Natural language is gaining more and more relevance as an interface between man and machine. Already today, we are able to carry out simple task by talking to our smartphone or smart speaker, like Google Home or Alexa. An important challenge for any kind of dialog agent or chatbot is to include external knowledge into the conversation with the user. Therefore, such systems need to be able to interact with resources like relational databases or unstructured resources, like search engines. However, the complexity of natural language makes it hard to capture diverse utterances with a set pre-defined rules. Instead, we present an approach that leverages Deep Learning to learn how to query an Elasticsearch given natural language questions. As our model learns to follow the inherent logic of querying, it is even possible to switch to other systems and query languages. This carries a great potential for future applications of Elasticsearch and related NoSQL solutions.