LogoLogo
Home
Core Platform
Core Platform
  • Introduction
    • Overview
    • Use Cases
    • Architecture
    • Built with ML & AI
    • Quick Start
  • Examples
    • Training Examples
      • API Flow Examples
      • Microservice Examples
      • UI Example
      • Exercise: Hello World API
      • Exercise: Test State
      • Exercise: Test UI
    • Exercise: To-do List
      • To-do List Runner
      • To-do List Gateway
      • To-do List UI
      • To-do List Query
  • Troubleshooting
    • Rierino Packages
    • Release Notes
    • Useful Checks
    • Error Codes
  • Devops
    • Overview
    • API Flows
      • Using the Saga Screen
      • Defining a Saga
      • Configuring Saga Steps
        • Event Step
        • Transform Step
          • Transform Classes
        • Condition Step
          • Condition Classes
        • Step Link
      • Injecting Variables
    • Microservices
      • Runners
        • Using the Runner Screen
        • Defining a Runner
        • Managing Runner Settings
        • Adding Runner Elements
        • Deploying Runners
          • Spring Runners
          • Samza Runners
          • Camel Runners
      • Elements
        • Systems
        • State Managers
          • Typical Use Cases
          • State Data Structure
          • Local States
            • In-Memory Map
            • Caffeine Cache
            • Samza Based
            • Lucene Based
            • Single File
            • Multiple Files
            • Selected IDs Map
            • Indexed Map
          • Shared States
            • MongoDB Collection
            • Jooq (SQL) Table
            • Redis Map
            • Couchbase Collection
            • Elasticsearch Index
            • Elasticsearch Joined
            • Etcd Namespace
          • Specialized States
            • CRUD Service
            • Odata Service
          • State Coordinators
            • Lazy Cache Coordinator
            • Event Store Coordinator
            • Write thru Coordinator
          • Loading Strategies
          • ID Generators
        • Listeners
        • Query Managers
          • MongoDB
          • Elasticsearch
          • Lucene
          • SQL Based
          • Odata Service
        • Handlers
          • Core Handlers
            • Write Data
            • Read Data
            • Query Data
            • Apply Rules
            • Call Rest API
            • Generate Text/Html
            • Parse Html
            • Generate Secrets
            • Orchestrate User Task
            • Perform File Operation
            • Run Shell Command
            • Send/Receive Emails
          • Custom Code Handlers
            • Run Scripts
            • Run Java Code
            • Run Java Package
          • Flow Handlers
            • Orchestrate Saga
            • Loop Each Entry
            • Run Multiple Steps
            • Buffer Payloads
            • Merge Parallel Steps
            • Log Event
            • Send Event
            • Validate Event
            • Transform Event
            • Perform DB Transaction
            • Trigger Runner Command
            • Do Nothing
            • Modify Role Data
            • Enrich Role Data
            • Convert Pulse to Journal
          • Gateway Handlers
            • Authenticate
              • No Authentication
              • State Based
              • Keycloak Based
            • Sessionize
          • Specialized Handlers
            • Apply Advanced Rules
            • Calculate Real-time Metrics
            • Score ML Models
            • Score LangChain Models
            • Service MCP Requests
            • Service A2A Requests
            • Consume Web of Things
            • Perform Text Embedding
            • Run Python Procedure
            • Generate Excel
            • Generate PDF
            • Call SOAP API
            • Integrate with Camel
        • Actions
        • Streams
          • Kafka Topic
          • CDC Feed
          • Camel Component
        • Roles
        • Generic Settings
        • Global Settings
      • Deployments
        • Defining a Deployment
        • Alternative Loaders
    • Gateway & Security
      • Gateway Servers
        • Gateway Systems
        • Gateway Channels
        • Gateway Services
        • Gateway Tokens
      • APIs
        • OpenAPI Specification
        • Response Formats
    • Administration
      • Managing Deployments
      • Sending Commands
      • Streaming Messages
      • Migrating Assets
    • Batch Tasks
      • Python Processes
      • Python Iterators
      • Python Processors
    • Pro-Code
      • Custom Handlers
      • Custom State Managers
      • Custom Query Managers
      • Custom CDC Managers
  • Design
    • Overview
    • User Interface
      • Apps
      • UIs
        • Listers
        • Widgets
          • Value Widgets
          • Array Widgets
          • Object Widgets
          • Indirect Widgets
          • Atom Widgets
        • Menus
          • Lister Menu Actions
          • Selection Menu Actions
          • Editor Menu Actions
          • Widget Menu Actions
          • Custom Menu Actions
          • RAI Menu Actions
        • Extended Scope
          • Conditional Display
          • Data Context
          • Extra Data
          • Default Item
          • Extra Events
      • Options
      • Translations
      • Icons
      • Styles
      • Components
    • API Mapping
    • Data Schema
      • Common Data
  • Configuration
    • Overview
    • Queries
      • Query Types
      • Query Platforms
        • MongoDB Queries
        • Odata Queries
        • SQL Queries
        • Elasticsearch Queries
        • Lucene Queries
        • Siddhi Queries
    • Business Rules
      • Drools Rules
    • Dynamic Handlers
  • Data Science
    • Overview
    • ML Models
      • Scheduler Platforms
        • Airflow Scheduler
    • GenAI Models
      • AI Agent APIs
      • Useful Checks
    • MCP Servers
    • Complex Event Processing
      • Siddhi Data Flows
    • Data Visualizations
    • Customizations
  • EXTENSIONS
    • JMESPath
    • Handlebars
Powered by GitBook

© Rierino Software Inc. 2025. All rights reserved.

On this page
  • Definition
  • Model
  • Toolkit
  • Prompts
  • Comments
  1. Data Science

GenAI Models

In addition to general ML models, Rierino provides facility for governing LLM models for GenAI use cases

PreviousAirflow SchedulerNextAI Agent APIs

Last updated 11 hours ago

GenAI model definitions allow configuration of AI agents and general purpose LangChain models using different providers such as Amazon Bedrock, Anthropic, Azure, Google Gemini, Mistral, OpenAI, as well as local LLM models.

To enable use of AI agents on a runner, you can simply add GenAI base runner to its configuration, set your API Keys for your preferred LLM provider in secrets and start allowing specific GenAI models to be executed on that runner.

Using AI agents on a runner increases its memory requirements, with minimum requirement becoming 1024mb.

To keep out of box runners lightweight, GenAI base runner is not added to them by default (even for core and training runners), which can be added after initial installation as preferred.

It is recommended to keep AI agents running on dedicated runners, if possible, as they can increase build time and consume more resources than the rest of event handlers on the runner.

All agents generated using this approach can be governed by RBAC and corporate governance rules, based on access rights of the users interacting with the agents.

Initial definition of a GenAI model includes 4 main tabs:

Definition

  • Name: A descriptive name

  • Version: Current version of the model

  • Domain: Business domain for grouping of the model

  • Allowed For: List of runners which can provide the AI agent

  • Tags: Descriptive tags for the model

  • Status: Whether this model should be deployed or not

  • Instructions: Instructions to send to agent for its initialization (such as main purpose and persona)

Model

  • Provider: LLM provider that will be used by the agent

  • Memory Name: State manager which will be used as the chat memory by the agent (distributed states for distributed agents)

  • Memory Size: Maximum memory size to be kept for chat history

  • Parameters: Model level parameters specific to LLM provider, including sagas that are allowed access for the AI agents as tools

Toolkit

  • Tool Sagas: List of sagas that can be executed by the agent for custom business flows & logic, which allows agents to have access to all capabilities available within Rierino

  • Tool States: List of state managers that the agent is allowed to use for read and/or write operations (individual actions such as Delete can be also disabled)

  • Tool Systems: External systems that the agent is allowed to interact with, automatically discovering endpoints from Open API specification of the target system and using already configured authentication logic

  • Tool Scripts: List of programming languages the agent is allowed to use for creating custom scripts and executing them on the fly (such as for data transformations or calculations)

Prompts

  • ID: Unique identifier of the prompt used when calling AI agent

  • Name: Descriptive name of the prompt

  • Description: Detailed description of the prompt and its use cases

  • Template: Handlebars template for producing prompt with given structured inputs

Comments

List of comments for reference to model capabilities or changes over time.

GenAI Model UI