Welcome to the third lesson of our course on building an image generation service with FastAPI! In our previous lessons, we created the PromptManager to format user inputs into detailed prompts and the ImageManager to handle storing and processing generated images. Now, we're ready to build the core component that brings everything together: the ImageGeneratorService.

The ImageGeneratorService is the central piece of our application that will:

1. Connect to Google's Gemini API to generate images
2. Use our PromptManager to format user inputs into effective prompts
3. Store generated images using our ImageManager
4. Provide access to all previously generated images

This service acts as the bridge between our application's components and the external AI service that actually creates the images. By encapsulating all the image generation logic in a dedicated service class, we maintain a clean separation of concerns in our application architecture.

In this lesson, we'll implement this service step by step, from setting up the API client to handling responses and errors. By the end, you'll have a fully functional image generation service that you can later integrate into a FastAPI web application.

Before we can generate images, we need to set up a client to communicate with Google's Gemini API. The Gemini API provides access to Google's powerful image generation models, allowing us to create high-quality images from text prompts.

First, we need to install the Google Generative AI library. In a typical development environment, you would run:

Remember that in the CodeSignal environment, this library is already installed, so you won't need to run this command there.

Now, let's create our ImageGeneratorService class and set up the client in the constructor. We'll create a new file called image_generator_service.py in the app/services directory:

In this constructor, we're doing two important things:

1. Creating an instance of our ImageManager class to handle storing and retrieving images
2. Initializing the Gemini client with an API key

The API_KEY placeholder should be replaced with your actual Gemini API key in a real application. For security reasons, it's best to store API keys in environment variables rather than hardcoding them in your source code. In a production environment, you might use something like:

The genai.Client is the main interface for interacting with Google's Generative AI services. We'll use this client to access the Imagen model, which specializes in generating images from text descriptions.

Now that we have our client set up, let's implement the core method of our service: generate_image(). This method will take a user input string, format it into a detailed prompt using our PromptManager, send the request to the Gemini API, and store the resulting image using our ImageManager.

Here's the implementation:

Let's break down what's happening in this method:

1. We start by calling PromptManager.format_prompt() to convert the user's input into a detailed prompt using our predefined template. This ensures consistency in our image generation requests.

2. We then make the API call using self.gemini_client.models.generate_images(), which takes several parameters:

   • model: We're using imagen-3.0-generate-002, which is Google's advanced image generation model
   • prompt: The formatted prompt from our PromptManager
   • config: A configuration object specifying that we want to generate just one image

3. From the response, we extract the first (and only) generated image using response.generated_images[0].

4. Finally, we pass the prompt and image to our ImageManager's add_image() method, which converts the image to base64 format, stores it, and returns the base64 string.

The method returns the base64-encoded image data, which can be used directly in web applications (for example, to display the image in an HTML <img> tag).

Generating images through an external API can fail for various reasons: network issues, API limits, invalid prompts, or server errors. To make our service robust, we've wrapped the API call in a try-except block that catches any exceptions and raises a more informative RuntimeError.

This error handling is crucial for a production application, as it prevents crashes and provides meaningful error messages that can help with debugging and user feedback.

Now, let's add one more method to our service to retrieve all previously generated images:

This simple method delegates to our ImageManager's get_images() method, returning the complete list of stored images along with their associated prompts and IDs.

With these two methods, our ImageGeneratorService provides a complete interface for generating and retrieving images. The service integrates our previously built components (PromptManager and ImageManager) and connects them to the external Gemini API.

Now that we've implemented our ImageGeneratorService, let's create a test script to verify that it works correctly. We'll update our app/main.py file to use the new service:

In this test script, we:

1. Import our ImageGeneratorService and PromptManager classes
2. Define a sample user input for testing
3. Create an instance of our ImageGeneratorService
4. Call the generate_image() method with our sample input
5. Print the result (the base64-encoded image)
6. Retrieve and print all stored images

When running this script with a valid API key, you would see output similar to:

The base64 string would be much longer in a real application, but I've truncated it here for readability. This string represents the encoded image data that can be used directly in an HTML <img> tag with the src attribute set to data:image/jpeg;base64, followed by the string.

In this lesson, we've built the ImageGeneratorService, the core component of our image generation application. This service connects our previously built components (PromptManager and ImageManager) to Google's Gemini API, allowing us to generate high-quality images from text prompts.

Let's review what we've learned:

1. We set up a client to communicate with Google's Gemini API
2. We implemented the generate_image() method to create images from user inputs
3. We added robust error handling to deal with potential API issues
4. We created a method to retrieve all previously generated images
5. We tested our service with a sample prompt

The ImageGeneratorService is a crucial piece of our application architecture. It encapsulates all the logic related to image generation, providing a clean interface for other components to use. In the next lesson, we'll build API endpoints that will use this service to handle HTTP requests in our FastAPI application.

In the upcoming practice exercises, you'll have the opportunity to work with the ImageGeneratorService, testing its functionality with different prompts and exploring how it integrates with the rest of our application. You'll also get to experiment with error handling and see how the service behaves in various scenarios.

Remember that to use this service in a real application, you'll need to:

1. Install the Google Generative AI library
2. Obtain a valid API key from Google
3. Replace the "API_KEY" placeholder with your actual key (preferably through environment variables)

With the ImageGeneratorService in place, we're one step closer to having a complete image generation web application powered by FastAPI!