The paper introduces the Healthcare Copilot, a framework designed to enhance the capabilities of general large language models (LLMs) for medical consultations. The copilot framework aims to tailor LLMs for specific complex tasks without requiring fine-tuning. The Healthcare Copilot consists of three main components: Dialogue, Memory, and Processing. The Dialogue component facilitates safe and effective interactions with patients, the Memory component stores current and historical conversation data, and the Processing component summarizes the entire dialogue and generates reports. The paper evaluates the Healthcare Copilot using an auto-evaluation scheme with ChatGPT, demonstrating significant improvements in inquiry capability, conversational fluency, response accuracy, and safety. Ablation studies highlight the effectiveness of each component. The main contributions include the pioneering use of copilot frameworks to enhance LLMs for medical consultations and the detailed modular design of the Healthcare Copilot. The paper also discusses limitations and ethical considerations, emphasizing the need for further clinical validation and the cautious use of generated information.The paper introduces the Healthcare Copilot, a framework designed to enhance the capabilities of general large language models (LLMs) for medical consultations. The copilot framework aims to tailor LLMs for specific complex tasks without requiring fine-tuning. The Healthcare Copilot consists of three main components: Dialogue, Memory, and Processing. The Dialogue component facilitates safe and effective interactions with patients, the Memory component stores current and historical conversation data, and the Processing component summarizes the entire dialogue and generates reports. The paper evaluates the Healthcare Copilot using an auto-evaluation scheme with ChatGPT, demonstrating significant improvements in inquiry capability, conversational fluency, response accuracy, and safety. Ablation studies highlight the effectiveness of each component. The main contributions include the pioneering use of copilot frameworks to enhance LLMs for medical consultations and the detailed modular design of the Healthcare Copilot. The paper also discusses limitations and ethical considerations, emphasizing the need for further clinical validation and the cautious use of generated information.