OpenApi测试接口(python写的api接口)

主体代码：

import openai
import requests
from flask import Flask, jsonify, request

app = Flask(__name__)

# Set OpenAI API credentials
openai.api_key = 'sk-3MXseSpzjlPaPg0jKMPuT3BlbkFJ70WHA5twkr'

@app.route('/ask', methods=['POST'])
def ask():
    # Retrieve question from request body
    question = request.json.get('question')

    # Call OpenAI API to get answer 模型的版本太低，如果高一些，回答会更好！
    model = "text-davinci-003"
    # 这个是调整返回字数的，太小了不好
    max_tokens = 1000
    prompt = f"Q: {question}\nA:"
    response = openai.Completion.create(
        engine=model,
        prompt=prompt,
        max_tokens=max_tokens,
        n=1,
        stop=None,
        temperature=0.7,
    )
    answer = response.choices[0].text.strip()

    # Return answer in JSON format
    return jsonify({'answer': answer})

if __name__ == '__main__':
    app.run()

先运行起来：python .\httpOpenai.py

上测试代码：

import requests

url = "http://localhost:5000/ask"
data = {"question": "What is the meaning of life?"}
response = requests.post(url, json=data)
answer = response.json()["answer"]
print(answer)

测试结果：python .\httpsend.py

 用postman测试一把：

结果：模型的版本太低，如果高一些，回答会更好！