Vision Understanding（画像認識）API

import requests

url = "https://api.apiyi.com/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "gpt-5.5",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Please describe this image in detail"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg"
                    }
                }
            ]
        }
    ]
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()
print(result['choices'][0]['message']['content'])

import base64
import requests

def image_to_base64(image_path):
    """Convert local image to base64 encoding"""
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode('utf-8')

# Read local image
base64_image = image_to_base64("path/to/your/image.jpg")

url = "https://api.apiyi.com/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "gemini-3.1-pro-preview",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Analyze all text content in this image"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/jpeg;base64,{base64_image}"
                    }
                }
            ]
        }
    ]
}

response = requests.post(url, headers=headers, json=payload)
print(response.json()['choices'][0]['message']['content'])

import requests

url = "https://api.apiyi.com/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "gemini-3.1-pro-preview",
    "messages": [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Please compare the differences between these two images:"},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/image1.jpg"}
                },
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/image2.jpg"}
                }
            ]
        }
    ],
    "max_tokens": 1000
}

response = requests.post(url, headers=headers, json=payload)
print(response.json()['choices'][0]['message']['content'])

curl https://api.apiyi.com/v1/chat/completions \
  -H "Authorization: Bearer $APIYI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-pro-preview",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "Please describe this image in detail" },
          { "type": "image_url", "image_url": { "url": "https://example.com/image.jpg" } }
        ]
      }
    ]
  }'

# 1. Convert local image to base64 (macOS / Linux)
BASE64_IMAGE=$(base64 -i path/to/your/image.jpg | tr -d '\n')

# 2. Pass the image content via a data URI
curl https://api.apiyi.com/v1/chat/completions \
  -H "Authorization: Bearer $APIYI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "Analyze all text content in this image" },
          { "type": "image_url", "image_url": { "url": "data:image/jpeg;base64,'"$BASE64_IMAGE"'" } }
        ]
      }
    ]
  }'

{
  "error": {
    "message": "Timeout while downloading ip:port",
    "type": "invalid_request_error",
    "code": "invalid_image_url"
  }
}

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "...source.base64: invalid base64 data"
  },
  "request_id": "req_011CczN..."
}

// ❌ Wrong: what follows base64, is an image link, not Base64-encoded data
"image_url": {
  "url": "data:image/jpeg;base64,https://example.com/generations/temp-xxx.jpg"
}

// ✅ Image is a remote URL → pass the link directly, no prefix at all
"image_url": {
  "url": "https://example.com/generations/temp-xxx.jpg"
}

// ✅ Image is a local file / binary → Base64-encode it first, then build the data URI (see Example 2 above)
"image_url": {
  "url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQ..."
}

{
  "status_code": 400,
  "error": {
    "message": "InvokeModel: operation error Bedrock Runtime: InvokeModel, https response error StatusCode: 400, RequestID: e87a35ed-..., ValidationException: ...source.base64: The image was specified using the image/png media type, but the image appears to be a image/jpeg image"
  }
}

import base64

def image_to_data_uri(image_path):
    """Detect the real format from magic bytes so the media type always matches the content"""
    with open(image_path, "rb") as f:
        data = f.read()

    if data[:8] == b"\x89PNG\r\n\x1a\n":
        mime = "image/png"
    elif data[:3] == b"\xff\xd8\xff":
        mime = "image/jpeg"
    elif data[:6] in (b"GIF87a", b"GIF89a"):
        mime = "image/gif"
    elif data[:4] == b"RIFF" and data[8:12] == b"WEBP":
        mime = "image/webp"
    else:
        raise ValueError(f"Unrecognized image format: {image_path}")

    return f"data:{mime};base64,{base64.b64encode(data).decode('utf-8')}"

import base64, io
from PIL import Image

def image_to_data_uri(image_path):
    img = Image.open(image_path)
    buf = io.BytesIO()
    img.convert("RGB").save(buf, format="JPEG", quality=90)
    b64 = base64.b64encode(buf.getvalue()).decode("utf-8")
    return f"data:image/jpeg;base64,{b64}"

prompt = """
Please analyze this product image, including:
1. Product type and brand
2. Main features and selling points
3. Suitable target audience
4. Suggested marketing copy
"""

prompt = """
Please extract all text content from the image and organize it in the original format.
If there are tables, please present them in Markdown table format.
"""

prompt = """
This is a medical imaging picture, please:
1. Describe basic image information (such as imaging type, body part, etc.)
2. Label visible anatomical structures
3. Note: For reference only, not for diagnostic purposes
"""

prompt = """
Analyze the surveillance footage to identify:
1. Number of people and their positions in the scene
2. Any abnormal behavior
3. Environmental safety hazards
4. Timestamp information (if visible)
"""

# ❌ Not Recommended: Vague prompt
prompt = "What is this"

# ✅ Recommended: Specific and clear prompt
prompt = """
Please analyze this image from the following aspects:
1. Main Objects: Identify main objects or people in the image
2. Scene Environment: Describe the shooting location and environmental features
3. Color Composition: Analyze color scheme and composition characteristics
4. Emotional Atmosphere: Emotions or atmosphere conveyed by the image
5. Possible Uses: What scenarios this image is suitable for
"""

import requests
from requests.exceptions import RequestException

def analyze_image_with_retry(image_url, prompt, max_retries=3):
    """Image analysis function with retry mechanism"""
    for attempt in range(max_retries):
        try:
            response = requests.post(
                "https://api.apiyi.com/v1/chat/completions",
                headers={
                    "Authorization": f"Bearer {API_KEY}",
                    "Content-Type": "application/json"
                },
                json={
                    "model": "gpt-5.5",
                    "messages": [{
                        "role": "user",
                        "content": [
                            {"type": "text", "text": prompt},
                            {"type": "image_url", "image_url": {"url": image_url}}
                        ]
                    }]
                },
                timeout=30
            )

            if response.status_code == 200:
                return response.json()
            elif response.status_code == 429:
                print(f"Rate limited, waiting to retry... (attempt {attempt + 1}/{max_retries})")
                time.sleep(2 ** attempt)  # Exponential backoff
            else:
                print(f"Error: {response.status_code} - {response.text}")

        except RequestException as e:
            print(f"Request exception: {e}")

    return None

payload = {
    "model": "gpt-5.5",
    "messages": [...],
    "stream": True
}

response = requests.post(url, headers=headers, json=payload, stream=True)
for line in response.iter_lines():
    if line:
        print(line.decode('utf-8'))

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "What animal is this?"},
            {"type": "image_url", "image_url": {"url": "animal.jpg"}}
        ]
    },
    {
        "role": "assistant",
        "content": "This is a Golden Retriever."
    },
    {
        "role": "user",
        "content": [{"type": "text", "text": "How old does it look? How is its health condition?"}]
    }
]

tools = [
    {
        "type": "function",
        "function": {
            "name": "save_image_analysis",
            "description": "Save image analysis results to database",
            "parameters": {
                "type": "object",
                "properties": {
                    "objects": {"type": "array", "items": {"type": "string"}},
                    "scene": {"type": "string"},
                    "text_content": {"type": "string"}
                }
            }
        }
    }
]

payload = {
    "model": "gpt-5.5",
    "messages": messages,
    "tools": tools,
    "tool_choice": "auto"
}