Performing prior art searches is an essential step in both patent drafting and invalidation. The task is challenging due to the large number of existing patent documents and the domain knowledge required to analyze the documents. We present a graph-based patent search engine that tries to mimic the work done by a professional patent examiner. Each patent document is converted to a graph that describes the parts of the invention and the relations between the parts. The search engine is powered by a graph neural network that learns to find prior art by using novelty citation data from patent office search reports where citations are compiled by human patent examiners. We show that a graph-based approach is an efficient way to perform searches on technical documents and demonstrate it in the context of patent searching.