GenAI threads

This section highlights the various features provided by the GenAI product.

The GenAI capabilities are divided into three main threads:

  • GenAI Embedded Experience: Exposing the Generative AI capabilities such as text generation, summarization, translation and text analysis features by embedding them into the application screens or exposing through widgets. These capabilities are available:
    • Use the Prompt Catalog within the GenAI Platform part of Infor OS to test differences in response from our supported models.
    • Use the GenAI suite within API Gateway. The suite provides application programming interfaces such as:
      • Getting the list of the LLMs
      • Accessing the LLMs
      • CRUD operation on Conversation Starter for the GenAI Assistant
  • Infor GenAI Assistant: conversational UX powered by LLM allowing to retrieve the knowledge from multiple sources using natural language.

    • Use Factory in the GenAI Platform to create agents and tools.

    • Use Chat in the GenAI Platform to test agents and tools.

    • Use Evaluation to run automated tests for agents.

  • GenAI Knowledge Hub: The GenAI Assistant capability of retrieving the knowledge from unstructured documents such as user guide, integration guide and more.

Application

With GenAI, you can test and validate the prompt you intend to send to Large Language Models (LLMs).

GenAI is also intended to create, test and manage the GenAI Assistant agents and tools. The GenAI includes these menu options:

  • Prompt Catalog: To create the GenAI prompt and test and validate it across up to three different LLMs.
  • Chat: To test and validate created GenAI tools meant for the chatbot.
  • Factory: To create and manage agents and tools.
  • Custom Guardrails: to configure the moderation criteria
  • Evaluation: to create the automated testing for the GenAI Assistant and GenAI Embedded Experience
  • Focus Mode: specify the Focus Mode to limit the conversation with with GenAI Assistant to limited set of sub-agents.
  • Conversation Starters: create the prompts that guide users on what to ask when chatting with the GenAI Assistant.
  • System Configuration: To opt out from sending any tracing data

GenAI API Suite

Features and capabilities within the GenAI user interface and beyond that are also available with corresponding RESTful APIs for programmatic development.

These APIs are useful in facilitating these scenarios:

  • Get list of LLMs.
  • Get the completion back from the LLM
  • Create, retrieve, update, or delete Conversation Starter from the GenAI Assistant

This table shows a few of the primary GenAI APIs available for each service endpoint:

Endpoints Description
GenAiCoreService
  • /api/v1/tools (GET) to retrieve a full list of Tools available on the tenant
  • /api/v1/tools (PUT) to update the parameters of an existing Tool
  • /api/v1/tools (POST) to add a new Tool
  • /api/v1/tools/{tool_guid} (GET) to retrieve a specific Tool
  • /api/v1/tools/{tool_guid} (DELETE) to delete a specific Tool
GENAI/chatsvc
  • /api/v1/chat for a prompt with Tools to be submitted to the LLM
  • /api/v2/chat for a prompt with Tools to be submitted to the LLM and getting a streaming response (applicable for Deep Agents)
  • /info to retrieve more application details
  • /api/v1/sessions/{session_id} to delete a session history
GENAI/coresvc
  • /api/v1/suggestions (GET) to retrieve all existing Conversation Starters
  • /api/v1/suggestions (POST) to create a new Conversation Starter
  • /api/v1/suggestions/{suggestion_id} (PUT) to edit an existing Conversation Starter
  • /api/v1/suggestions/{suggestion_id} (PUT) to delete an existing Conversation Starter
GENAI/llmsvc

(previously resided in GENAI/chatsvc)
  • /api/v1/embeddings (POST) to transform text into numerical vectors that capture semantic meaning, which enables similarity search and retrieval for RAG applications using the Titan Text Embeddings V2 model
  • /api/v1/prompt for a single prompt to be submitted to the LLM
  • /api/v1/messages for sending multiple messages to the LLM
  • /api/v1/prompt/stream for a single prompt to be submitted to the LLM and getting response as a stream
  • /api/v1/messages/stream for sending multiple messages to the LLM and getting a response as a stream
  • /api/v2/messages for sending multiple messages to the LLM with additional function calling capabilities
  • /api/v2/messages/stream for sending multiple messages to the LLM with additional function calling capabilities and getting a response as a stream
  • /api/v1/models for a list that provides details on all supported LLMs in the GenAI Assistant

GenAI Assistant

GenAI Assistant is a conversational interface powered by a large language model, designed for interactive dialogue.

It allows users to engage in natural language conversations. The GenAI Assistant can retrieve information from a variety of sources, including documentation and industrial data. This makes it a versatile tool for accessing diverse types of information. By leveraging advanced AI, it provides accurate and relevant responses to user queries.

IDM GenAI Feature flag

In order to expose documents through the GenAI Assistant chat interface in IDM, an administrator can define the document type for which the documents must be exposed via the GenAI Assistant conversational UX.