python -m venv openai-env

openai-env\Scripts\activate

source openai-env/bin/activate

set OPENAI_API_KEY "你的API_KEY"

echo %OPENAI_API_KEY%

export OPENAI_API_KEY='你的API_KEY'

echo $OPENAI_API_KEY

from openai import OpenAI
import os

client = OpenAI(
 # 預設是抓取環境變數 os.environ.get("OPENAI_API_KEY")
 api_key= "你的API_KEY"  # 申請來的API_KEY
)

response = client.completions.create(
    model = "text-davinci-002",    # 使用的模型
    prompt = "將英文翻譯成法文：'Hello, how are you?'",
    max_tokens = 50, # 控制生成文本的最大令牌數
    temperature=0.7  # 調整多樣性，較高的值會產生更多變化的輸出
)

print(response.choices[0].text)  # 印出GPT的回應

pip install --upgrade openai

from openai import OpenAI
import os

client = OpenAI(
 # 預設是抓取環境變數 os.environ.get("OPENAI_API_KEY")
 api_key= "你的API_KEY"  # 申請來的API_KEY
)

response_top_p = client.completions.create(
  model="text-davinci-002",
  prompt="將英文翻譯成法文： 'Hello, how are you?'",
  max_tokens=50,
  temperature=0.7,
  top_p=0.8  # 控制選擇性，模型將考慮前80%的詞彙  
)

print("Response with top_p:")
print(response_top_p.choices[0].text)

from openai import OpenAI

client = OpenAI(
 # 預設是抓取環境變數 os.environ.get("OPENAI_API_KEY")
 api_key= "你的API_KEY"  # 申請來的API_KEY
)

response_top_p = client.completions.create(
  model="text-davinci-002",
  prompt="將英文翻譯成法文： 'Hello, how are you?'",
  max_tokens=50,
  temperature=0.7,
  frequency_penalty=0.5  #透過增加頻率懲罰來減少生成文本中常見詞彙的出現
)

print(response_top_p.choices[0].text)

from openai import OpenAI
import os

client = OpenAI(
 # 預設是抓取環境變數 os.environ.get("OPENAI_API_KEY")
 api_key= "你的API_KEY"  # 申請來的API_KEY
)

response_top_p = client.completions.create(
  model="text-davinci-002",
  prompt="將英文翻譯成法文： 'Hello, how are you?'",
  max_tokens=50,
  temperature=0.7,
  presence_penalty=0.5 #透過增加存在懲罰，增加特定詞彙在生成文本中的出現頻率
)

print(response_top_p.choices[0].text)

from openai import OpenAI
import os

client = OpenAI(
    api_key= "你的API_KEY"
)
response = client.chat.completions.create(
    model = "gpt-3.5-turbo",
    messages=[
        {
            "role": "system",
            "content": "你的任務是根據英文文法，修改英文句子"
        },
        {
            "role": "user",
            "content": "She no went to the market."
        }
    ],
    temperature=0,  # 回應變化的多樣性，0：變化最少, 1:變化最多
    max_tokens=256  # 最多256個token
)
print(response.choices[0].message)  # 訊息資料結構
print(response.choices[0].message.content)  # 訊息

from openai import OpenAI

client = OpenAI(
    api_key= "你的API_KEY"
)

response = client.chat.completions.create(
    model = "gpt-3.5-turbo",
    messages=[
        {
            "role": "system",
            "content": "你的任務是將一則推文做情感分析為正面、中性或負面。"
        },
        {
            "role": "user",
            "content": "I loved the new Batman movie!"
        }
    ],
    temperature=0,  # 回應變化的多樣性，0：變化最少, 1:變化最多
    max_tokens=256  # 最多256個token
)
print(response.choices[0].message)  # 訊息資料結構
print(response.choices[0].message.content)  # 訊息

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model = "gpt-3.5-turbo",
    messages=[
        {
            "role": "system",
            "content": "你的任務將給你的文章，為小學二年級學生摘錄重點"
        },
        {
            "role": "user",
            "content": "木星是距離太陽第五顆行星，也是太陽系中最大的行星。"+
            "它是一顆氣態巨行星，質量是太陽的千分之一，但是太陽系中所有其他行星"+
            "質量總和的兩倍半。木星是夜空中肉眼可見的最亮天體之一，早在有記載的"+
            "歷史之前就為古代文明所知。它以羅馬神朱庇特命名。從地球上觀察時"+
            "，木星的亮度足以使其反射光投射出可見的陰影，並且平均而言，木星"+
            "是夜空中第三亮的自然物體，僅次於月球和金星。"
        }
    ],
    temperature=0,  # 回應變化的多樣性，0：變化最少, 1:變化最多
    max_tokens=1024  # 最多1024個token
)
print(response.choices[0].message.content)  # 訊息

from openai import OpenAI
import os

_path = os.path.dirname(__file__) #目前程式所在資料夾
file_path = _path + '/' + '05-Hello.py' # 替換成你的Python檔案路徑

with open(file_path, 'r', encoding="utf-8") as file: #檔案可能讀取失敗
    code = file.read()  # 使用read()讀取整個檔案內容        

client = OpenAI()
response = client.chat.completions.create(
    model = "gpt-3.5-turbo",
    messages=[
        {
            "role": "system",
            "content": "您將獲得一段程式碼，您的任務是以簡潔的方式解釋它。"
        },
        {
            "role": "user",
            "content": code # 前面讀取的檔案內容
        }
    ],
    temperature=0,  # 回應變化的多樣性，0：變化最少, 1:變化最多
    max_tokens=1024  # 最多256個token
)
print(response.choices[0].message.content)  # 訊息

from openai import OpenAI

client = OpenAI(
    api_key= "你的API_KEY"
)

response = client.chat.completions.create(
    model = "gpt-3.5-turbo",
    messages=[
        {
            "role": "system",
            "content": "您將獲得產品描述和種子詞，任務則是產生產品名稱。"
        },
        {
            "role": "user",
            "content": "產品描述: A home milkshake maker\n" +
                        "種子詞: fast, healthy, compact."
        }
    ],
    temperature=0.8,  # 回應變化的多樣性，0：變化最少, 1:變化最多
    max_tokens=256  # 最多256個token
)

print(response.choices[0].message.content)  # 訊息

from openai import OpenAI

client = OpenAI(
    api_key= "你的API_KEY"
)

response = client.chat.completions.create(
    model = "gpt-3.5-turbo",
    messages=[
        {
            "role": "user",
            "content": "建立一個包含 8 個問題的清單，用於訪問一位科幻作家。"
        }
    ],
    temperature=0.5,  # 回應變化的多樣性，0：變化最少, 1:變化最多
    max_tokens=1024  # 最多1024個token
)

print(response.choices[0].message.content)  # 訊息

from openai import OpenAI

client = OpenAI(
    api_key= "你的API_KEY"
)

response = client.chat.completions.create(
    model = "gpt-3.5-turbo",
    messages=[
        {
            "role": "user",
            "content": "建立包含頂級科幻電影以及發行年份的兩列 CSV。"
        }
    ],
    temperature=0.5,  # 回應變化的多樣性，0：變化最少, 1:變化最多
    max_tokens=256  # 最多1024個token
)

print(response.choices[0].message.content)  # 訊息

def answer_question(
    df,
    model="gpt-3.5-turbo",
    question="Am I allowed to publish model outputs to Twitter, without a human review?",
    max_len=1800,
    size="ada",
    debug=False,
    max_tokens=150,
    stop_sequence=None
):
    """
    根據最近似的自訂文字內容的context來回答問題
    """
    context = create_context(
        question, # 問題指令
        df,       # 自訂文字內容的context
        max_len=max_len,
        size=size,
    )
    # If debug, print the raw model response
    if debug:
        print("Context:\n" + context)
        print("\n\n")

    try:
        # Create a chat completion using the question and context
        response = client.chat.completions.create(
            model="gpt-3.5-turbo",
            messages=[
                {"role": "system", "content": "Answer the question based on the context below, and if the question can't be answered based on the context, say \"I don't know\"\n\n"},
                {"role": "user", f"content": "Context: {context}\n\n---\n\nQuestion: {question}\nAnswer:"}
            ],
            temperature=0,
            max_tokens=max_tokens,
            top_p=1,
            frequency_penalty=0,
            presence_penalty=0,
            stop=stop_sequence,
        )
        return response.choices[0].message.strip()
    except Exception as e:
        print(e)
        return ""

answer_question(df, question="What day is it?", debug=False)

answer_question(df, question="What is our newest embeddings model?")

answer_question(df, question="What is ChatGPT?")

"I don't know."

'The newest embeddings model is text-embedding-ada-002.'

'ChatGPT is a model trained to interact in a conversational way. It is able to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.'