GPT系列

# 使用GPT-4o进行多模态理解
from openai import OpenAI
import base64

client = OpenAI()

# 文本+图像输入
def analyze_multimodal(text_prompt, image_path):
    with open(image_path, "rb") as image_file:
        base64_image = base64.b64encode(image_file.read()).decode('utf-8')
    
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": text_prompt},
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{base64_image}"
                        }
                    }
                ]
            }
        ],
        max_tokens=1000
    )
    return response.choices[0].message.content

# 使用o3进行复杂推理
def complex_reasoning(problem):
    response = client.chat.completions.create(
        model="o3",
        messages=[
            {"role": "system", "content": "你是一个专业的问题求解器，请展示完整的推理过程"},
            {"role": "user", "content": problem}
        ],
        temperature=0.1,  # 低温度提高推理准确性
        max_thinking_tokens=50000  # o系列特有：思考token
    )
    return response.choices[0].message.content

# 流式输出 (GPT-4 Turbo)
def stream_response(prompt):
    stream = client.chat.completions.create(
        model="gpt-4-turbo",
        messages=[{"role": "user", "content": prompt}],
        stream=True
    )
    
    for chunk in stream:
        if chunk.choices[0].delta.content is not None:
            print(chunk.choices[0].delta.content, end="")