AI_product_Description/llm.py

import io
from PIL import Image
import os

from openai import OpenAI
from  conf import *
from tos import HttpMethodType
import time
from openai import OpenAI
import os
import base64
from PIL import Image

def image_to_base64(image):
    # 将Image对象转换为BytesIO对象
    image_io = io.BytesIO()
    image.save(image_io, format='PNG')
    image_io.seek(0)

    # 使用base64编码
    image_base64 = base64.b64encode(image_io.read()).decode('utf-8')

    return f"data:image/png;base64,{image_base64}"

def image_reader(image):
    """图片读取器,输出PIL.Image格式的图片"""
    if isinstance(image,str):
        if image.startswith("http"):
            return image
        else:
            image_path = image
        out_image = Image.open(image_path)
    elif isinstance(image,np.ndarray):
        out_image = Image.fromarray(image)
    else:
        out_image = image
    out_image=out_image.convert('RGB')
    base64_img=image_to_base64(out_image)
    return base64_img
def get_lm_text(sys_prompt,user_prompt):
    completion = LMConfig.lm_client.chat.completions.create(
        messages = [
            {"role": "system", "content": sys_prompt},
            {"role": "user", "content": user_prompt},
        ],
        model=LMConfig.model,
    )

    return completion.choices[0].message.content




## 多模态的输入
def compress_image(input_path, output_path):
    img = Image.open(input_path)
    current_size = os.path.getsize(input_path)
    # 粗略的估计压缩质量，也可以从常量开始，逐步减小压缩质量，直到文件大小小于目标大小
    image_quality = int(float(MMMConfig.target_size / current_size) * 100)
    img.save(output_path, optimize=True, quality=int(float(MMMConfig.target_size / current_size) * 100))
    # 如果压缩后文件大小仍然大于目标大小，则继续压缩
    # 压缩质量递减，直到文件大小小于目标大小
    while os.path.getsize(output_path) > MMMConfig.target_size:
        img = Image.open(output_path)
        image_quality -= 10
        if image_quality <= 0:
            break
        img.save(output_path, optimize=True, quality=image_quality)
    return image_quality

def upload_tos(filename,  tos_object_key):

    tos_client, inner_tos_client = MMMConfig.tos_client, MMMConfig.inner_tos_client
    try:
        # 将本地文件上传到目标桶中, filename为本地压缩后图片的完整路径
        tos_client.put_object_from_file(MMMConfig.tos_bucket_name, tos_object_key, filename)
        # 获取上传后预签名的 url
        return inner_tos_client.pre_signed_url(HttpMethodType.Http_Method_Get, MMMConfig.tos_bucket_name, tos_object_key)
    except Exception as e:
        if isinstance(e, tos.exceptions.TosClientError):
            # 操作失败，捕获客户端异常，一般情况为非法请求参数或网络异常
            print('fail with client error, message:{}, cause: {}'.format(e.message, e.cause))
        elif isinstance(e, tos.exceptions.TosServerError):
            # 操作失败，捕获服务端异常，可从返回信息中获取详细错误信息
            print('fail with server error, code: {}'.format(e.code))
            # request id 可定位具体问题，强烈建议日志中保存
            print('error with request id: {}'.format(e.request_id))
            print('error with message: {}'.format(e.message))
            print('error with http code: {}'.format(e.status_code))

        else:

            print('fail with unknown error: {}'.format(e))

        raise e



def doubao_MMM_request(pre_signed_url_output, prompt):

    client = MMMConfig.client
    

    response = client.chat.completions.create(
        model=MMMConfig.model,
        messages=[{"role": "user","content": [
                {"type": "text", "text": prompt},
                {"type": "image_url", "image_url": {"url": pre_signed_url_output.signed_url}}
            ],
        }],
        temperature=0.8,
        extra_headers={"x-ark-beta-vision": "true"}
    )
    result = response.choices[0].message.content
    return result


class llm_request:
    def __init__(self,api_key,base_url,model) -> None:
        self.api_key=api_key
        self.base_url=base_url
        self.model=model


    def llm_mm_request(self,usr_text,img,sys_text="You are a helpful assistant."):
        client = OpenAI(
        # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
        api_key=self.api_key,
        base_url=self.base_url
    )
        completion = client.chat.completions.create(
            model=self.model,#
            messages=[
                {
                    "role": "system",
                    "content": [{"type":"text","text": sys_text}]},
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "image_url",
                            # 需要注意，传入Base64，图像格式（即image/{format}）需要与支持的图片列表中的Content Type保持一致。"f"是字符串格式化的方法。
                            # PNG图像：  f"data:image/png;base64,{base64_image}"
                            # JPEG图像： f"data:image/jpeg;base64,{base64_image}"
                            # WEBP图像： f"data:image/webp;base64,{base64_image}"
                            "image_url": {"url": image_reader(img)}, 
                        },
                        {"type": "text", "text": usr_text},
                    ],
                }

            ],
            temperature=1.5,
            top_p=0.85, 
            presence_penalty=1.5, 
            frequency_penalty=1.5,
        )
        return completion.choices[0].message.content
    
    def llm_text_request(self,text,sys_text="You are a helpful assistant."):
        client = OpenAI(
        # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
        api_key=self.api_key,
        base_url=self.base_url
    )
        completion = client.chat.completions.create(
            model=self.model,#
            messages=[
                {
                    "role": "system",
                    "content": sys_text},
                {
                    "role": "user",
                    "content":  text,
                }
            ],
            temperature=0.9,
        )
        return completion.choices[0].message.content
    


if __name__=="__main__":
    ##ali
    ky="sk-04b63960983445f980d85ff185a17876"
    baseurl="https://dashscope.aliyuncs.com/compatible-mode/v1"
    model="qwen-vl-max-latest"
    ##doubao
    # ky='817dff39-5586-4f9b-acba-55004167c0b1'
    # baseurl="https://ark.cn-beijing.volces.com/api/v3"
    # model="doubao-1-5-vision-pro-32k-250115"
    llm=llm_request(ky,baseurl,model)
    res1=llm.llm_mm_request("描述一下图片中的衣服","/data/data/Mia/product_env_project/gen_sellpoint/企业微信截图_17372766091671.png")
    print(res1)
    res2=llm.llm_text_request("你好！你是谁")
    print(res2)