Task 1 of KodeKloud's 𝗔𝗜 - 𝗟𝗲𝘃𝗲𝗹 𝟭 curriculum

Task 𝟭 of KodeKloud's 𝗔𝗜 - 𝗟𝗲𝘃𝗲𝗹 𝟭 curriculum. This curriculum focuses on tasks related to AI and AI code development. Today's task was to create a script that will take a bug report and rewrite it in a clear, structured, and professional issue summary.

Here were the task requirements:
• Initialize the OpenAI client using environment values (api_key and base_url).
• Define a function 𝗰𝗹𝗮𝗿𝗶𝗳𝘆_𝗯𝘂𝗴(𝗱𝗲𝘀𝗰𝗿𝗶𝗽𝘁𝗶𝗼𝗻: 𝘀𝘁𝗿) -> 𝘀𝘁𝗿 that builds a parameterized prompt to rewrite the raw bug description.
• Send this prompt to the OpenAI Chat Completion API.
• Use the following configuration for the API call:
model: openai/gpt-4.1-mini
messages: user → the constructed prompt
max_tokens: 100
temperature: 0.0
• Use the input bug report: "App keeps crashing when I click save."
• Store the AI response in a variable named 𝗿𝗲𝘀𝗽𝗼𝗻𝘀𝗲 and print the clarified bug summary to the console.
• Function must use the developer's input description dynamically in the prompt.
• OpenAI credentials are stored as ENV variables

These were a lot of requirements, though it's not as difficult as it sounds. If you want to see how this completed, please review the screenshot of my script that I have included. Here are some things to pay attention to:

1. I added comments on each section for clarification on what is happening and matching up with the task requirements
2. I didn't hard-code ANY api keys or base_urls. This is for 2 reasons, security and to make this modularized. This allows ANYONE to run this script with their own OpenAI credentials
3. I used the OpenAI library, not LangChain. This was due to the task requirements

I hope you found this informative! More to come!Task 𝟭 of KodeKloud's 𝗔𝗜 - 𝗟𝗲𝘃𝗲𝗹 𝟭 curriculum. This curriculum focuses on tasks related to AI and AI code development. Today's task was to create a script that will take a bug report and rewrite it in a clear, structured, and professional issue summary.

Here were the task requirements:
• Initialize the OpenAI client using environment values (api_key and base_url).
• Define a function 𝗰𝗹𝗮𝗿𝗶𝗳𝘆_𝗯𝘂𝗴(𝗱𝗲𝘀𝗰𝗿𝗶𝗽𝘁𝗶𝗼𝗻: 𝘀𝘁𝗿) -> 𝘀𝘁𝗿 that builds a parameterized prompt to rewrite the raw bug description.
• Send this prompt to the OpenAI Chat Completion API.
• Use the following configuration for the API call:

model: openai/gpt-4.1-mini  
messages: user → the constructed prompt  
max_tokens: 100  
temperature: 0.0  

• Use the input bug report: "App keeps crashing when I click save."
• Store the AI response in a variable named 𝗿𝗲𝘀𝗽𝗼𝗻𝘀𝗲 and print the clarified bug summary to the console.
• Function must use the developer's input description dynamically in the prompt.
• OpenAI credentials are stored as ENV variables

These were a lot of requirements, though it's not as difficult as it sounds. If you want to see how this completed, please review the script that I have included. Here are some things to pay attention to:

1. I added comments on each section for clarification on what is happening and matching up with the task requirements
2. I didn't hard-code ANY api keys or base_urls. This is for 2 reasons, security and to make this modularized. This allows ANYONE to run this script with their own OpenAI credentials
3. I used the OpenAI library, not LangChain. This was due to the task requirements

from openai import OpenAI

# declaring the OpenAI client and passing explicitly the api_key and base_url
# the values are passed from the ENV keys found in /root/.bash_profile
client = OpenAI(
    base_url=os.environ.get("OPENAI_API_BASE"),
    api_key=os.environ.get("OPENAI_API_KEY")
)

# defining clarify_bug with a description parameter for input bug report
def clarify_bug(description: str) -> str:
    # declaring model, max_tokens, and temperature
    response = client.chat.completions.create(
        model="openai/gpt-4.1-mini",
        messages=[
            {
                "role": "system", 
                "content": "You are a helpful, articulate software engineer. Please give clear, structured, professional summaries."
            },
            {
                "role": "user", 
                "content": f"Please rewrite the raw bug description: {description}."
            }
        ],
        temperature=0.0,
        max_tokens=100
    )
    # Extract and return the response text
    return response.choices[0].message.content

# declaring main
def main():
    input_test_report = "App keeps crashing when I click save."
    # as per the requirement, storing reponse as a response variable
    response = clarify_bug(input_test_report)
    if response:
        # print the response
        print(response)
    else:
        print("Failed to retrieve response from LLM")

if __name__ == "__main__":
    main()

I hope you found this informative! More to come!