langchain==0.2.9 torch html2text paddlepaddle paddleocr

import cv2from paddleocr import PPStructure
table_engine = PPStructure(show_log=True, use_gpu=False, lang='ch')img_path = r'./2.jpg'img = cv2.imread(img_path)result = table_engine(img)html = result[0]['res']['html']print(len(html))# 2723

import html2text
markdown = html2text.html2text(html)print(len(markdown))# 1051

from langchain_openai import ChatOpenAIchat_model = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0.0)

from langchain_huggingface import HuggingFacePipelinefrom langchain_huggingface import ChatHuggingFace
llm = HuggingFacePipeline.from_model_id(model_id="./Qwen/Qwen2-0.5B-Instruct",task="text-generation",pipeline_kwargs=dict(max_new_tokens=512,do_sample=False,),)
chat_model = ChatHuggingFace(llm=llm)

from langchain_core.prompts import ChatPromptTemplate
# 创建Prompt模板chat_prompt_template = ChatPromptTemplate.from_messages([("system", "You are a helpful assistant"),("user", "根据表格内容回答下面问题：\n表格内容：\n{context}\nQuestion: {question}\nAnswer:")])
# 流程搭建chain = chat_prompt_template | chat_model.bind(skip_prompt=True)
# 问答运行res = chain.invoke({"context": markdown, "question": "姓名是什么？"})# res.content# 赵开心res = chain.invoke({"context": markdown, "question": "婚姻状况？"})# res.content# 婚姻状况为未婚。