Accessing Microsoft Copilot programmatically

AN 0 Reputation points
2024-12-18T18:10:24.44+00:00

Hello, the below sample python code shows how to access chatgpt programmatically with a prompt. My question is - is it possible to do something equivalent programmatically with Microsoft copilot:

 

import openai

import os

 

from dotenv import load_dotenv, find_dotenv

__ = load_dotenv(find_dotenv())_

 

openai.api_key  = os.getenv('OPENAI_API_KEY')

 

def get_completion(prompt, model="gpt-3.5-turbo"):

    messages = [{"role": "user", "content": prompt}]

    response = openai.ChatCompletion.create(

        model=model,

        messages=messages,

        temperature=0, # this is the degree of randomness of the model's output

    )

    return response.choices[0].message["content"]

 

text_1 = f"""

_Making a cup of tea is easy! First, you need to get some _

_water boiling. While that's happening, _

_grab a cup and put a tea bag in it. Once the water is _

_hot enough, just pour it over the tea bag. _

_Let it sit for a bit so the tea can steep. After a _

_few minutes, take out the tea bag. If you _

_like, you can add some sugar or milk to taste. _

_And that's it! You've got yourself a delicious _

cup of tea to enjoy.

"""

prompt = f"""

You will be provided with text delimited by triple quotes.

_If it contains a sequence of instructions, _

re-write those instructions in the following format:

 

Step 1 - ...

Step 2 - …

Step N - …

 

_If the text does not contain a sequence of instructions, _

then simply write "No steps provided."

 

"""{text_1}"""

"""

response = get_completion(prompt)

print("Completion for Text 1:")

print(response)

Microsoft Copilot
Microsoft Copilot
Microsoft terminology for a universal copilot interface.
432 questions
0 comments No comments
{count} votes

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.