Welcome back! Building on your previous experience with the OpenAI SDK, this course will guide you in developing a RESTful API for a Personal Tutor using FastAPI. In this lesson, we begin by crafting a robust system prompt that provides the DeepSeek model with clear guidelines and ample context for effective educational interactions. You'll learn how to store this prompt in a file and seamlessly load it into your code, setting the foundation for a well-structured tutoring service.

A robust system prompt is essential for guiding the behavior of an AI tutor, especially when it functions as a personal educational assistant. The system prompt serves as the foundation for the tutor's interactions, providing it with the necessary guidelines and context to perform its role effectively. For a personal tutor, the system prompt should include specific information about its educational expertise, tutoring approach, ethical guidelines, and the expected behavior when interacting with students. This ensures that the tutor can provide accurate and helpful responses, maintain an appropriate demeanor, and adhere to educational best practices.

Key elements of a system prompt for a personal tutor:

1. Role Definition: Clearly define the role of the AI as a personal tutor. This helps the model understand its primary function and the context in which it operates.

2. Expertise & Subjects: Provide essential details about the tutor's knowledge domains and academic subjects. This gives the tutor a comprehensive understanding of its capabilities, enabling it to accurately answer questions across various fields like mathematics, science, and humanities.

3. Tutoring Approach: Establish clear guidelines for how the tutor should interact with students to ensure a consistent and effective educational style. This includes setting expectations for explanations, guidance methods, and pedagogical techniques to maintain clarity, engagement, and student-centered learning.

4. Ethical & Educational Guidelines: Define the limitations and rules that the tutor must adhere to during interactions. This ensures compliance with academic integrity and educational best practices, such as avoiding direct exam answers and promoting independent learning.

5. Additional Instructions: Outline specific procedural expectations for the tutor to ensure effective educational interactions. This includes guidance on assessing student knowledge levels, providing step-by-step explanations, and offering alternative methods when appropriate.

By incorporating these elements into the system prompt, we can ensure that the tutor behaves consistently and aligns with high educational standards.

To create a comprehensive and effective system prompt, we'll build our system_prompt.txt file step by step. By storing the system prompt in a text file, we can easily load it into our code, ensuring that our tutoring AI is well-prepared to handle student interactions efficiently.

We'll use a markdown format to structure our prompt. This format provides a clear and organized way to present the information, enhancing readability and making it easier to manage and update the prompt as needed. By organizing the prompt into distinct sections, we ensure that each component effectively guides the tutor's behavior and capabilities.

It's important to be aware of the input size limitations of the model you are working with. Models like DeepSeek V3 have a maximum input size, which includes both the system prompt and the user's input. If the system prompt is too lengthy, it might limit the amount of user input that can be processed in a single interaction. Therefore, it's crucial to strike a balance between providing enough context for the tutor to function effectively and keeping the prompt concise to ensure efficient processing. This helps maintain a smooth and responsive interaction with students.

Let's delve into each section of the system prompt to understand how it shapes the tutor's role and interactions.

The role section is the starting point of the system prompt. It defines the tutor's identity and primary function. By specifying that the AI is an expert tutor designed to inspire curiosity and empower students, we provide it with a clear understanding of its responsibilities and the context in which it operates. This foundational information helps the tutor align its responses with educational objectives.

Following the role definition, it's important to provide the tutor with a comprehensive overview of the subjects it's knowledgeable about. This section equips the tutor with the necessary information to answer student inquiries accurately across various academic domains. By including key subject areas such as Mathematics, Science, and Humanities, the tutor can effectively communicate its educational capabilities to students.

Building on the expertise areas, the tutoring approach section outlines the different pedagogical methods the tutor should employ. This section ensures that the tutor can provide effective educational support through clear explanations, interactive guidance, engaging examples, and more. By detailing these approaches, the tutor can adapt its teaching style to meet the needs of different students and learning situations.

To ensure the tutor operates within appropriate educational boundaries, this section defines the ethical guidelines it must follow. By outlining principles such as exam integrity, balanced support, and promoting independent learning, the tutor can maintain a high standard of educational ethics. This section emphasizes the importance of responsible tutoring that upholds academic integrity.

Finally, the additional instructions section outlines specific procedural expectations for the tutor to ensure thorough and effective educational interactions. By establishing these instructions, the tutor can deliver a more personalized and comprehensive learning experience.

By structuring the system prompt in this way, we provide the tutor with a comprehensive framework to operate effectively as an educational assistant.

Now that we understand the structure of a system prompt, let's see how to load it into our Python code. We will create a load_system_prompt function that accepts a file path as an argument. This function will read the system prompt from the specified file and return its content. If an error occurs while reading the file, a default prompt will be returned instead.

Here's the code for the load_system_prompt function:

This function uses a try-except block to handle potential errors, such as the file not being found. If the file is successfully read, its content is returned. Otherwise, an error message is printed, and a default prompt is used.

To utilize this function, we load the system prompt into our code by passing the file path as follows:

By loading the system prompt, we ensure that our tutor is equipped with the necessary context and guidelines to interact effectively with students.

With the system prompt loaded, we can now integrate it with the DeepSeek model using the OpenAI SDK to create a tutoring conversation. The send_query function is responsible for sending a message to the DeepSeek model and receiving a response. It uses the loaded system prompt as part of the conversation context. To demonstrate this, let's create a simple tutoring session using the system prompt and a student question:

In this example, the tutor uses the system prompt to understand its role and respond appropriately to the student's question. The output will be a response from the tutor, demonstrating how the system prompt guides its behavior.

Upon executing the test, the tutor utilizes the system prompt to generate a response. This example illustrates how the system prompt effectively guides the tutor's interaction with the student:

This response showcases the tutor's ability to provide detailed and relevant educational information based on the system prompt, ensuring a consistent and informative learning experience. Notice how the tutor:

• Breaks down the complex topic into manageable parts
• Uses clear explanations for each concept
• Provides examples to illustrate key points
• Ends with a question to assess the student's understanding

These behaviors directly reflect the guidelines provided in the system prompt.

In this lesson, we explored the concept of system prompts and their importance in guiding AI tutor behavior. We examined the structure of a system prompt, learned how to load it into Python, and created a tutoring conversation using the DeepSeek model. These foundational skills are crucial as we continue to build more complex components of our personal tutor service.

As you move on to the practice exercises, take the opportunity to experiment with modifying the system prompt and observe how it affects the tutor's responses. This hands-on practice will reinforce the concepts covered in this lesson and prepare you for the next steps in our course.