Large Language Models (LLMs) like ChatGPT and GPT-4 have gained significant popularity with emergent capabilities. In this sample, we have demonstrated how SAP partners can leverage this powerful AI technology in combination with SAP technologies to accelerate their solution development processes, and create more intelligent solutions on SAP Business Technology Platform(SAP BTP). In addition, please find more detail about exploring the potential of GPT in SAP ecosystem in this blog post series
Specifically, SAP partners can
- Use GPT to assist in SAP Application development
- SAP Cloud Application Programming Model(SAP CAP)
- SAP ABAP RESTful Application Programming Model(SAP RAP)
- Integrate GPT into your solutions on SAP BTP with through APIs.
| File or Folder | Purpose |
|---|---|
gpt-api-samples/ |
nodejs samples for GPT's chat api amd embedding apis for reference |
resources/ |
images etc |
src/ |
source code of the sample solution customer-interaction-gpt4 |
This sample solution aims to capture all kinds of customer communications via various channels in customer service in the form of customer interaction
- customers leave a product review on the website
- customers express feedback and concern about the product or service on social media(twitter,fb,ins,linkedin etc)
- customers has a question about the product update or their online order status, then create an inquiry through Q&A chatbot on instant messaging(whatsapp,messenger,wechat etc.)
- customers request support about troubleshooting etc.
The inbound customer messages in the customer interaction are analyzed and processed upon submission by GPT through its APIs for appropriate action.
- generate a title and a short summary of the message.
- perform sentiment analysis of the message to determine if it is positive, negative, or neutral.
- extract entities mentioned in the message, such as product, customer, and order etc, which can be used for further process automation.
- classify the message into different categories, such as technical issues requiring troubleshooting assistance or complaints needing immediate attention etc. which triggers the follow-up action based on business rules.
Keep a comprehensive record of all communication between end customers and service agents. Instead of using the term "ticket", let's refer to it as "customer interaction" to encompass various forms of communication, including in-person conversations, phone calls, emails, live chat, and more. The purpose of customer interactions is to address customer needs, answer questions, provide support, and assist with any concerns. Each customer interaction consists of inbound customer messages and outbound service messages.
Apply advanced text analysis and processing techniques to analyze each inbound customer message. This includes sentiment analysis, title and summary summarization, entity extraction, and intent classification. These analyses will be used to determine the appropriate actions to be taken based on configurable rules.
Customer Interaction Insights and Analytics: Provide insights and analytics on customer messages using various dimensions such as time, customer, priority, category, and intent. This allows for a deeper understanding of customer interactions and facilitates data-driven decision-making processes.
Provide insights and analytics on customer messages using various dimensions such as time, customer, priority, category, and intent. This allows for a deeper understanding of customer interactions and facilitates data-driven decision-making processes.
- Ticketing Service: Customer interaction submmision and tracking
- LLM Proxy Service: A reusable service to proxy all the LLM-related integration
- Orchestrator Service: Responsible integration with Business Rules and Backend system(SAP Field Service Management etc.)
Please refer to the instruction here.
Create an issue in this repository if you find a bug or have questions about the content.
For additional support, ask a question in SAP Community.
If you wish to contribute code, offer fixes or improvements, please send a pull request. Due to legal reasons, contributors will be asked to accept a DCO when they create the first pull request to this project. This happens in an automated fashion during the submission process. SAP uses the standard DCO text of the Linux Foundation.
Copyright (c) 2023 SAP SE or an SAP affiliate company. All rights reserved. This project is licensed under the Apache Software License, version 2.0 except as noted otherwise in the LICENSE file.