Spatial transcriptomics provides unprecedented opportunities to analyze gene expression patterns while preserving spatial tissue architecture. However, traditional deep learning methods face significant challenges in multi-modal data integration, spatial dependency modeling, and biological knowledge incorporation, while existing large language models (LLMs) lack explicit spatial modeling capabilities for transcriptomic data. To address these limitations, we present ST-LLM (Spatial Transcriptomics Embedding with Large Language Models), a novel approach that transforms complex spatial graph structures into structured textual representations suitable for LLMs through innovative prompt engineering. ST-LLM features three key components: dynamic graph adjacency construction using reinforcement learning to adaptively optimize spatial relationships, graph-to-text conversion that creates hierarchical descriptions with spatial context, and comprehensive utilization of pre-trained semantic understanding to generate high-dimensional spatial-aware embeddings. Comprehensive experiments on 14 datasets demonstrate that ST-LLM consistently outperforms state-of-the-art methods in spatial domain clustering and region detection tasks. Our framework establishes LLM embeddings as a simple yet powerful paradigm for encoding spatial transcriptomics biological knowledge, opening new avenues for computational spatial biology research.