline workflows, improve decision-making, and drive innovation. It can also be used to generate new product designs, marketing materials, and even virtual prototypes.

In addition, GenAI can help businesses better understand their customers through advanced data analysis and predictive modeling. This can lead to more targeted marketing campaigns, improved customer service, and ultimately, increased customer satisfaction and loyalty.

This workshop will introduce the Generative AI hub and the SAP AI Launchpad.

SAP AI Core and the generative AI hub help you to integrate LLMs and AI into new business processes in a cost-efficient manner.

LLMs are self-supervised, deep learning models that have been trained on vast amounts of unlabeled data. They leverage AI technology and industrial-scale computational resources to learn complex language patterns and semantic knowledge bases for natural language processing (NLP) tasks. They parse input, such as prompts, and return contextually relevant responses written in natural language. A single LLM can perform multiple NLP tasks by using different input formats and output modes.

The generative AI hub gives 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, it’s possible to orchestrate multiple models, whether programmatically via SAP AI Core or via the playground within SAP AI Launchpad.

LLMs are general models but can be fine-tuned with additional embeddings for specialized or domain-specific use cases.

Scenarios

Access to generative AI models is provided under the global AI scenario foundation-models, which is managed by SAP AI Core. Individual models are provided as executables in the form of serving templates, and accessed by choosing the corresponding template for the desired model.

The following scenarios are available:

Global Scenario	Executable ID	Description
foundation-models	azure-openai	The Azure OpenAI Service provides REST API access to OpenAI’s LLMs
foundation-models	aicore-opensource	Open source models hosted and accessed through SAP AI Core
foundation-models	gcp-vertexai	GCP Vertex AI provides access to PaLM 2 and Gemini models from Google
foundation-models	aws-bedrock	AWS Bedrock provides access to Foundation models from Anthropic, Amazon and other providers.

Models

For more information about these models, including conversion rates for tokens, rate limits and deprecation dates, see SAP Note 3437766

For the latest updates on scenarios and models please see Models and Scenarios in the Generative AI Hub

Listed below are some models which can be used with the generative AI hub.

Executable ID	Model Name	Model Version	More Info
azure-openai	gpt-35-turbo	0613 & 1106	Azure Chat Completions
azure-openai	gpt-35-turbo-16k	0613	Azure Chat Completions
azure-openai	gpt-4	0613	Azure Chat Completions
azure-openai	gpt-4-32k	0613	Azure Chat Completions
azure-openai	text-embedding-ada-002	2	Azure Chat Completions
aicore-opensource	tiiuae–falcon-40b-instruct	N/A	Tiiuae Falcon 40b Instruct
gcp-vertexai	text-bison	002	GCP Vertex AI
gcp-vertexai	chat-bison	002	GCP Vertex AI
gcp-vertexai	textembedding-gecko	003	GCP Vertex AI
gcp-vertexai	textembedding-gecko-multilingual	001	GCP Vertex AI
gcp-vertexai	gemini-1.0-pro	001	GCP Vertex AI

The focus of this Technical Academy workshop is to show how Generative AI can be used to assist companies with a typical business process, and how this can be even further enhanced by employing the use of Retrieval Augmented Generation (RAG) in conjunction with SAP HANA Cloud’s vector engine to create more contextually relevant responses to queries.

For more information on the Generative AI Hub and SAP AI Core in general, please visit the AI Core Landing Page on the SAP help portal.