import requests
import base64

# Hugging Face Endpoint
HF_TOKEN = "hf_<>"
HF_ENDPOINT = "https://"

# 读取本地图片并转换为 Base64
def encode_image(image_path):
    with open(image_path, "rb") as f:
        return base64.b64encode(f.read()).decode("utf-8")

# 构造请求数据
image_base64 = encode_image("./test.png")
payload = {
    "inputs": {  # Wrap everything inside "inputs"
        "image": image_base64,  # 发送 Base64 编码的图片
        "convs": [
            {"role": "system", "content": "You are agent that can see, talk and act."},
            {"role": "user", "content": "<image_start><image><image_end>\nWhat is in this image?"}
        ]
    }
}

# 发送请求
headers = {
    "Accept" : "application/json",
    "Content-Type": "application/json",
    "Authorization": f"Bearer {HF_TOKEN}",
}
response = requests.post(HF_ENDPOINT, headers=headers, json=payload)

# 解析响应
if response.status_code == 200:
    print("Response:", response.json())
else:
    print("Error:", response.status_code, response.text)