Katecheo: A Portable and Modular System for Multi-Topic Question Answering
This system addresses the need for a flexible and deployable question-answering tool that can be extended to various domains without requiring model training or code modifications, though it is incremental as it builds on existing modular and open-source approaches.
The authors tackled the problem of building a portable and modular system for multi-topic question answering by introducing Katecheo, which enables question identification, topic classification, document search, and reading comprehension via a REST API on Kubernetes clusters, using publicly available knowledge base articles from Stack Exchange sites.
We introduce a modular system that can be deployed on any Kubernetes cluster for question answering via REST API. This system, called Katecheo, includes three configurable modules that collectively enable identification of questions, classification of those questions into topics, document search, and reading comprehension. We demonstrate the system using publicly available knowledge base articles extracted from Stack Exchange sites. However, users can extend the system to any number of topics, or domains, without the need to modify any of the model serving code or train their own models. All components of the system are open source and available under a permissive Apache 2 License.