Multimodal

# 멀티모달 AI API 사용 예제
import openai
import anthropic
import base64
from pathlib import Path

# 1. OpenAI GPT-4o 멀티모달 (이미지 분석)
client = openai.OpenAI()

def analyze_image_gpt4o(image_path: str, question: str):
    """GPT-4o로 이미지 분석"""
    # 이미지를 base64로 인코딩
    with open(image_path, "rb") as f:
        image_data = base64.b64encode(f.read()).decode("utf-8")

    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": question},
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{image_data}",
                            "detail": "high"  # low, high, auto
                        }
                    }
                ]
            }
        ],
        max_tokens=1024
    )
    return response.choices[0].message.content

# 사용 예시
result = analyze_image_gpt4o(
    "chart.png",
    "이 차트에서 2024년 매출 트렌드를 분석해주세요."
)
print(result)


# 2. Claude 3.5 멀티모달 (문서 분석)
claude_client = anthropic.Anthropic()

def analyze_document_claude(image_path: str, instruction: str):
    """Claude로 문서/이미지 분석"""
    with open(image_path, "rb") as f:
        image_data = base64.standard_b64encode(f.read()).decode("utf-8")

    # 이미지 타입 감지
    suffix = Path(image_path).suffix.lower()
    media_types = {".png": "image/png", ".jpg": "image/jpeg", ".gif": "image/gif"}
    media_type = media_types.get(suffix, "image/jpeg")

    response = claude_client.messages.create(
        model="claude-3-5-sonnet-20241022",
        max_tokens=2048,
        messages=[
            {
                "role": "user",
                "content": [
                    {
                        "type": "image",
                        "source": {
                            "type": "base64",
                            "media_type": media_type,
                            "data": image_data
                        }
                    },
                    {"type": "text", "text": instruction}
                ]
            }
        ]
    )
    return response.content[0].text


# 3. 여러 이미지 비교 분석
def compare_images(image_paths: list[str], question: str):
    """여러 이미지를 동시에 분석"""
    content = [{"type": "text", "text": question}]

    for path in image_paths:
        with open(path, "rb") as f:
            image_data = base64.b64encode(f.read()).decode("utf-8")
        content.append({
            "type": "image_url",
            "image_url": {"url": f"data:image/jpeg;base64,{image_data}"}
        })

    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": content}],
        max_tokens=2048
    )
    return response.choices[0].message.content


# 4. 오픈소스 멀티모달 (LLaVA / Qwen-VL)
# pip install transformers accelerate
from transformers import AutoProcessor, LlavaForConditionalGeneration
from PIL import Image

def analyze_with_llava(image_path: str, prompt: str):
    """LLaVA로 로컬 이미지 분석"""
    model_id = "llava-hf/llava-1.5-7b-hf"

    processor = AutoProcessor.from_pretrained(model_id)
    model = LlavaForConditionalGeneration.from_pretrained(
        model_id,
        torch_dtype="auto",
        device_map="auto"
    )

    image = Image.open(image_path)
    conversation = [
        {"role": "user", "content": [
            {"type": "image"},
            {"type": "text", "text": prompt}
        ]}
    ]

    text = processor.apply_chat_template(conversation, add_generation_prompt=True)
    inputs = processor(images=image, text=text, return_tensors="pt").to(model.device)

    output = model.generate(**inputs, max_new_tokens=512)
    return processor.decode(output[0], skip_special_tokens=True)

print("=== 멀티모달 AI 예제 실행 완료 ===")