# -*- coding: utf-8 -*-
# 
# @author: lyg
# @date: 2025-5-7
# @version: 1
# @description:视觉识别文档内容

from langchain_openai.chat_models import ChatOpenAI
from langchain_core.prompts import HumanMessagePromptTemplate, ChatPromptTemplate
from langchain_core.messages import HumanMessage,SystemMessage
from langchain_core.output_parsers import JsonOutputParser
import json
import base64


class VisionTest:
    def __init__(self,file):
        self.llm = ChatOpenAI(temperature=0,
                              model="qwen2.5-72b-instruct",
                              base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
                              api_key="sk-15ecf7e273ad4b729c7f7f42b542749e")

        image = base64.b64encode(open(file, 'rb').read()).decode()
        self.prompt = ChatPromptTemplate.from_messages([
            SystemMessage("你是一个资深软件工程师，请分析图片回答问题。"),
            HumanMessage(content=[
                {"type": "text", "text": "describe the weather in this image"},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/jpeg;base64,{image}"},
                }
            ])
        ])

    def run(self,msg):
        chain = self.prompt | self.llm
        resp = chain.invoke({"msg": msg})
        print(resp.content)

if __name__ == '__main__':
    vision = VisionTest("image_path")
    vision.run("问题")