5013.大模型-调用api - 多模态调用

测试链接是否成功

curl https://api.openai.com/v1/models \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "OpenAI-Organization: YOUR_ORG_ID" \
  -H "OpenAI-Project: $PROJECT_ID"

from openai import OpenAI

client = OpenAI(
  api_key=api_key,  # 必选
  base_url=base_url, # 必选
  organization='YOUR_ORG_ID', #可选
  project='$PROJECT_ID', # 可选
)

发送api请求示例

curl https://api.openai.com/v1/chat/completions \ # 部署服务的地址
  -H "Content-Type: application/json" \  # 传递数据的格式
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
     "model": "gpt-4o-mini",  # 访问的模型
     "messages": [{"role": "user", "content": "Say this is a test!"}], # 模型参数
     "temperature": 0.7 # 模型温度
   }'

像模型发送上述请求后，你会得到一个完整的json格式的返回，格式如下

{
    "id": "chatcmpl-abc123",
    "object": "chat.completion",
    "created": 1677858242,
    "model": "gpt-4o-mini",
    "usage": {
        "prompt_tokens": 13,
        "completion_tokens": 7,
        "total_tokens": 20,
        "completion_tokens_details": {
            "reasoning_tokens": 0,
            "accepted_prediction_tokens": 0,
            "rejected_prediction_tokens": 0
        }
    },
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "\n\nThis is a test!"
            },
            "logprobs": null,
            "finish_reason": "stop",
            "index": 0
        }
    ]
}

聊天

创建对话

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-4o",
  messages=[
    {"role": "developer", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
)

print(completion.choices[0].message)

对话包含图片上传

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
                    }
                },
            ],
        }
    ],
    max_tokens=300,
)

print(response.choices[0])

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What'\''s in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 300
  }'

api使用音频

文字转音频

from pathlib import Path
import openai

speech_file_path = Path(__file__).parent / "speech.mp3"
response = openai.audio.speech.create(
  model="tts-1",
  voice="alloy",
  input="The quick brown fox jumped over the lazy dog."
)
response.stream_to_file(speech_file_path)

音频转文字

from openai import OpenAI
client = OpenAI()

audio_file = open("speech.mp3", "rb")
transcript = client.audio.transcriptions.create(
  model="whisper-1",
  file=audio_file
)

翻译

from openai import OpenAI
client = OpenAI()

audio_file = open("speech.mp3", "rb")
transcript = client.audio.translations.create(
  model="whisper-1",
  file=audio_file
)