Building the Tutor Service Layer

In the previous lesson, we explored the SessionManager struct, which plays a crucial role in managing tutoring session data within our application. Now, we will take the next step in our journey by building the Tutor Service Layer. This layer is essential for integrating the DeepSeek language model with tutoring sessions, allowing us to process student queries and generate tailored explanations. By the end of this lesson, you will understand how to set up the TutorService struct, create tutoring sessions, and process academic questions using DeepSeek models via the Rust async OpenAI client.

The service layer acts as a bridge between the model layer, where data is managed, and the AI model, which generates educational responses. It is responsible for orchestrating the flow of data and ensuring that student interactions are handled effectively. Let's dive into the details of setting up this important component.

Setting Up the TutorService Struct

The TutorService struct is the heart of our service layer. It is responsible for managing tutoring sessions and interacting with the DeepSeek model to generate educational responses. To begin, we need to set up the struct and its components.

Here is the definition of the TutorService struct, which contains a SessionManager for handling session data, a DeepSeek API client for interacting with the language model, and a system_prompt string to guide the tutor's responses:

pub struct TutorService {
    session_manager: SessionManager,
    client: Client<OpenAIConfig>,
    system_prompt: String,
}

Next, we implement the initialization logic for TutorService. This includes loading environment variables for API configuration, reading the system prompt from a file, and initializing the SessionManager and DeepSeek client.

impl TutorService {
    pub fn new() -> Self {
        dotenv::dotenv().ok();
        let api_key = env::var("OPENAI_API_KEY").expect("OPENAI_API_KEY not set");
        let base_url = env::var("OPENAI_BASE_URL").expect("OPENAI_BASE_URL not set");

        let config = OpenAIConfig::new()
            .with_api_key(api_key)
            .with_api_base(base_url);
        let client = Client::with_config(config);

        let system_prompt = fs::read_to_string("data/system_prompt.txt")
            .unwrap_or_else(|e| {
                eprintln!("Error loading system prompt: {}", e);
                "You are a helpful tutor.".to_string()
            });

        Self {
            session_manager: SessionManager::new(),
            client,
            system_prompt,
        }
    }
}

This implementation loads configuration, initializes the DeepSeek client, reads the system prompt, and constructs a new TutorService ready to manage tutoring sessions and interact with the AI model.

Creating a New Tutoring Session

Creating a new tutoring session is a fundamental task of the TutorService. The create_session method is responsible for generating a unique session ID and initializing a tutoring session using the SessionManager.

In Rust, we use the uuid crate to generate a unique session ID. We then call the create_session method of SessionManager, passing the student_id, session_id, and system_prompt. This initializes a new tutoring session, which is ready to receive student queries.

Here is the implementation:

impl TutorService {
    // ... (other methods)

    pub fn create_session(&mut self, student_id: &str) -> String {
        let session_id = Uuid::new_v4().to_string();
        self.session_manager
            .create_session(student_id, &session_id, &self.system_prompt);
        session_id
    }
}

This method generates a new UUID for the session, creates the session in the session manager, and returns the session ID.

Processing Student Queries

The process_query method is where the educational magic happens. It processes student questions, interacts with the DeepSeek model to generate tutoring explanations, and updates the session history. Below, we outline the steps involved in this process, followed by the corresponding Rust implementation:

  1. Retrieve the session using get_session, and return an error if the session is not found.
  2. Add the student's query to the session history.
  3. Send the conversation, including the system prompt and all previous exchanges, to the DeepSeek model to generate a response.
  4. Add the tutor's explanation to the session history and return it to the student.
  5. Handle any errors with the AI client gracefully.

Here's how it may look:

impl TutorService {
    // ... (other methods)

    pub async fn process_query(
        &mut self,
        student_id: &str,
        session_id: &str,
        query: &str,
    ) -> Result<String> {
        self.session_manager
            .get_session(student_id, session_id)
            .ok_or_else(|| anyhow!("Session not found"))?;
        self.session_manager
            .add_message(student_id, session_id, "user", query)?;

        let conversation = self.session_manager.get_conversation(student_id, session_id);

        let request = CreateChatCompletionRequestArgs::default()
            .model("deepseek-ai/DeepSeek-V3")
            .messages(conversation)
            .temperature(0.6)
            .max_tokens(500_u32)
            .build()?;
        let response = self.client.chat().create(request).await?;

        let tutor_response = response.choices[0]
            .message.content.as_deref().unwrap_or_default().trim().to_string();

        self.session_manager
            .add_message(student_id, session_id, "assistant", &tutor_response)?;

        Ok(tutor_response)
    }
}

In the context of a personal tutor, we configure our DeepSeek model with specific parameters to optimize its educational performance. The temperature is set to 0.6, which balances accuracy and creativity in the tutor's explanations, ensuring they are both informative and engaging. The max_tokens is set to 500, allowing the model to provide detailed educational content without overwhelming the student, thus maintaining an effective learning experience.

Example: Simulating a Tutoring Session

Let's see the TutorService in action by simulating a tutoring session. We'll create a script to initialize a tutoring session and process a student's academic query:

#[tokio::main]
async fn main() -> Result<()> {
    // Initialize the tutor service
    let mut tutor_service = TutorService::new();

    // Simulate a student ID
    let student_id = "student123";

    // Create a new tutoring session
    let session_id = tutor_service.create_session(student_id);
    println!("Tutoring session created with ID: {}", session_id);

    // Simulate sending a tutoring query
    let student_query = "Can you explain the principles of supply and demand in economics?";

    // Call process_query and handle any errors
    match tutor_service
        .process_query(student_id, &session_id, student_query)
        .await
    {
        Ok(tutor_response) => {
            println!("Tutor Response: {}", tutor_response);
        }
        Err(e) => {
            eprintln!("Error: {}", e);
        }
    }

    Ok(())
}

In this example, we initialize the TutorService, simulate a student ID, and create a new tutoring session, printing the session ID. We then simulate sending an economics question and print the tutor's response, demonstrating the flow from student query to tutoring explanation and showcasing the functionality of the TutorService.

Tutoring session created with ID: 01a17870-8a4f-4b6f-a3ce-f04e1136d597
Tutor Response: Supply and demand are fundamental principles in economics that describe how prices are determined in a market economy. Let me explain each concept and how they interact:

1. Supply: This refers to the quantity of a good or service that producers are willing and able to offer for sale at various price points. 
   - The law of supply states that as the price of a good increases, the quantity supplied also increases (and vice versa).
   - This creates an upward-sloping supply curve when plotted on a graph with price on the vertical axis and quantity on the horizontal axis.

2. Demand: This refers to the quantity of a good or service that consumers are willing and able to purchase at various price points.
   - The law of demand states that as the price of a good increases, the quantity demanded decreases (and vice versa).
   - This creates a downward-sloping demand curve on the same type of graph.

3. Market Equilibrium: This occurs at the intersection of the supply and demand curves.
   - At this point, the quantity that producers want to supply exactly equals the quantity that consumers want to buy.
   - The price at this intersection is called the equilibrium price, and the quantity is called the equilibrium quantity.

4. Price Mechanism: When markets are not in equilibrium, the price acts as a signal:
   - If price is above equilibrium, there's a surplus (excess supply), which puts downward pressure on prices.
   - If price is below equilibrium, there's a shortage (excess demand), which puts upward pressure on prices.

5. Shifts in Supply and Demand: Various factors can cause entire curves to shift:
   - Supply shifters include technology, input costs, number of sellers, and expectations.
   - Demand shifters include income, preferences, number of buyers, and expectations.

These principles help explain how markets allocate resources efficiently and how changes in market conditions affect prices and quantities.

Does this explanation help? Would you like me to elaborate on any specific aspect of supply and demand?

This output illustrates a successful tutoring interaction where a new session is created, and the AI responds to the student's economics question with a comprehensive explanation. The tutor's response demonstrates the system's ability to provide relevant, structured, and educational content, showcasing how the DeepSeek model can be effectively used for personalized academic support.

Summary and Next Steps

In this lesson, we explored the TutorService struct and its role in integrating the DeepSeek language model with tutoring sessions. We learned how to set up the struct, load the system prompt, create sessions, and process student queries. The service layer is a vital component of our personal tutor application, ensuring that student interactions are handled effectively and that educational content is delivered in a clear and engaging manner.

As you move on to the practice exercises, take the opportunity to experiment with the TutorService functionality. This hands-on practice will reinforce the concepts covered in this lesson and prepare you for the next steps in our course. Keep up the great work, and I look forward to seeing your progress!

Sign up
Join the 1M+ learners on CodeSignal
Be a part of our community of 1M+ users who develop and demonstrate their skills on CodeSignal