Currently, the IT market is promoting the use of cloud resources to build solutions using machine learning. Some projects require full independence from external resources, mainly due to the volatility of prices for renting computing power and services provided by the cloud. The paper presents the creation process of scalable “on-premise” environment en-abling the construction and development of artificial intelligence systems in the field of natural language processing. The proposed approach was based on aspects related to containerization, scalability, and automation of the machine learning process. Therefore, the created “on-premise” environment can be used in the implementation and delivery of systems based on artificial intelligence.

Conversational Information Seeking (CIS) is an emerging area of Information Retrieval focused on interactive search systems. As a result there is a need for new benchmark datasets and tools to enable their creation. In this demo we present the Agent Dialogue (AD) platform, an open-source system developed for researchers to perform Wizard-of-Oz CIS experiments. AD is a scalable cloud-native platform developed with Docker and Kubernetes with a flexible and modular micro-service architecture built on production-grade state-of-the-art open-source tools (Kubernetes, gRPC streaming, React, and Firebase). It supports varied front-ends and has the ability to interface with multiple existing agent systems, including Google Assistant and open-source search libraries. It includes support for centralized structure logging as well as offline relevance annotation.