In this paper we describe the use of Personalised PageRank (PPR) to generate recommendations from a large collection of cultural heritage items. Various methods for computing item-to-item similarities are investigated, together with representing the collection as a network over which random walks can be taken. The network can represent similarity between item metadata, item co-occurrences in search logs, and the similarity of items based on linking them to Wikipedia articles and categories. To evaluate the use of PPR, search logs from Europeana are used to simulate user interactions. PPR on each information source is compared to a standard retrieval-based baseline, resulting in higher performance.