chatGPT slow response? Use openAI's api_key

Preconditions

1. You need to have an openAI account.
2. You need to have a magic tool.
These two will not be taught. There are tutorials on the first one online, but I am afraid to go into the second one. . .

process

Enter the openAI homepage, find personal information, click View API keys

, click API Keys, create a key, remember to copy it, otherwise you will not be able to open it when you put it away .
After you have the key, you need to write a program.

the code

import openai
import gradio as gr
openai.api_key = "你的api_key"

def chatgpt(content, temperature=0.8):
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {
    
    "role": "user", "content": content}
        ],
        temperature=temperature,
        max_tokens=1000,
        top_p=1,
        frequency_penalty=0,
        presence_penalty=0,
    )
    # print(response)
    return response.choices[0].message.content

if __name__ == "__main__":
    def send_chatgpt(text):
        output = chatgpt(text,0.8)
        return output

    interface = gr.Interface(fn=send_chatgpt, inputs="text", outputs="text")
    interface.launch()

Remember to pip openai and gradio (UI interface), then run the code and click the link

You can go here. Note that the apikey has a quota, which is basically enough for a single person.

If you have any questions, you can ask them in the comment area and answer them when you see them.