LogoLogo
  • E.D.D.I Documentation
  • Getting started
  • Your first bot
    • Understanding your first bot
  • Bot Manager GUI
  • Creating your first Chatbots
    • Create a "Hello World" bot
    • Create a bot that reacts to user inputs
  • Import/Export a Chatbot
  • Managed Bots
  • Deployement management of Chatbots
  • Extensions
  • Behavior Rules
  • HttpCalls
  • Langchain
  • Output Configuration
  • Conversations
  • Passing context information
  • Output Templating
  • Semantic Parser
  • Git support
  • Docker
  • Setting Up EDDI on AWS with MongoDB Atlas
  • RedHat Openshift
  • Metrics
  • FAQs
Powered by GitBook
On this page

Was this helpful?

Export as PDF

E.D.D.I Documentation

Prompt & Conversation Management Middleware for Conversational AI APIs. Developed in Java, powered by Quarkus, provided with Docker, and orchestrated with Kubernetes or Openshift.

NextGetting started

Last updated 9 months ago

Was this helpful?

E.D.D.I (Enhanced Dialog Driven Interface) is a middleware to connect and manage LLM API bots with advanced prompt and conversation management for APIs such as OpenAI ChatGPT, Facebook Hugging Face, Anthropic Claude, Google Gemini and Ollama

Developed in Java using Quarkus, it is lean, RESTful, scalable, and cloud-native. It comes as Docker container and can be orchestrated with Kubernetes or Openshift. The Docker image has been certified by IBM/Red Hat.

Latest stable version: 5.3.3

License: Apache License 2.0

Project website:

alt text

Intro

E.D.D.I is a high performance middleware for managing conversations in AI-driven applications. It is designed to run efficiently in cloud environments such as Docker, Kubernetes, and Openshift. E.D.D.I offers seamless API integration capabilities, allowing easy connection with various conversational services or traditional REST APIs with runtime configurations. It supports the integration of multiple chatbots, even multiple versions of the same bot, for smooth upgrading and transitions.

Notable features include:

  • Seamless integration with conversational or traditional REST APIs

  • Configurable NLP and Behavior rules to orchestrate LLM involvement

  • Support for multiple chatbots, including multiple versions of the same bot, running concurrently

  • Support for Major AI API integrations via langchain4j: OpenAI, Hugging Face (text only), Claude, Gemini, Ollama (and more to come)

Technical specifications:

  • Resource-/REST-oriented architecture

  • Java Quarkus framework

  • JAX-RS

  • Dependency Injection

  • Prometheus integration (Metrics endpoint)

  • Kubernetes integration (Liveness/Readiness endpoint)

  • MongoDB for storing bot configurations and conversation logs

  • OAuth 2.0 (Keycloak) for authentication and user management

  • HTML, CSS, Javascript (Dashboard)

  • React (Basic Chat UI)

here