Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsistent objects. We present BlenderRAG, a retrieval-augmented generation system that operates on a curated multimodal dataset of 500 expert-validated examples (text, code, image) across 50 object categories. By retrieving semantically similar examples during generation, BlenderRAG improves compilation success rates from 40.8% to 70.0% and semantic normalized alignment from 0.41 to 0.77 (CLIP similarity) across four state-of-the-art LLMs, without requiring fine-tuning or specialized hardware, making it immediately accessible for deployment. The dataset and code will be available at https://github.com/MaxRondelli/BlenderRAG.

翻译：从自然语言自动生成可执行的Blender代码仍具挑战性，最先进的LLM常产生语法错误和几何不一致的物体。我们提出BlenderRAG，一种检索增强生成系统，基于包含50个物体类别、500个专家验证样本（文本、代码、图像）的精选多模态数据集运行。通过在生成过程中检索语义相似示例，BlenderRAG在不需微调或专用硬件的情况下，将四个最先进LLM的编译成功率从40.8%提升至70.0%，语义归一化对齐度（CLIP相似性）从0.41提升至0.77，使其可直接部署使用。数据集和代码将发布于 https://github.com/MaxRondelli/BlenderRAG。