Search engine acts as an interface between users and computers. Online search is a very quick and impactful evolution of human experience. It is becoming a key technology that people rely on every day to get information about almost everything. Searching is typically performed with a common purpose underlying the query. If the user does not know the knowledge of the keywords to be searched, spends more time to frame the query. The search may not contain the user’s intended answers. Understanding the meaning of the query given by the user is the important role of the search engine. The query auto-completion feature is important for search engines. The query auto-completion process occurs uninterruptedly, dynamically listing terms with each click. It provides recommendations that facilitate query formulation and improve the relevancy of the search. Graphs and additional data structures are used frequently in computer science and related fields. The applications of graph machine learning include data recovery, friendship recommendation, and social networking. Heterogeneous graphs (HGs) consist of different kinds of nodes and links, and are useful for defining a wide range of complicated real-world systems a robust graph neural architecture for encoding a knowledge graph is the Relational Graph Convolutional Network (R-GCN).The proposed model uses the supervised Relational Graph Convolutional Network(R-GCN), Long Short-Term Memory (LSTM) for completion of the query. The model predicts the object given the subject and predicate and the accuracy is 92.4%.