星火大模型——多模态API调用（图像+文本）

参考文档

• 图片理解 API 文档

环境配置

pip3 install websocket-client

核心代码

import _thread as thread
import base64
import datetime
import hashlib
import hmac
import json
from urllib.parse import urlparse
import ssl
from datetime import datetime
from time import mktime
from urllib.parse import urlencode
from wsgiref.handlers import format_date_time
import websocket  # 使用websocket_client
from PIL import Image
import io

appid = "xxx"    #填写控制台中获取的 APPID 信息
api_secret = "xxxx"   #填写控制台中获取的 APISecret 信息
api_key ="xxxx"    #填写控制台中获取的 APIKey 信息
#  = open("images\PointAClouth.png",'rb').read()

# Function to resize the image
def resize_image(image_path, size):
    image = Image.open(image_path)
    resized_image = image.resize(size)
    print(resized_image.size)
    # import pdb; pdb.set_trace()
    return resized_image

# Function to encode the image
def encode_image(image):
    image_byte_array = io.BytesIO()
    image.save(image_byte_array, format='PNG')
    image_byte_array = image_byte_array.getvalue()
    return image_byte_array, base64.b64encode(image_byte_array).decode('utf-8')

# Path to your image
image_path = "images/PointAClouth.png"

# Getting the base64 string of the resized image
new_size = (1000, 1000)
resized_image = resize_image(image_path, new_size)
imagedata, base64_image = encode_image(resized_image)



imageunderstanding_url = "wss://spark-api.cn-huabei-1.xf-yun.com/v2.1/image"#云端环境的服务地址
text =[
    {
   
        "role": "user", 
        "content":