dsProject/dsRag/Tools/T4_DocxProcessor.py

from openai import OpenAI
from Config import Config

class DocxProcessor:
    def __init__(self):
        # 独立初始化DeepSeek客户端
        self.client = OpenAI(
            api_key=Config.DEEPSEEK_API_KEY,
            base_url=Config.DEEPSEEK_URL
        )
    
    def call_deepseek(self, prompt):
        """独立调用DeepSeek API"""
        try:
            response = self.client.chat.completions.create(
                model="deepseek-chat",
                messages=[
                    {"role": "system", "content": "你是一个专业的文档分析助手"},
                    {"role": "user", "content": prompt}
                ],
                temperature=0.3
            )
            return response.choices[0].message.content
        except Exception as e:
            print(f"调用DeepSeek API出错: {str(e)}")
            return ""

    def ask_llm(self, text_chunk):
        """向大模型提问并获取响应"""
        prompt = f"""请分析以下文本段落并返回有价值的内容:
要求:
1. 保持原文关键信息
2. 用清晰的格式返回
3. 可包含简要总结

文本段落内容:
{text_chunk}"""
        return self.call_deepseek(prompt)

# 初始化DeepSeek客户端
client = OpenAI(
    api_key=Config.DEEPSEEK_API_KEY,
    base_url=Config.DEEPSEEK_URL
)

def split_text(text, chunk_size=6000):
    """按段落分割文本，确保每个块接近6000字"""
    paragraphs = [p.strip() for p in text.split('\n') if p.strip()]
    chunks = []
    current_chunk = []
    current_length = 0
    
    for para in paragraphs:
        para_length = len(para)
        if current_length + para_length > chunk_size and current_chunk:
            chunks.append('\n'.join(current_chunk))
            current_chunk = []
            current_length = 0
        current_chunk.append(para)
        current_length += para_length
    
    if current_chunk:
        chunks.append('\n'.join(current_chunk))
    return chunks

def ask_llm(text_chunk, is_final=False):
    prompt = """请将以下文本按内容相关性划分为段落，要求：
    1. 意思一致或强相关的内容放在同一段落
    2. 每个段落有明确的主题
    3. 输出格式为：## 段落主题\n段落内容\n\n"""
    return call_deepseek_api(prompt)

def process_document(input_file, output_file):
    """处理文档主流程"""
    text = read_docx(input_file)
    chunks = split_text(text)
    
    for i, chunk in enumerate(chunks, 1):
        print(f"正在处理第{i}个段落...")
        try:
            processor = DocxProcessor()
            response = processor.ask_llm(chunk)
            paragraphs = processor.process_llm_response(response)
            for para in paragraphs:
                processor.save_to_txt(para, output_file)
        except Exception as e:
            save_to_txt(f"段落{i}处理失败: {str(e)}", output_file)
    
    print(f"处理完成，结果已保存到 {output_file}")


def read_docx(file_path):
    """读取docx文件内容"""
    from docx import Document
    try:
        doc = Document(file_path)
        return '\n'.join([para.text for para in doc.paragraphs if para.text.strip()])
    except Exception as e:
        print(f"读取docx文件出错: {str(e)}")
        return ""

def save_to_txt(content, file_path, mode='a'):
    """将内容保存到txt文件"""
    try:
        with open(file_path, mode, encoding='utf-8') as f:
            f.write(content + '\n\n')
    except Exception as e:
        print(f"保存到txt文件出错: {str(e)}")

# 在process_document方法中调用时，请确保output_file参数是完整的文件路径


def call_deepseek_api(prompt, stream_callback=None):
    """流式调用DeepSeek API"""
    try:
        response = client.chat.completions.create(
            model="deepseek-chat",
            messages=[
                {"role": "system", "content": "你是一个专业的文档分析助手"},
                {"role": "user", "content": prompt}
            ],
            temperature=0.3,
            stream=True
        )
        
        full_response = ""
        for chunk in response:
            if chunk.choices[0].delta.content:
                content = chunk.choices[0].delta.content
                full_response += content
                if stream_callback:
                    stream_callback(content)
        
        return full_response
    except Exception as e:
        print(f"调用DeepSeek API出错: {str(e)}")


def process_llm_response(response):
    """处理大模型的段落划分响应"""
    paragraphs = []
    current_para = ""
    for line in response.split('\n'):
        if line.startswith('## '):
            if current_para:
                paragraphs.append(current_para.strip())
            current_para = line[3:] + '\n'  # 去掉##标记
        else:
            current_para += line + '\n'
    if current_para:
        paragraphs.append(current_para.strip())
    return paragraphs


if __name__ == "__main__":
    input_file = '../Txt/小学数学（史校长）.docx'
    output_file ='../Txt/小学数学（史校长）.txt'
    process_document(input_file, output_file)