This paper presents our approach to the CLPsych 2025 (Tseriotou et al., 2025) shared task, where our proposed system implements a comprehensive solution using In-Context Learning (ICL) with vector similarity to retrieve relevant examples that guide Large Language Models (LLMs) without specific fine-tuning. We leverage ICL to analyze self-states and mental health indicators across three tasks. We developed a pipeline architecture using Ollama, where we are running Llama 3.3 70B locally and specialized vector databases for post- and timeline-level examples. We experimented with different numbers of retrieved examples (k=5 and k=10) to optimize performance. Our results demonstrate the effectiveness of ICL for clinical assessment tasks, particularly when dealing with limited training data in sensitive domains. The system shows strong performance across all tasks, with particular strength in capturing self-state dynamics.