Welcome to the lesson on Prompt Structure and Variables. In this lesson, we will explore how prompts are structured and how variables are used to create dynamic and flexible AI interactions. Prompts are essential in guiding AI behavior, allowing us to tailor responses to specific needs. By the end of this lesson, you will understand how to load and render templates using variables — a crucial skill in building the AI Cooking Helper.

Before we dive into templates, let's briefly recall file handling in Python. This knowledge is essential, as we will be loading template files in this lesson. In Python, the open() function is used to open a file, and the read() method is used to read its contents. Here's a quick reminder:

This code snippet opens a file named example.txt, reads its contents, and prints them. The with statement ensures the file is closed automatically after reading.

Our templates will represent prompts that can be enriched with variables, in the form of text files with placeholders. These placeholders are enclosed in double curly braces, like {{variable_name}}, where variable_name can be any custom name you choose. This allows you to create flexible templates that can be reused with different values.

For example, consider the following template:

In this template, {{sentence}} and {{max_versions}} are placeholders. When rendering the template, you can provide any values for these variables, making the prompt adaptable to different situations.

To use a template, we first need to load it from a file. Let's break down the load_template function:

• base_dir is set to the absolute path of the parent directory of the current script.
• prompts_dir points to the folder where prompt templates are stored.
• file_path is constructed by joining prompts_dir with the template filename (using f"{template_name}.txt"), resulting in the full path to the desired template file.
• The file is opened, and its contents are read and returned as a string.

Once we have loaded a template, we can render it by replacing placeholders with actual values. The render_template function allows you to substitute any custom variable names in the template with the values you provide.

• template_str is the template string loaded from the file.
• variables is a dictionary where keys are variable names and values are the values to substitute.
• The function uses a regular expression to find all placeholders like {{variable_name}} and replaces them with the corresponding value from the variables dictionary.
• If a variable is not provided, the placeholder remains unchanged.

Finally, let's see how loading and rendering are combined in the render_prompt_from_file function. This function takes a template file name and a dictionary of variables, loads the template, and renders it with the provided values.

• file_name is the name of the template file (without the .txt extension).
• variables is a dictionary of variable names and their values.
• The function loads the template and renders it, returning the final prompt string with all placeholders replaced.

In this lesson, you learned how to structure prompts using templates and variables. We covered loading templates from files, rendering them with actual values using custom variable names, and combining these steps to create dynamic prompts. As you move on to the practice exercises, you'll apply these skills to create and render your own templates. Experiment with different inputs and variable names to see how they affect the output. Keep up the great work, and enjoy the hands-on practice!