Split gives an index out of range error

Short Course Q&A ChatGPT Prompt Engineering for Developers
1

Does this code in the inferring section work correctly? I am getting an index out of range error.

topic_dict = {i.split(‘: ‘)[0]: int(i.split(’: ‘)[1]) for i in response.split(sep=’\n’)}
if topic_dict[‘nasa’] == 1:
print(“ALERT: New NASA story!”)

Appreciate the help.

2

The result of the previous exercise now comes in a different format compared to the video. The error disappears as soon as format is corrected by slightly modifying the prompt.

3

I´m getting the same error, did you fix it?
ty

4

Hi @vkbalasub

In your code, the if statement will only be executed if the topic_dict dictionary contains an entry for the key “nasa” and the value of this entry is 1. However, the answer string does not contain a line beginning with the text nasa : 1. This means that the topic_dict dictionary does not contain an entry for the key “nasa”.

To solve this problem, consider checking the answer string for a line beginning with the text nasa :

5

I just solve the format of answer by
prompt = f"“”
Determine whether each item in the following list of
topics is a topic in the text below, which
is delimited with triple backticks.

Give your answer as jsonwith topic list items an key.
Give your answer for each topic 0 or 1 as value.\

List of topics: {", ".join(topic_list)}

Text sample: ‘’‘{story}’‘’
“”"
response = get_completion(prompt)
print(response)

6

First import the json module to notebook, then modify the prompt to format your response in json like fatemeh1370 mentioned, finally convert the json string to dictionary with the code below, it should work!

topic_dict = json.loads(response)
if topic_dict['nasa'] == 1:
    print("ALERT: New NASA story!")