Building the Chat Manager with Ruby

Welcome back! In the previous lesson, we explored the importance of a robust system prompt and how it guides the behavior of our chatbot. Now, we will delve into the next step of our journey: building the Chat Manager. This lesson will focus on the model layer of the MVC (Model-View-Controller) architecture, which is crucial for organizing and managing data in a structured way. The ChatManager class will be the core component of our model layer, responsible for managing chat data effectively. By the end of this lesson, you will understand how to create, manage, and retrieve chat data using the ChatManager class.

The ChatManager class is designed to handle the storage and management of chat data. It serves as the backbone of our chatbot's data management system. We'll start by setting up the class and then gradually add methods to handle chat creation, message addition, and conversation retrieval.

Let's begin by defining the ChatManager class and its initialize method. The initialize method sets up an empty hash, @chats, which will store all chat data.

class ChatManager
  def initialize
    @chats = {}  # user_id => { chat_id => chat_data }
  end
end

In this setup, @chats is a nested hash where the first key is the user_id, and the second key is the chat_id. This structure allows us to efficiently manage multiple chats for different users.

Next, we'll add the create_chat method. This method is responsible for creating a new chat entry for a user. It takes three parameters: user_id, chat_id, and system_prompt.

class ChatManager
  def initialize
    @chats = {}
  end

  def create_chat(user_id, chat_id, system_prompt)
    @chats[user_id] ||= {}
    @chats[user_id][chat_id] = {
      'system_prompt' => system_prompt,
      'messages' => []
    }
  end
end

The create_chat method checks if the user_id exists in @chats. If not, it creates a new entry. Then, it initializes the chat with the provided system_prompt and an empty array for messages.

To access a specific chat, we need the get_chat method. This method retrieves a chat based on the user_id and chat_id.

def get_chat(user_id, chat_id)
  @chats.dig(user_id, chat_id)
end

The get_chat method uses the dig method to safely access the nested hash, returning the chat data if it exists.

This use of dig avoids runtime errors from trying to access keys that don't exist, making your code more robust and eliminating the need for multiple nested nil checks. However, if chat retrieval fails frequently, it may indicate a problem elsewhere—such as improper chat initialization—so logging these cases can aid in debugging.

Now, let's add the add_message method. This method allows us to append messages to a chat. It requires the user_id, chat_id, role, and content of the message.

def add_message(user_id, chat_id, role, content)
  if chat = get_chat(user_id, chat_id)
    chat['messages'] << { "role" => role, "content" => content }
  end
end

The add_message method first retrieves the chat using get_chat. If the chat exists, it appends the message to the chat's message array.

Finally, we'll implement the get_conversation method. This method returns the entire conversation, including the system prompt and all messages.

def get_conversation(user_id, chat_id)
  if chat = get_chat(user_id, chat_id)
    system_message = { "role" => "system", "content" => chat['system_prompt'] }
    [system_message] + chat['messages']
  else
    []
  end
end

The get_conversation method retrieves the chat and constructs an array starting with the system prompt, followed by the chat messages. If the chat does not exist, it returns an empty array. This method constructs a new array each time it's called, which is ideal for ensuring immutability of the internal data. However, if performance becomes a concern in high-frequency use cases, caching the result or storing precompiled conversation arrays might offer optimization at the cost of added complexity.

To create a new chat, we use the create_chat method. This method takes three parameters: user_id, chat_id, and system_prompt. It initializes a new chat entry in the @chats hash. If the user_id does not already exist in the hash, a new entry is created. The chat entry includes the system prompt and an empty array for messages.

Here's an example of how to create a new chat:

def load_system_prompt
  begin
    File.read('data/system_prompt.txt')
  rescue => e
    puts "Error loading system prompt: #{e}"
    "You are a helpful assistant."
  end
end

# Load the system prompt
system_prompt = load_system_prompt

# Initialize manager
manager = ChatManager.new

# Create a new chat
user_id = "user123"
chat_id = "chat123"
manager.create_chat(user_id, chat_id, system_prompt)

In this example, we initialize a ChatManager instance and create a new chat for a user with the ID "user123". The chat is identified by "chat123" and is initialized with a system prompt. This setup allows us to manage chat data efficiently.

Once a chat is created, we can add messages to it using the add_message method. This method requires the user_id, chat_id, role, and content of the message. The role indicates whether the message is from the user or the assistant. The message is then appended to the chat's message array.

Here's how you can add messages to a chat:

# Add some messages
manager.add_message(user_id, chat_id, "user", "Hello!")
manager.add_message(user_id, chat_id, "assistant", "Hi there!")

In this example, we add a user message, "Hello!", and an assistant response, "Hi there!", to the chat. The add_message method ensures that messages are stored in the correct chat entry.

To retrieve the entire conversation, including the system prompt, we use the get_conversation method. This method returns an array of messages, starting with the system prompt followed by the chat messages.

# Get chat history
conversation = manager.get_conversation(user_id, chat_id)

The get_conversation method compiles the chat history, allowing us to access the full context of the conversation.

In this lesson, we explored the ChatManager class and its role in managing chat data within the model layer of our application. We learned how to create and manage chats, add messages, and retrieve chat histories. The ChatManager is a crucial component for organizing chat data, ensuring that our chatbot can handle multiple conversations efficiently.

As you move on to the practice exercises, take the opportunity to experiment with modifying and extending the ChatManager 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!