For most knowledge bases, there is a vast amount of document content to communicate with human readers for sharing knowledge. Making the document content accessible to users via conversational systems could be a meaningful yet challenging task. To effectively improve the accuracy of information retrieval and response generation, our team proposed a pipeline system of “retrieve, re-rank, and generate” for handling users’ information-seeking queries. This conversational chatbot can help users to search for information from massive contents ranging from encyclopedias to public policies.