RAG精度瓶颈破局：结构化解析如何将知识库准确率拉满

import json
import requests

class OCRClient:
    def __init__(self, app_id: str, secret_code: str):
        self.app_id = app_id
        self.secret_code = secret_code

    def recognize(self, file_content: bytes, options: dict) -> str:
        # 构建请求参数
        params = {}
        for key, value in options.items():
            params[key] = str(value)

        # 设置请求头
        headers = {
            "x-ti-app-id": self.app_id,
            "x-ti-secret-code": self.secret_code,
            # 方式一：读取本地文件
            "Content-Type": "application/octet-stream"
            # 方式二：使用URL方式
            # "Content-Type": "text/plain"
        }

        # 发送请求
        response = requests.post(
            f"https://api.textin.com/ai/service/v1/pdf_to_markdown",
            params=params,
            headers=headers,
            data=file_content
        )

        # 检查响应状态
        response.raise_for_status()
        return response.text

def main():
    # 创建客户端实例
    client = OCRClient("你的x-ti-app-id", "你的x-ti-secret-code")

        # 插入下面的示例代码

if __name__ == "__main__":
    main()

# 在main函数中插入
    # 读取本地文件
    with open("你的文件.pdf", "rb") as f:
        file_content = f.read()

    # 设置URL参数，可按需设置，这里已为你默认设置了一些参数
    options = dict(
        dpi=144,
        get_image="objects",
        markdown_details=1,
        page_count=10,
        parse_mode="auto",
        table_flavor="html",
    )

    try:
        response = client.recognize(file_content, options)

        # 保存完整的JSON响应到result.json文件
        with open("result.json", "w", encoding="utf-8") as f:
            f.write(response)

        # 解析JSON响应以提取markdown内容
        json_response = json.loads(response)
        if"result"in json_response and "markdown"in json_response["result"]:
            markdown_content = json_response["result"]["markdown"]
            with open("result.md", "w", encoding="utf-8") as f:
                f.write(markdown_content)

        print(response)
    except Exception as e:
        print(f"Error: {e}")

# 在main函数中插入
    # 读取本地文件夹
    input_dir = "./tmp"# 你可以修改为自己的文件夹
    output_dir = "./output"# 输出结果的文件夹
        import os
    os.makedirs(output_dir, exist_ok=True)

    # 支持的文件类型
    exts = (".pdf",".png",".jpg",".jpeg",".bmp",".tiff",".webp",".doc",".docx",".html",".mhtml",".xls",".xlsx",".csv",".ppt",".pptx",".txt")
    files = [f for f in os.listdir(input_dir) if f.lower().endswith(exts)]

    # 设置URL参数，可按需设置，这里已为你默认设置了一些参数
    options = dict(
        dpi=144,
        get_image="objects",
        markdown_details=1,
        page_count=10,
        parse_mode="auto",
        table_flavor="html",
    )

    #循环处理
    for filename in files:
        file_path = os.path.join(input_dir, filename)
        with open(file_path, "rb") as f:
            file_content = f.read()
        try:
            response = client.recognize(file_content, options)
            base_name = os.path.splitext(filename)[0]
            # 保存JSON
            with open(os.path.join(output_dir, f"{base_name}.json"), "w", encoding="utf-8") as fw:
                fw.write(response)
            # 保存Markdown
            json_response = json.loads(response)
            if"result"in json_response and "markdown"in json_response["result"]:
                markdown_content = json_response["result"]["markdown"]
                with open(os.path.join(output_dir, f"{base_name}.md"), "w", encoding="utf-8") as fw:
                    fw.write(markdown_content)
            print(f"{filename} 处理完成")
        except Exception as e:
            print(f"{filename} 处理出错: {e}")