High Performance, In-Memory Chatbot Platform. Build multiple Chatbots with NLP, Behavior Rules, API Connector, Templating.
v4.7.0 - LATEST
v4.6.0 - STABLE
License: Apache License 2.0
Visit https://eddi.labs.ai for further references.
For professional support, check out: https://www.labs.ai
Check out the full documentation here.
- it is open source 💚
- the configuration is extremely open and flexible
- the code is self-explanatory and easy to extend
- eddi is channel independent, therefore can be used anywhere
- the (NLP) parser is extremely cool
- the framework is focused and does not pretend to be the magic bullet that solves it all
- great tech stack, when you want to build a chatbot product yourself
The Chatbot System - E.D.D.I (Enhanced Dialog Driven Intelligence), has been developed with the focus on the use in enterprise applications as well as the ease of connecting it to other resources (such as databases or other Services).
This platform has been developed for over many years and completely restructured from scratch four times because of logical "dead ends" in the art of building chatbots - thus version 4.
The most outstanding features are:
- Flexible in NLP and Behavior
- Fluently connect to REST APIs
- Powerful Templating
- Reuse Conversation Flows in multiple bots
technical spec:
- Resource- / REST-oriented architecture
- OAuth 2.0 / Basic Authentication
- Java
- JAX-RS
- Dependency Injection
- Embedded Jetty
- NoSQL
- HTML, CSS, Javascript, JSON
- Java 12
- Maven 3
Go to the root directory and execute
mvn clean install
- Setup a local mongodb (> v3.0)
- launch with VM options
-DEDDI_ENV=[development/production] -Duser.dir=[LOCAL_PATH_TO_EDDI]\apiserver ai.labs.api.ApiServer
- Go to Browser --> http://localhost:7070
Note: If running locally inside an IDE you need lombok to be enabled (otherwise you will get compile errors complaining about missing constructors). Either download as plugin (e.g. inside Intellij) or follow instructions here https://projectlombok.org/
For development, use
docker-compose -f docker-compose.yml -f docker-compose.local.yml up
after running mvn package
. This builds a local image of EDDI.
For integration testing run
./integration-tests.sh
or
docker-compose -f docker-compose.yml -f docker-compose.local.yml -f docker-compose.testing.yml -p ci up -d
For running in cloud (with authentication), check: https://hub.docker.com/r/labsai/eddi