Modern code generation tools, powered by Large Language Models (LLMs), typically rely on file-level context and often ignore structural information and dependencies distributed across an entire code repository. This limitation leads to inaccurate code suggestions, especially in real-world projects where cross-file relationships are important. To address this gap, we propose a graph-based Retrieval-Augmented Code Generation (GRACG) framework that leverages repository-level context. Our approach models the repository as a heterogeneous graph of files, classes, and functions. A Graph Neural Network (GNN) is used to generate node embeddings that incorporate information from connected nodes. These embeddings are precomputed and serve as an efficient index, allowing us to retrieve context for user queries without re-running the GNN. Retrieved nodes are then used to construct prompts for LLMs to perform repositoryaware function generation. We evaluate retrieval performance on a benchmark where the goal is to identify functions likely to be called based on a natural language description. For end-toend evaluation, we use pass@k, which measures the percentage of tasks where at least one of the top-k generated solutions passes the associated test cases. Our results show that graphbased retrieval outperforms classical methods, highlighting it as a promising direction for future research. However, in terms of end to-end code generation, we did not observe significant improvements in the metrics, even when using target-relevant functions. Importantly, the modular nature of our framework also makes it suitable as a building block in multi-agent settings, where specialized components for retrieval, generation, and verification can collaborate around repository-level knowledge.