init

README.md

-hi 
\ No newline at end of file
+## 搜整页图片和搜题
+
+#### 1、需求
+
+需求1、依据用户拍摄的图书整页图片，搜索es库中对应的整页图片数据。
+
+需求2、依据用户拍摄图书某个题目图片， 搜索es库中对应的题目图片数据。
+
+
+
+服务器地址： 61.170.32.8
+
+开发文件路径：/home/liuxin/work/search_question
+
+conda虚拟环境：conda activate search_book
+
+
+
+#### 2、搜索方案
+
+```
+准备工作：
+1、将习题图书拆分为整页整页的完整图片，并使用合合OCR解析整页图片，放入excel的page_ocr列。
+2、将习题图书拆分为一个个独立的题目图片，并使用合合OCR解析题目图片，将ocr结果放入question_ocr列。将题目图片和题目合合eOCR结果一起输入豆包embedding模型"doubao-embedding-vision-250615"得到一个1024维的向量，处理为json字符串后放入excel的“question_image_embedding”列里。
+3、后端将以上excel数据通过接口插入es数据库（excel文档样例：“12668836-2025.xlsx”），在原有拆书平台下载的excel文档中添加【question_ocr(题目的ocr结果)，source_image_url(整页图片url)，page_ocr(整页图片ocr)，question_image_embedding(题目ocr和题目原图的向量)】列
+
+
+搜整页图片流程：
+1、用户手机拍摄图书完整页面图片并上传
+2、使用合合OCR对用户拍摄的图片进行解析
+3、搜整页图片api接口接收用户拍摄图片的ocr长字符串，使用长字符串在es中搜索
+4、返回es搜索的top 1数据内容。
+
+搜题目流程
+1、用户手机拍摄某个习题的图片并上传。
+2、使用合合OCR对用户拍摄的题目图片进行解析。
+3、将题目ocr结果和题目图片作为一个整体输入豆包embedding模型"doubao-embedding-vision-250615"得到一个1024维的向量。
+4、可只将题目图片合合OCR结果输入接口，进行搜题。也可以将1024维的向量输入接口进行搜题。
+5、只使用合合ocr搜题准确率99%。使用embedding向量搜题准确率100%。
+
+```
+
+
+
+#### 3、接口
+
+```python
+# 1、excel数据插入es数据库接口
+
+def insert_excel(data):
+    # 1、excel 数据插入es数据库
+    url = 'http://localhost:31001/upload/excel'
+    url = 'http://61.170.32.8:31001/upload/excel'
+    headers = { 'accept': 'application/json' }
+    file_path = data['file_path']
+    # 上传文件
+    with open(file_path, 'rb') as file:
+        files = {
+            'file': (file_path, file),
+        }
+
+        # 发送请求
+        response = requests.post(url, headers=headers, data=data, files=files)
+
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    print(f"响应内容: {response.json()}")
+    
+    
+data = {'book_id': '12670279', 'book_name': '衔接教材地理', "file_path": '12670279-2025版《锦上添花（期末大赢家）》下册.xlsx' }  
+
+insert_excel(data)
+
+```
+
+
+
+```python
+# 2、依据 book_id 删除es库中book_id相同的所有数据 接口
+
+def delete_es_book(book_id="12663121"):
+    # 2、指定book_id 删除es中对应的图书数据
+    url = 'http://localhost:31001/delete_book'
+    url = 'http://61.170.32.8:31001/delete_book'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    print(res)
+    
+book_id = "12667382"
+delete_es_book(book_id)
+```
+
+
+
+```python
+# 3、搜整页图片接口
+
+def search_book_question(book_id, image_ocr):
+    # 3、搜书搜题
+    url = 'http://localhost:31001/search_page'
+    url = 'http://61.170.32.8:31001/search_page'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id,
+        "image_ocr": image_ocr,
+        "top_k": 1
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+    bankId = res['es_search'][0]['_source']['bankId']
+    print("bankId: ", bankId)
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    return res
+
+book_id = "12664728"
+image_ocr = "用户拍摄图片整页的合合ocr结果"
+res = search_book_question(book_id, image_ocr)
+print(res)
+```
+
+
+
+#### 4、搜题接口 （只用题目合合OCR结果）
+
+```
+# 4、搜题（只用题目paddleOCR结果）接口
+
+def search_question_text(book_id, question_ocr):
+    url = 'http://localhost:31001/search_question_text'
+    # url = 'http://61.170.32.8:31001/search_question_text'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id,
+        "question_ocr": question_ocr,
+        "top_k": 1
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+
+    bankId = res['es_search'][0]['_source']['bankId']
+    print("bankId: ", bankId)
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    return res
+
+book_id = "12667382"
+question_ocr = "题目图片合合ocr结果"
+search_question_text(book_id, question_ocr)
+```
+
+
+
+#### 5、搜题接口 （题目合合ocr和题目图片作为一个整体的向量）
+
+```
+# 5、搜题接口 （题目合合ocr和题目图片作为一个整体的向量）
+
+def search_question_embedding(book_id:str, question_embedding):
+    url = 'http://localhost:31001/search_question_embedding'
+    # url = 'http://61.170.32.8:31001/search_question_embedding'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id,
+        "question_embedding": question_embedding,
+        "top_k": 1
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+
+    bankId = res['es_search'][0]['_source']['bankId']
+    print("bankId: ", bankId)
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    return res
+    
+book_id = "12670279"
+# 豆包embedding模型"doubao-embedding-vision-250615"得到一个1024维的向量
+question_embedding = np.random.random(1024).tolist() 
+question_embedding = json.dumps(question_embedding)
+
+res=search_question_embedding(book_id, question_embedding)
+```
+
+
+
+#### 6、启动服务
+
+```linux
+#  61.170.32.8 服务器
+$ cd /home/liuxin/work/search_question
+$ conda activate search_book
+$ nohup python -u api_service.py > api_service.log 2>&1 &
+$ tail -f log/search_question.log
+
+```
+

api_service.py

+from fastapi import FastAPI, File, UploadFile, Form, HTTPException
+import os,re,json
+from typing import Optional
+from pathlib import Path
+from pydantic import BaseModel
+import uvicorn
+import logging
+
+from save_es_database import EsHelper
+from prepare_data import prepareData
+
+__path__ = os.path.dirname(os.path.abspath(__file__))
+
+pre_data = prepareData() # 准备写入es的图书数据
+
+app = FastAPI(title="搜图书整页搜题")
+es = EsHelper()
+index_name = "search_question"  # rays 搜书搜题
+
+# 配置上传文件夹和允许的文件类型
+UPLOAD_DIR = Path("uploads")
+ALLOWED_EXTENSIONS = {"xlsx"}
+print("UPLOAD_DIR: ", UPLOAD_DIR)
+# 确保上传文件夹存在
+UPLOAD_DIR.mkdir(exist_ok=True)
+
+embed_dim = 1024 # es库中图片向量的维度
+# 定义将excel数据插入es库的 响应结构
+class UploadResponse(BaseModel):
+    status: str
+    message: str
+    filename: str
+    file_path: str
+    book_id: str
+    book_name: str
+
+
+# 搜整页图片请求数据结构
+class SearchPage(BaseModel):
+    book_id: str
+    image_ocr: str
+    top_k: int = 1
+
+# 搜题目请求数据结构（仅输入题目图片的OCR文本）
+class SearchQuestionText(BaseModel):
+    book_id: str
+    image_ocr: str = None  # 整页图片的paddleOCR结果，先确定题目所在的页再确定具体是那个题目 （题目大概率位于当前页，残题可能位于上一页）
+    question_ocr: str      # 题目的paddleOCR结果
+    top_k: int = 1
+
+# 搜题目请求数据结构（仅输入题目图片的向量）
+class SearchQuestionEmbedding(BaseModel):
+    book_id: str
+    question_embedding: str # 题目的图片的embedding ; json.dumps([])
+    top_k: int = 1
+
+# 搜题目请求数据结构（输入题目图片的向量 和题目图片的OCR结果）
+class SearchQuestionTextAndEmbedding(BaseModel):
+    book_id: str
+    question_ocr: str  # 题目的paddleOCR结果
+    question_embedding: str # 题目的图片的embedding   json.dumps([])
+    top_k: int = 1
+
+class DeleteBook(BaseModel):
+    book_id: str
+
+
+# 检查文件扩展名是否允许
+def allowed_file(filename: str) -> bool:
+    return "." in filename and filename.rsplit(".", 1)[1].lower() in ALLOWED_EXTENSIONS
+
+def setup_logger():
+    # 创建logger对象（单例，按名称唯一）
+    logger = logging.getLogger('search_question')
+    # 避免重复初始化：如果已有处理器，直接返回
+    if logger.handlers:
+        return logger
+
+    logger.setLevel(logging.INFO)
+    # 禁用日志传播到父Logger
+    logger.propagate = False
+
+    # 日志目录路径（使用脚本所在目录，替代__path__）
+    current_dir = os.path.dirname(os.path.abspath(__file__))
+    log_dir = os.path.join(current_dir, "log")
+    if not os.path.exists(log_dir):
+        os.makedirs(log_dir, exist_ok=True)  # 增加exist_ok避免多线程冲突
+
+    log_file = os.path.join(log_dir, "search_question.log")
+
+    # 创建文件处理器（延迟打开文件）
+    file_handler = logging.FileHandler(log_file, encoding='utf-8', delay=True)
+    file_handler.setLevel(logging.INFO)
+
+    # 设置日志格式
+    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+    file_handler.setFormatter(formatter)
+
+    # 添加处理器
+    logger.addHandler(file_handler)
+
+    return logger
+
+# 创建全局logger实例
+logger_es = setup_logger()
+
+# 1、文件上传API(接收拆书传入的excel文件)
+@app.post("/upload/excel", response_model=UploadResponse)
+async def upload_excel(
+        book_id: str = Form(...),  # 必填字段
+        book_name: str = Form(...),  # 必填字段
+        file: UploadFile = File(...)
+):
+    # 检查文件类型是否允许
+    if not allowed_file(file.filename):
+        logger_es.info(f"/upload/excel : 文件类型不允许。允许的类型: {', '.join(ALLOWED_EXTENSIONS)}")
+        raise HTTPException(
+            status_code=400,
+            detail=f"文件类型不允许。允许的类型: {', '.join(ALLOWED_EXTENSIONS)}"
+        )
+
+    # 1、生成安全的文件名
+    file_ext = os.path.splitext(file.filename)[1]
+    safe_filename = f"{book_id}_{book_name}{file_ext}"
+    file_path = UPLOAD_DIR / safe_filename
+
+    # 2、保存excel文件
+    try:
+        with open(file_path, "wb") as f:
+            contents = await file.read()
+            f.write(contents)
+    except Exception as e:
+        logger_es.info(f"/upload/excel : 保存excel文件时出错: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"保存excel文件时出错: {str(e)}；book_name:{book_name}")
+    finally:
+        await file.close()
+
+    # 3、保存清洗后的excel进json文件
+    try:
+        sheet_name = "题库数据"
+        data = pre_data.read_excel(file_path, sheet_name,  book_id, book_name)
+
+        safe_filename_json = f"{book_id}_{book_name}.json"
+        file_path_json = UPLOAD_DIR / safe_filename_json
+
+        pre_data.write2json(file_path_json, data) # excel保存为json数据
+    except Exception as e:
+        logger_es.info(f"/upload/excel : 清洗excel数据出错: {str(e)}")
+        raise HTTPException(status_code=520, detail=f"清洗excel数据出错: {str(e)}；book_name:{book_name}")
+
+    # 4、将拆书数据插入es数据库
+    try:
+        es.insert_doc_batch(index_name, data)
+    except Exception as e:
+        logger_es.info(f"/upload/excel : 数据插入es出错: {str(e)}")
+        raise HTTPException(status_code=530, detail=f"数据插入es出错: {str(e)}")
+
+    logger_es.info(f"/upload/excel : 数据插入es success: book_id：{str(book_id)}；book_name：{book_name}；file: {safe_filename}")
+
+    return {
+        "status": "success",
+        "message": "文件插入 ES 成功",
+        "filename": safe_filename,
+        "file_path": str(file_path),
+        "book_id": book_id,
+        "book_name": book_name
+    }
+
+
+# 2、依据book_id删除es库里对应的数据
+@app.post("/delete_book")
+async def delete_book(input: DeleteBook):
+    book_id = input.book_id
+    logger_es.info(f"delete_book : {input}")
+    try:
+        es.delete_book_id(index_name, book_id)
+    except Exception as e:
+        logger_es.info(f"delete_book : 删除 book_id:{book_id} 数据出错：{e}。")
+        raise HTTPException(status_code=500, detail=f"删除 book_id:{book_id} 数据出错：{e}。")
+
+    return { "status": "success", "msg":f"成功删除 book_id：{book_id} 图书数据。"}
+
+
+# 3、搜图书的整页
+@app.post("/search_page")
+async def search_page(input: SearchPage):
+    logger_es.info(f"search_page : {input}")
+    book_id = input.book_id
+    image_ocr = input.image_ocr
+    top_k = input.top_k
+    try:
+        res = await es.search_page( index_name, book_id, image_ocr, top_k)
+    except Exception as e:
+        logger_es.info(f"search_page : 搜索 book_id:{book_id}，image_ocr：{image_ocr}，出错：{e}。")
+        raise HTTPException(status_code=500, detail=f"search_page 接口 book_id:{book_id}，image_ocr：{image_ocr}，出错：{e}。")
+    return {"status": "success", "es_search":res}
+
+
+# 3、搜图书中的某个题目(只使用题目图片的OCR结果）
+@app.post("/search_question_text")
+async def search_question_text(input: SearchQuestionText):
+    book_id = input.book_id
+    image_ocr = input.image_ocr
+    question_ocr = input.question_ocr
+    top_k = input.top_k
+
+    if image_ocr: # 如果输入了整页图片的paddleOCR结果，也输入了题目的paddleOCR结果；先确定题目所在的页，再搜索题目
+        try:
+            logger_es.info(f"search_question ：image_ocr 非空: {input}")
+            res = await es.search_page_question(index_name, book_id, image_ocr, question_ocr, top_k)
+        except Exception as e:
+            logger_es.info(  f"search_question : 搜索 book_id:{book_id}，image_ocr 非空:{image_ocr}; question_ocr：{question_ocr}，出错：{e}。")
+            raise HTTPException(status_code=502,  detail=f"search_question 接口 book_id:{book_id}，image_ocr：{image_ocr}，question_ocr：{question_ocr}，出错：{e}。")
+    else:
+        try:
+            logger_es.info(f"search_question ： image_ocr 为空 : {input}")
+            res = await es.search_question( index_name, book_id, question_ocr, top_k)
+        except Exception as e:
+            logger_es.info(f"search_question : 搜索 book_id:{book_id}，image_ocr 为空:{image_ocr}; question_ocr：{question_ocr}，出错：{e}。")
+            raise HTTPException(status_code=500, detail=f"search_question 接口 book_id:{book_id}，image_ocr：{image_ocr}，question_ocr：{question_ocr}，出错：{e}。")
+
+    return {"status": "success", "es_search":res}
+
+
+# 4、搜图中的某个题目（只使用题目图片和ocr的向量）
+@app.post("/search_question_embedding")
+async def search_question_embedding(input: SearchQuestionEmbedding):
+    logger_es.info(f"search_question_embedding : book_id: {input.book_id}")
+    book_id = input.book_id
+    question_embedding = input.question_embedding
+    top_k = input.top_k
+
+    try:
+        question_embedding = json.loads(question_embedding)
+        res = await es.search_question_embedding(index_name, book_id, question_embedding, top_k)
+    except Exception as e:
+        logger_es.info(f"search_question_embedding : 搜索 book_id:{book_id}，出错：{e}。")
+        raise HTTPException(status_code=500, detail=f"search_question_embedding 接口 book_id:{book_id}，出错：{e}。")
+
+    return {"status": "success", "es_search": res}
+
+
+# 5、搜图中某个题目（联合文本搜索和向量搜索）
+@app.post("/search_question_text_and_embedding")
+async def search_question_text_and_embedding(input: SearchQuestionTextAndEmbedding):
+    logger_es.info(f"search_question_text_and_embedding : {input.book_id}")
+    book_id = input.book_id
+    question_ocr = input.question_ocr
+    question_embedding = input.question_embedding
+
+    top_k = input.top_k
+
+    try:
+        question_embedding = json.loads(question_embedding)
+        res = await es.search_question_textAndEmbedding(index_name, book_id, question_ocr, question_embedding, top_k)
+    except Exception as e:
+        logger_es.info(f"search_question_text_and_embedding : 搜索 book_id:{book_id}，出错：{e}。")
+        raise HTTPException(status_code=500, detail=f"search_question_text_and_embedding 接口 book_id:{book_id}，出错：{e}。")
+
+    return {"status": "success", "es_search": res}
+
+
+if __name__ == "__main__":
+    uvicorn.run(app="api_service:app", host="0.0.0.0", port=31001, workers=1) # 部署的服务是 31001
+
+    # cd /home/liuxin/work/search_question  # 61.170.32.8 服务器
+    # conda activate search_book
+    # nohup python -u api_service.py > api_service.log 2>&1 &
+    # tail -f log/search_question.log
+
+

api_tst.py

+import requests
+import re,json,os,sys
+
+
+def get_page_image_url(bankId="760261"):
+    # 输入题目的bankid 输出题目所在整页的url链接
+    url = "https://rays7.5rs.me/matrix/v1.0/aIRecognized/getPageInfoByBankId"
+
+    headers = {
+        "token": "whlg2025!",
+        "Only-For-Backend": "y"
+    }
+    data = {
+        "bankId": bankId
+    }
+
+    response = requests.get(url, headers=headers, params=data)
+    response = response.text
+    sourceImageUrl = json.loads(response)['data']['sourceImageUrl']
+
+    return sourceImageUrl
+
+# get_page_image_url()
+
+
+def insert_excel(data):
+    # 1、excel 数据插入es数据库
+    url = 'http://localhost:31001/upload/excel'
+    # url = 'http://61.170.32.8:31001/upload/excel'
+    headers = { 'accept': 'application/json' }
+    file_path = data['file_path']
+    # 上传文件
+    with open(file_path, 'rb') as file:
+        files = {
+            'file': (file_path, file),
+        }
+
+        # 发送请求
+        response = requests.post(url, headers=headers, data=data, files=files)
+
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    print(f"响应内容: {response.json()}")
+
+
+def delete_es_book(book_id="12663121"):
+    # 2、指定book_id 删除es中对应的图书数据
+    url = 'http://localhost:31001/delete_book'
+    # url = 'http://61.170.32.8:31001/delete_book'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    print(res)
+
+
+def search_page(book_id, image_ocr):
+    # 3、搜书图书的整页
+    url = 'http://localhost:31001/search_page'
+    # url = 'http://61.170.32.8:31001/search_page'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id,
+        "image_ocr": image_ocr,
+        "top_k": 1
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+    bankId = res['es_search'][0]['_source']['bankId']
+    print("bankId: ", bankId)
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    return res
+
+def search_question_text(book_id, question_ocr, image_ocr=""):
+    # 3、搜题(只用题目的ocr结果进行搜题）
+    url = 'http://localhost:31001/search_question_text'
+    # url = 'http://61.170.32.8:31001/search_question_text'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id,
+        "image_ocr": image_ocr,
+        "question_ocr": question_ocr,
+        "top_k": 1
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+
+    bankId = res['es_search'][0]['_source']['bankId']
+    print("bankId: ", bankId)
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    return res
+
+def search_question_embedding(book_id, question_embedding):
+    # 4、搜题(只用题目的ocr和图片的embedding数据）
+    url = 'http://localhost:31001/search_question_embedding'
+    # url = 'http://61.170.32.8:31001/search_question_embedding'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id,
+        "question_embedding": question_embedding,
+        "top_k": 1
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+
+    bankId = res['es_search'][0]['_source']['bankId']
+    print("bankId: ", bankId)
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    return res
+
+def search_question_text_and_embedding(book_id, question_ocr, question_embedding):
+    # 5、搜题(使用题目ocr的文本搜题，再使用题目ocr和图片整体的向量搜题，联合两个搜索的得分）
+    url = 'http://localhost:31001/search_question_text_and_embedding'
+    # url = 'http://61.170.32.8:31001/search_question_text_and_embedding'
+    headers = {
+        'accept': 'application/json',
+    }
+
+    # 表单数据
+    data = {
+        "book_id": book_id,
+        "question_ocr": question_ocr,
+        "question_embedding": question_embedding,
+        "top_k": 1
+    }
+    data = json.dumps(data, ensure_ascii=False)
+    response = requests.post(url, headers=headers, data=data )
+    # 输出响应结果
+    print(f"状态码: {response.status_code}")
+    res = response.json()
+
+    bankId = res['es_search'][0]['_source']['bankId']
+    print("bankId: ", bankId)
+
+    res = json.dumps(res, ensure_ascii=False, indent=4)
+    return res
+
+
+if __name__ == "__main__":
+    # 1、es中插入excel数据
+
+    # data = {'book_id': '12663121', 'book_name': '衔接教材地理', "file_path": '/home/liuxin/work/search_question/data/12663121-衔接教材地理-原图/12663121-衔接教材地理.xlsx' } # 64
+    # data = {'book_id': '12667382', 'book_name': '25春北师一数暑假作业',  "file_path": '/home/liuxin/work/search_question/data/12667382-25春北师一数暑假作业-原图/12667382-25春北师一数暑假作业.xlsx'} # 44
+    data = {'book_id': '12664728', 'book_name': '课计划·七年级英语·RJ·上册（出血文件）',   "file_path": '/home/liuxin/work/search_question/data/12664728-课计划·七年级英语·RJ·上册（出血文件）-原图/12664728-课计划·七年级英语·RJ·上册（出血文件）.xlsx'} # 96
+    data = {'book_id': '12670279', 'book_name': '2025版ZT7地-下册横版《锦上添花（期末大赢家）》下册-新编文件5.8',  "file_path": '/home/liuxin/work/search_question/data/12670279-12670279-2025版ZT7地-下册横版《锦上添花（期末大赢家）》下册-新编文件5.8-原图/12670279-12670279-2025版ZT7地-下册横版《锦上添花（期末大赢家）》下册-新编文件5.8.xlsx'} # 26
+    data = {'book_id': '12677472', 'book_name': '衔接教材地理', "file_path": '/home/liuxin/work/search_question/data/12677472-语文1-160-原图/12677472-语文1-160.xlsx'}
+    data = {'book_id': '12677471', 'book_name': '卷1-132', "file_path": '/home/liuxin/work/search_question/data/12677471-卷1-132-原图/12677471-卷1-132.xlsx'}
+    data = {'book_id': '12677035', 'book_name': '2025《创新教程》新高考试题精选生物学', "file_path": '/home/liuxin/work/search_question/data/12677035-2025《创新教程》新高考试题精选生物学-原图/12677035-2025《创新教程》新高考试题精选生物学.xlsx'}
+    data = {'book_id': '12668851', 'book_name': '高二暑假作业化学', "file_path": '/home/liuxin/work/search_question/data/12668851-高二暑假作业化学-原图/12668851-高二暑假作业化学.xlsx'}
+    data = {"book_id": "12671977", "book_name":"暑假生活·学期总复习八年级物理通用版6", "file_path": "/home/liuxin/work/search_question/data/12671977-暑假生活·学期总复习八年级物理通用版6-原图/12671977-暑假生活·学期总复习八年级物理通用版6.xlsx"}
+
+    # print("\n1、es中插入excel数据")
+    # insert_excel(data)
+
+    # 1.2、插入整个文件夹的数据进入es
+    path_dir = "/home/liuxin/work/search_question/data/拆书平台下载excel文件_添加字段内容"
+    file_names = os.listdir(path_dir)
+    file_names = [file_name for file_name in file_names if file_name.endswith(".xlsx")]
+    print(f"文件夹 {path_dir} 共{len(file_names)}个excel文件")
+    file_names = [file_name for file_name in file_names if  "-" in file_name]
+    print(f"文件夹 {path_dir} 共{len(file_names)}个excel文件")
+    book_ids = [file_name.split("-")[0] for file_name in file_names ]
+    for book_id, file_name in zip(book_ids, file_names):
+        file = os.path.join(path_dir, file_name)
+        input = {"book_id":book_id, "book_name":file_name[:-5], "file_path":file}
+        insert_excel(input)
+
+    # # 2、指定 book_id 删除es中对应的数据
+    # print("\n2、指定 book_id 删除es中对应的数据")
+    book_id = "12664728"
+    book_id = "12670279"
+    book_id = "12667382"
+    book_id = "12663121"
+    # delete_es_book(book_id)
+
+    # # # # # 3、搜书图书的整页
+    # print("\n3、搜书图书的整页")
+    # book_id = "12671977"
+    # image_ocr = "物理"
+    # res = search_page(book_id, image_ocr)
+    # print(res)
+
+    # # # 4、搜题 只搜索文本数据
+    print("\n4、搜题 只搜索文本数据")
+    book_id = "12667382"
+    question_ocr = "物理10"
+    image_ocr = ""
+
+    # res = search_question_text(book_id, question_ocr, image_ocr=image_ocr)
+    # print(res)
+
+    # 5、搜题 只搜索题目向量
+    print("\n5、搜题 只搜索题目向量")
+    book_id = "12667382"
+    question_embedding = [
+            0.00543212890625,
+            -0.005035400390625,
+            0.00714111328125,
+            0.06591796875,
+            -0.032958984375,
+            -0.0380859375,
+            -0.0255126953125,
+            -0.046630859375,
+            0.01031494140625,
+            0.036376953125,
+            0.013916015625,
+            0.0255126953125,
+            -0.0107421875,
+            -0.04345703125,
+            0.0008697509765625,
+            0.02587890625,
+            -0.0201416015625,
+            -0.02099609375,
+            -0.00830078125,
+            0.033203125,
+            -0.01007080078125,
+            0.0224609375,
+            -0.04931640625,
+            0.0206298828125,
+            0.009765625,
+            0.02392578125,
+            0.00095367431640625,
+            0.03369140625,
+            0.005035400390625,
+            0.07373046875,
+            0.0262451171875,
+            0.015625,
+            -0.021728515625,
+            0.0054931640625,
+            0.0308837890625,
+            0.055419921875,
+            -0.0517578125,
+            0.011474609375,
+            -0.023681640625,
+            0.0235595703125,
+            -0.00128173828125,
+            0.0096435546875,
+            0.003936767578125,
+            -0.01953125,
+            -0.05126953125,
+            0.001617431640625,
+            -0.005218505859375,
+            -0.01409912109375,
+            -0.026611328125,
+            0.0198974609375,
+            0.02001953125,
+            0.004974365234375,
+            0.053955078125,
+            -0.0634765625,
+            -0.0654296875,
+            -0.03369140625,
+            -0.08154296875,
+            0.06005859375,
+            0.0223388671875,
+            -0.044921875,
+            -0.0283203125,
+            0.01483154296875,
+            0.150390625,
+            0.026611328125,
+            0.02392578125,
+            -0.00125885009765625,
+            -0.053955078125,
+            -0.03759765625,
+            -0.0390625,
+            0.02734375,
+            -0.01385498046875,
+            0.00140380859375,
+            0.0218505859375,
+            -0.01025390625,
+            -0.0205078125,
+            0.04638671875,
+            0.0145263671875,
+            -0.00927734375,
+            0.01025390625,
+            -0.0225830078125,
+            -0.00909423828125,
+            -0.0142822265625,
+            0.02978515625,
+            0.0101318359375,
+            -0.072265625,
+            -0.049560546875,
+            0.0311279296875,
+            0.0101318359375,
+            -0.00445556640625,
+            -0.03369140625,
+            0.0615234375,
+            -0.021240234375,
+            -0.034912109375,
+            -0.004150390625,
+            0.07177734375,
+            0.0262451171875,
+            -0.013671875,
+            0.03369140625,
+            0.021728515625,
+            0.0252685546875,
+            -0.00982666015625,
+            -0.0028228759765625,
+            -0.00151824951171875,
+            0.003753662109375,
+            0.004791259765625,
+            -0.03759765625,
+            0.025146484375,
+            0.0235595703125,
+            -0.0103759765625,
+            0.0084228515625,
+            -0.0191650390625,
+            0.044921875,
+            0.052001953125,
+            -0.053955078125,
+            0.0206298828125,
+            0.036376953125,
+            0.01202392578125,
+            0.0196533203125,
+            0.025146484375,
+            -0.000457763671875,
+            -0.0033721923828125,
+            -0.0101318359375,
+            0.005035400390625,
+            0.0089111328125,
+            0.002227783203125,
+            -0.041015625,
+            0.00927734375,
+            0.10693359375,
+            0.01043701171875,
+            0.00616455078125,
+            0.013916015625,
+            0.0035858154296875,
+            -0.0283203125,
+            -0.06591796875,
+            0.016845703125,
+            -0.0615234375,
+            -0.01385498046875,
+            -0.05029296875,
+            -0.01556396484375,
+            -0.0128173828125,
+            -0.0140380859375,
+            0.00732421875,
+            -0.0164794921875,
+            0.01239013671875,
+            0.0150146484375,
+            -0.0169677734375,
+            -0.142578125,
+            -0.0008087158203125,
+            -0.007171630859375,
+            0.0033416748046875,
+            0.03662109375,
+            -0.00341796875,
+            -0.0198974609375,
+            -0.03955078125,
+            -0.06640625,
+            -0.05712890625,
+            0.0133056640625,
+            -0.0277099609375,
+            -0.005462646484375,
+            -0.0224609375,
+            0.002166748046875,
+            0.0296630859375,
+            -0.030517578125,
+            -0.029052734375,
+            0.030517578125,
+            -0.0162353515625,
+            -0.0252685546875,
+            -0.0174560546875,
+            -0.023193359375,
+            0.005340576171875,
+            -0.026611328125,
+            -0.006011962890625,
+            -0.01611328125,
+            -0.033203125,
+            -0.000820159912109375,
+            0.04248046875,
+            -0.0301513671875,
+            0.019287109375,
+            0.00909423828125,
+            0.0400390625,
+            0.03564453125,
+            0.030517578125,
+            0.0140380859375,
+            -0.0014495849609375,
+            0.01251220703125,
+            -0.0556640625,
+            0.04248046875,
+            -0.056640625,
+            -0.030517578125,
+            -0.009033203125,
+            -0.01165771484375,
+            -0.0277099609375,
+            0.0087890625,
+            0.024658203125,
+            -0.043701171875,
+            0.0146484375,
+            -0.020751953125,
+            0.01007080078125,
+            0.0164794921875,
+            0.06591796875,
+            -0.06298828125,
+            0.0303955078125,
+            -0.020263671875,
+            -0.007171630859375,
+            0.004425048828125,
+            0.0020751953125,
+            -0.01373291015625,
+            0.050537109375,
+            -0.08203125,
+            -0.036865234375,
+            0.019775390625,
+            -0.0050048828125,
+            0.06640625,
+            -0.00823974609375,
+            0.04248046875,
+            -0.02734375,
+            0.004425048828125,
+            0.006500244140625,
+            -0.00537109375,
+            -0.0546875,
+            0.01470947265625,
+            0.0089111328125,
+            0.0025787353515625,
+            -0.00860595703125,
+            0.018310546875,
+            -0.0208740234375,
+            -0.06689453125,
+            -0.00592041015625,
+            -0.0303955078125,
+            -0.0021514892578125,
+            0.00372314453125,
+            0.0218505859375,
+            -0.0301513671875,
+            0.02587890625,
+            -0.01239013671875,
+            0.04541015625,
+            0.03662109375,
+            0.07421875,
+            0.0225830078125,
+            0.000385284423828125,
+            0.06396484375,
+            -0.0020294189453125,
+            0.008056640625,
+            0.0111083984375,
+            0.0081787109375,
+            0.033447265625,
+            -0.01544189453125,
+            0.09912109375,
+            -0.00994873046875,
+            0.0208740234375,
+            -0.044921875,
+            -0.017333984375,
+            0.0211181640625,
+            0.08056640625,
+            -0.02294921875,
+            0.062255859375,
+            0.01708984375,
+            -0.011474609375,
+            0.03125,
+            0.018798828125,
+            0.0019683837890625,
+            0.0390625,
+            -0.0052490234375,
+            -0.01312255859375,
+            -0.002044677734375,
+            -0.046630859375,
+            0.015625,
+            0.037353515625,
+            0.002777099609375,
+            -0.00811767578125,
+            0.0233154296875,
+            -0.007232666015625,
+            0.039794921875,
+            0.009765625,
+            0.01708984375,
+            0.043212890625,
+            0.0101318359375,
+            0.02783203125,
+            -0.021484375,
+            -0.01470947265625,
+            -0.013671875,
+            0.01470947265625,
+            -0.032470703125,
+            -0.0185546875,
+            -0.00506591796875,
+            0.03125,
+            -0.03125,
+            0.048095703125,
+            -0.01165771484375,
+            0.0296630859375,
+            0.017822265625,
+            -0.011474609375,
+            0.00787353515625,
+            0.005645751953125,
+            -0.0093994140625,
+            0.0380859375,
+            -0.017333984375,
+            0.0255126953125,
+            -0.01806640625,
+            0.033447265625,
+            -0.001739501953125,
+            -0.0191650390625,
+            0.0054931640625,
+            0.053466796875,
+            -0.0308837890625,
+            -0.006072998046875,
+            0.0179443359375,
+            0.025634765625,
+            -0.01318359375,
+            0.01214599609375,
+            -0.0040283203125,
+            0.03125,
+            0.047119140625,
+            0.056640625,
+            0.01116943359375,
+            -0.0235595703125,
+            0.00872802734375,
+            0.003936767578125,
+            -0.000652313232421875,
+            -0.004638671875,
+            -0.00341796875,
+            0.0035400390625,
+            0.0322265625,
+            0.0169677734375,
+            0.008056640625,
+            -0.0262451171875,
+            -0.080078125,
+            -0.04638671875,
+            0.017822265625,
+            -0.01544189453125,
+            -0.0296630859375,
+            0.033203125,
+            0.10693359375,
+            0.038330078125,
+            0.00286865234375,
+            0.04541015625,
+            0.021484375,
+            -0.04931640625,
+            0.01953125,
+            -0.035400390625,
+            -0.07958984375,
+            -0.07177734375,
+            -0.004119873046875,
+            0.0208740234375,
+            0.10498046875,
+            -0.006011962890625,
+            -0.04248046875,
+            -0.045654296875,
+            -0.001434326171875,
+            0.00994873046875,
+            0.0164794921875,
+            0.0277099609375,
+            0.006378173828125,
+            -0.0286865234375,
+            0.0191650390625,
+            -0.02587890625,
+            0.011474609375,
+            0.0703125,
+            0.00732421875,
+            -0.032470703125,
+            -0.0211181640625,
+            -0.05615234375,
+            0.01092529296875,
+            0.031494140625,
+            0.0247802734375,
+            -0.00372314453125,
+            -0.0013427734375,
+            -0.06982421875,
+            -0.00714111328125,
+            0.0196533203125,
+            0.017333984375,
+            0.01336669921875,
+            -0.00188446044921875,
+            -0.01019287109375,
+            -0.00836181640625,
+            0.035400390625,
+            -0.0400390625,
+            0.01177978515625,
+            0.009033203125,
+            0.004425048828125,
+            0.0157470703125,
+            0.0015716552734375,
+            0.007354736328125,
+            -0.037841796875,
+            0.01214599609375,
+            -0.002685546875,
+            -0.0233154296875,
+            0.0107421875,
+            -0.052001953125,
+            -0.057373046875,
+            0.007354736328125,
+            0.007171630859375,
+            -0.02734375,
+            -0.005523681640625,
+            -0.0010528564453125,
+            -0.0106201171875,
+            0.0022125244140625,
+            0.08642578125,
+            -0.033447265625,
+            0.03125,
+            -0.0225830078125,
+            -0.03125,
+            0.007049560546875,
+            -0.0712890625,
+            -0.0023956298828125,
+            0.006317138671875,
+            -0.056640625,
+            0.0206298828125,
+            -0.017333984375,
+            0.048828125,
+            0.0419921875,
+            -0.0037078857421875,
+            0.02978515625,
+            0.0159912109375,
+            0.04443359375,
+            -0.060302734375,
+            -0.038330078125,
+            0.0277099609375,
+            0.036865234375,
+            0.0322265625,
+            -0.006011962890625,
+            -0.022705078125,
+            -0.050537109375,
+            0.041748046875,
+            0.01507568359375,
+            0.007232666015625,
+            0.050048828125,
+            0.041015625,
+            -0.0240478515625,
+            0.006561279296875,
+            0.000301361083984375,
+            -0.01446533203125,
+            0.01507568359375,
+            -0.0556640625,
+            -0.02734375,
+            -0.0081787109375,
+            0.04736328125,
+            0.0025787353515625,
+            -0.0283203125,
+            0.01129150390625,
+            -0.0252685546875,
+            0.0225830078125,
+            0.00421142578125,
+            -0.004791259765625,
+            0.005401611328125,
+            0.006011962890625,
+            -0.057861328125,
+            -0.0289306640625,
+            0.008544921875,
+            -0.0115966796875,
+            0.022705078125,
+            -0.008056640625,
+            -0.01416015625,
+            0.0021209716796875,
+            -0.0038909912109375,
+            0.01025390625,
+            -0.0247802734375,
+            0.01275634765625,
+            0.031494140625,
+            -0.00015926361083984375,
+            -0.004119873046875,
+            0.041259765625,
+            -0.040283203125,
+            0.052734375,
+            -0.052734375,
+            -0.0225830078125,
+            -0.06884765625,
+            -0.07421875,
+            -0.0341796875,
+            0.0196533203125,
+            0.0038604736328125,
+            -0.041015625,
+            -0.005615234375,
+            -0.039794921875,
+            -0.0205078125,
+            0.04931640625,
+            -0.0289306640625,
+            0.006561279296875,
+            0.020751953125,
+            -0.03369140625,
+            0.020263671875,
+            -0.039794921875,
+            0.0081787109375,
+            -0.0020294189453125,
+            0.0218505859375,
+            0.01611328125,
+            -0.0281982421875,
+            -0.027099609375,
+            0.00131988525390625,
+            -0.0654296875,
+            0.023681640625,
+            -0.006256103515625,
+            -0.0211181640625,
+            -0.006103515625,
+            -0.034912109375,
+            -0.00299072265625,
+            -0.0059814453125,
+            -0.036376953125,
+            -0.0174560546875,
+            -0.056640625,
+            0.000316619873046875,
+            -0.033935546875,
+            0.00726318359375,
+            -0.033447265625,
+            0.06591796875,
+            0.0018768310546875,
+            0.02734375,
+            -0.04345703125,
+            0.032958984375,
+            -0.01953125,
+            -0.0034332275390625,
+            0.01300048828125,
+            0.000713348388671875,
+            -0.008056640625,
+            -0.004730224609375,
+            -0.0341796875,
+            0.030517578125,
+            -0.0255126953125,
+            0.0286865234375,
+            -0.04638671875,
+            0.025146484375,
+            -0.03515625,
+            0.001220703125,
+            -0.01068115234375,
+            0.043212890625,
+            -0.01416015625,
+            -0.0223388671875,
+            -0.03369140625,
+            -0.0059814453125,
+            0.007049560546875,
+            0.0220947265625,
+            -0.0281982421875,
+            -0.00811767578125,
+            -0.00799560546875,
+            0.0263671875,
+            0.01373291015625,
+            0.00194549560546875,
+            0.20703125,
+            -0.0076904296875,
+            0.06591796875,
+            -0.0059814453125,
+            0.01043701171875,
+            -0.01251220703125,
+            0.038330078125,
+            -0.0087890625,
+            0.09765625,
+            0.003082275390625,
+            0.0096435546875,
+            0.000152587890625,
+            0.02392578125,
+            -0.04638671875,
+            -0.007781982421875,
+            -0.0030975341796875,
+            -0.00098419189453125,
+            -0.0181884765625,
+            -0.007232666015625,
+            -0.0235595703125,
+            0.033447265625,
+            0.0125732421875,
+            -0.00171661376953125,
+            0.022216796875,
+            -0.000278472900390625,
+            -0.02392578125,
+            0.0294189453125,
+            -0.0128173828125,
+            0.039794921875,
+            -0.0247802734375,
+            -0.049560546875,
+            0.003631591796875,
+            0.0206298828125,
+            0.0164794921875,
+            0.028564453125,
+            -0.01251220703125,
+            0.02294921875,
+            -0.00099945068359375,
+            -0.022216796875,
+            -0.050537109375,
+            0.001861572265625,
+            -0.0191650390625,
+            -0.045654296875,
+            -0.023681640625,
+            0.004119873046875,
+            0.050048828125,
+            -0.007232666015625,
+            0.05029296875,
+            -0.027099609375,
+            -0.0169677734375,
+            0.035888671875,
+            -0.02001953125,
+            -0.0040283203125,
+            0.01043701171875,
+            0.0035400390625,
+            -0.0059814453125,
+            0.0263671875,
+            -0.01220703125,
+            -0.016357421875,
+            0.01483154296875,
+            -0.0390625,
+            -0.00396728515625,
+            0.04345703125,
+            0.023193359375,
+            -0.0172119140625,
+            0.021240234375,
+            -0.04736328125,
+            0.006866455078125,
+            0.036376953125,
+            -0.0289306640625,
+            0.0208740234375,
+            0.011474609375,
+            -0.0260009765625,
+            0.01904296875,
+            0.016357421875,
+            -0.04931640625,
+            -0.0478515625,
+            0.0213623046875,
+            -0.01275634765625,
+            -0.032470703125,
+            -0.0084228515625,
+            -0.001922607421875,
+            0.0191650390625,
+            0.008544921875,
+            -0.037353515625,
+            0.0111083984375,
+            -0.022705078125,
+            -0.04052734375,
+            0.033447265625,
+            -0.01116943359375,
+            -0.03369140625,
+            -0.0167236328125,
+            -0.0303955078125,
+            0.0191650390625,
+            -0.06591796875,
+            0.00433349609375,
+            -0.078125,
+            -0.00732421875,
+            0.04150390625,
+            0.00286865234375,
+            0.0157470703125,
+            -0.00008440017700195312,
+            0.041015625,
+            -0.034423828125,
+            0.053466796875,
+            0.005218505859375,
+            0.01239013671875,
+            -0.006072998046875,
+            -0.00628662109375,
+            0.018798828125,
+            0.00151824951171875,
+            0.01165771484375,
+            0.0164794921875,
+            0.0089111328125,
+            0.0247802734375,
+            0.024658203125,
+            -0.0031585693359375,
+            -0.0181884765625,
+            -0.0103759765625,
+            -0.04541015625,
+            0.00323486328125,
+            0.0157470703125,
+            -0.004791259765625,
+            0.0308837890625,
+            -0.03076171875,
+            0.00506591796875,
+            0.02392578125,
+            -0.0179443359375,
+            0.0269775390625,
+            -0.003509521484375,
+            -0.0181884765625,
+            0.020263671875,
+            0.03076171875,
+            0.00145721435546875,
+            -0.004547119140625,
+            0.0167236328125,
+            0.035400390625,
+            -0.0206298828125,
+            -0.0810546875,
+            -0.0113525390625,
+            -0.02294921875,
+            0.0022735595703125,
+            0.0250244140625,
+            -0.006561279296875,
+            0.0223388671875,
+            0.043212890625,
+            0.03564453125,
+            -0.009765625,
+            0.036376953125,
+            -0.0028228759765625,
+            -0.003204345703125,
+            -0.041748046875,
+            -0.001495361328125,
+            -0.05419921875,
+            -0.04248046875,
+            -0.01708984375,
+            -0.002777099609375,
+            -0.01251220703125,
+            -0.001739501953125,
+            -0.0084228515625,
+            0.00130462646484375,
+            -0.000579833984375,
+            -0.0262451171875,
+            0.01446533203125,
+            0.037841796875,
+            0.02001953125,
+            -0.0157470703125,
+            -0.017333984375,
+            0.006317138671875,
+            0.0125732421875,
+            -0.0206298828125,
+            0.02197265625,
+            0.012939453125,
+            -0.0162353515625,
+            -0.068359375,
+            0.0250244140625,
+            0.006317138671875,
+            0.00201416015625,
+            -0.005126953125,
+            -0.00872802734375,
+            -0.06591796875,
+            0.0233154296875,
+            -0.01806640625,
+            -0.01312255859375,
+            -0.042236328125,
+            -0.03125,
+            -0.0198974609375,
+            -0.00193023681640625,
+            -0.004364013671875,
+            -0.0262451171875,
+            -0.0439453125,
+            -0.020263671875,
+            -0.01043701171875,
+            -0.0250244140625,
+            0.036865234375,
+            0.00946044921875,
+            -0.012939453125,
+            0.0213623046875,
+            -0.032470703125,
+            -0.048095703125,
+            0.020263671875,
+            0.00482177734375,
+            0.048583984375,
+            0.0301513671875,
+            -0.046630859375,
+            -0.021728515625,
+            -0.00408935546875,
+            0.0164794921875,
+            -0.006591796875,
+            -0.01409912109375,
+            0.0439453125,
+            -0.003936767578125,
+            -0.053955078125,
+            -0.0123291015625,
+            -0.025146484375,
+            -0.0185546875,
+            -0.061767578125,
+            0.0045166015625,
+            -0.01348876953125,
+            -0.025634765625,
+            0.0013580322265625,
+            -0.033447265625,
+            -0.0093994140625,
+            -0.039794921875,
+            0.04638671875,
+            -0.00799560546875,
+            -0.03955078125,
+            -0.015869140625,
+            0.0322265625,
+            0.0093994140625,
+            0.02978515625,
+            0.005828857421875,
+            -0.00011873245239257812,
+            -0.003936767578125,
+            0.0274658203125,
+            0.00701904296875,
+            0.000858306884765625,
+            -0.0146484375,
+            0.020263671875,
+            0.04150390625,
+            0.0216064453125,
+            -0.0164794921875,
+            0.043212890625,
+            0.0546875,
+            0.050048828125,
+            0.01470947265625,
+            -0.006561279296875,
+            0.00958251953125,
+            -0.0164794921875,
+            -0.01177978515625,
+            -0.03564453125,
+            -0.009765625,
+            0.007598876953125,
+            -0.00133514404296875,
+            -0.0322265625,
+            0.0211181640625,
+            0.029296875,
+            0.009765625,
+            -0.00151824951171875,
+            -0.0019073486328125,
+            -0.00830078125,
+            -0.032958984375,
+            0.028564453125,
+            -0.0186767578125,
+            -0.03369140625,
+            0.00897216796875,
+            -0.0040283203125,
+            -0.01104736328125,
+            0.01434326171875,
+            0.05419921875,
+            0.012939453125,
+            -0.0341796875,
+            -0.002471923828125,
+            -0.01446533203125,
+            0.04150390625,
+            0.04541015625,
+            0.0203857421875,
+            0.01251220703125,
+            -0.01348876953125,
+            0.01312255859375,
+            0.0052490234375,
+            0.0419921875,
+            -0.01092529296875,
+            -0.022705078125,
+            -0.0252685546875,
+            0.00836181640625,
+            -0.03759765625,
+            -0.03076171875,
+            0.009033203125,
+            -0.017822265625,
+            -0.00982666015625,
+            0.04736328125,
+            0.025634765625,
+            0.01165771484375,
+            -0.032470703125,
+            -0.0267333984375,
+            0.03515625,
+            0.0012664794921875,
+            -0.061767578125,
+            -0.0089111328125,
+            0.050048828125,
+            0.01275634765625,
+            0.0250244140625,
+            0.0191650390625,
+            0.036376953125,
+            0.005828857421875,
+            -0.0047607421875,
+            0.0023956298828125,
+            -0.031494140625,
+            -0.003143310546875,
+            -0.004669189453125,
+            0.0194091796875,
+            0.00897216796875,
+            -0.01104736328125,
+            0.0849609375,
+            0.007232666015625,
+            -0.0201416015625,
+            -0.0260009765625,
+            -0.0172119140625,
+            0.08984375,
+            0.0517578125,
+            -0.0260009765625,
+            -0.0260009765625,
+            -0.01239013671875,
+            -0.0247802734375,
+            0.0164794921875,
+            -0.0225830078125,
+            0.018798828125,
+            -0.038330078125,
+            -0.0308837890625,
+            -0.024658203125,
+            -0.002227783203125,
+            0.003204345703125,
+            0.0185546875,
+            -0.04443359375,
+            -0.004302978515625,
+            0.03271484375,
+            -0.01507568359375,
+            -0.00080108642578125,
+            0.038818359375,
+            0.0040283203125,
+            0.007049560546875,
+            -0.0198974609375,
+            0.004364013671875,
+            -0.02392578125,
+            -0.029296875,
+            -0.0037994384765625,
+            -0.033447265625,
+            0.01348876953125,
+            0.058837890625,
+            0.00811767578125,
+            0.0341796875,
+            0.0064697265625,
+            0.025146484375,
+            -0.000492095947265625,
+            0.0289306640625,
+            -0.0074462890625,
+            0.0189208984375,
+            0.031494140625,
+            -0.00518798828125,
+            -0.0283203125,
+            -0.0011444091796875,
+            0.03857421875,
+            0.036376953125,
+            0.026611328125,
+            0.005615234375,
+            -0.0032958984375,
+            -0.025146484375,
+            -0.02197265625,
+            0.0194091796875,
+            0.0181884765625,
+            0.07275390625,
+            -0.0045166015625,
+            0.025634765625,
+            -0.0286865234375,
+            0.0103759765625,
+            -0.01141357421875,
+            -0.03564453125,
+            0.049560546875,
+            -0.03173828125,
+            -0.0269775390625,
+            0.02734375,
+            0.041015625,
+            -0.01953125,
+            -0.0003528594970703125,
+            -0.0133056640625,
+            0.0203857421875,
+            -0.011474609375,
+            0.0150146484375,
+            0.0001010894775390625,
+            -0.01165771484375,
+            -0.026611328125,
+            0.03564453125,
+            -0.012939453125,
+            0.00024127960205078125,
+            -0.01446533203125,
+            0.0322265625,
+            -0.03125,
+            -0.0093994140625,
+            0.00066375732421875,
+            -0.02197265625,
+            0.0115966796875,
+            -0.033935546875,
+            -0.045166015625,
+            0.0361328125,
+            0.017822265625,
+            0.0322265625,
+            -0.0263671875,
+            0.04345703125,
+            -0.0133056640625,
+            -0.0478515625,
+            0.0087890625,
+            0.0208740234375,
+            -0.014892578125,
+            0.0135498046875,
+            0.044921875,
+            -0.006011962890625,
+            -0.0042724609375,
+            -0.0242919921875,
+            0.025146484375,
+            -0.021728515625,
+            -0.033935546875,
+            -0.0198974609375,
+            0.0172119140625,
+            0.00958251953125,
+            0.01806640625,
+            0.04345703125,
+            -0.01104736328125,
+            0.036376953125,
+            0.00141143798828125,
+            -0.03466796875,
+            -0.0001964569091796875,
+            -0.035400390625,
+            0.0191650390625,
+            0.0031280517578125,
+            0.00848388671875,
+            0.03076171875,
+            -0.0277099609375,
+            0.01953125,
+            0.08447265625,
+            0.0169677734375,
+            -0.02783203125,
+            -0.045166015625,
+            0.0181884765625,
+            0.039794921875,
+            -0.023681640625,
+            -0.00701904296875,
+            0.040771484375,
+            -0.020751953125,
+            0.06689453125,
+            -0.048828125,
+            -0.00164031982421875,
+            0.006256103515625,
+            0.01007080078125,
+            0.00323486328125,
+            -0.03662109375,
+            0.0419921875,
+            0.0002651214599609375,
+            -0.0301513671875,
+            -0.0111083984375,
+            0.072265625,
+            0.10009765625,
+            0.03564453125,
+            -0.0032501220703125,
+            0.06103515625,
+            0.0103759765625,
+            0.011474609375,
+            -0.034912109375,
+            -0.0115966796875,
+            0.025634765625,
+            -0.062255859375,
+            -0.01416015625,
+            0.037841796875,
+            -0.006683349609375,
+            -0.04736328125,
+            0.04345703125,
+            0.0021514892578125,
+            -0.0311279296875,
+            0.00885009765625,
+            -0.0107421875,
+            0.00372314453125,
+            -0.021728515625,
+            -0.00020503997802734375,
+            0.000263214111328125,
+            -0.01446533203125,
+            0.0028228759765625,
+            0.0277099609375
+          ]
+    question_embedding = json.dumps(question_embedding)
+    # res = search_question_embedding(book_id, question_embedding)
+    # print(res)
+
+
+    # 6、搜题 只搜索题目向量
+    print("\n6、搜题 搜索题目向量和题目ocr文本，联合打分")
+    book_id = "12667382"
+    question_embedding = [
+            0.00543212890625,
+            -0.005035400390625,
+            0.00714111328125,
+            0.06591796875,
+            -0.032958984375,
+            -0.0380859375,
+            -0.0255126953125,
+            -0.046630859375,
+            0.01031494140625,
+            0.036376953125,
+            0.013916015625,
+            0.0255126953125,
+            -0.0107421875,
+            -0.04345703125,
+            0.0008697509765625,
+            0.02587890625,
+            -0.0201416015625,
+            -0.02099609375,
+            -0.00830078125,
+            0.033203125,
+            -0.01007080078125,
+            0.0224609375,
+            -0.04931640625,
+            0.0206298828125,
+            0.009765625,
+            0.02392578125,
+            0.00095367431640625,
+            0.03369140625,
+            0.005035400390625,
+            0.07373046875,
+            0.0262451171875,
+            0.015625,
+            -0.021728515625,
+            0.0054931640625,
+            0.0308837890625,
+            0.055419921875,
+            -0.0517578125,
+            0.011474609375,
+            -0.023681640625,
+            0.0235595703125,
+            -0.00128173828125,
+            0.0096435546875,
+            0.003936767578125,
+            -0.01953125,
+            -0.05126953125,
+            0.001617431640625,
+            -0.005218505859375,
+            -0.01409912109375,
+            -0.026611328125,
+            0.0198974609375,
+            0.02001953125,
+            0.004974365234375,
+            0.053955078125,
+            -0.0634765625,
+            -0.0654296875,
+            -0.03369140625,
+            -0.08154296875,
+            0.06005859375,
+            0.0223388671875,
+            -0.044921875,
+            -0.0283203125,
+            0.01483154296875,
+            0.150390625,
+            0.026611328125,
+            0.02392578125,
+            -0.00125885009765625,
+            -0.053955078125,
+            -0.03759765625,
+            -0.0390625,
+            0.02734375,
+            -0.01385498046875,
+            0.00140380859375,
+            0.0218505859375,
+            -0.01025390625,
+            -0.0205078125,
+            0.04638671875,
+            0.0145263671875,
+            -0.00927734375,
+            0.01025390625,
+            -0.0225830078125,
+            -0.00909423828125,
+            -0.0142822265625,
+            0.02978515625,
+            0.0101318359375,
+            -0.072265625,
+            -0.049560546875,
+            0.0311279296875,
+            0.0101318359375,
+            -0.00445556640625,
+            -0.03369140625,
+            0.0615234375,
+            -0.021240234375,
+            -0.034912109375,
+            -0.004150390625,
+            0.07177734375,
+            0.0262451171875,
+            -0.013671875,
+            0.03369140625,
+            0.021728515625,
+            0.0252685546875,
+            -0.00982666015625,
+            -0.0028228759765625,
+            -0.00151824951171875,
+            0.003753662109375,
+            0.004791259765625,
+            -0.03759765625,
+            0.025146484375,
+            0.0235595703125,
+            -0.0103759765625,
+            0.0084228515625,
+            -0.0191650390625,
+            0.044921875,
+            0.052001953125,
+            -0.053955078125,
+            0.0206298828125,
+            0.036376953125,
+            0.01202392578125,
+            0.0196533203125,
+            0.025146484375,
+            -0.000457763671875,
+            -0.0033721923828125,
+            -0.0101318359375,
+            0.005035400390625,
+            0.0089111328125,
+            0.002227783203125,
+            -0.041015625,
+            0.00927734375,
+            0.10693359375,
+            0.01043701171875,
+            0.00616455078125,
+            0.013916015625,
+            0.0035858154296875,
+            -0.0283203125,
+            -0.06591796875,
+            0.016845703125,
+            -0.0615234375,
+            -0.01385498046875,
+            -0.05029296875,
+            -0.01556396484375,
+            -0.0128173828125,
+            -0.0140380859375,
+            0.00732421875,
+            -0.0164794921875,
+            0.01239013671875,
+            0.0150146484375,
+            -0.0169677734375,
+            -0.142578125,
+            -0.0008087158203125,
+            -0.007171630859375,
+            0.0033416748046875,
+            0.03662109375,
+            -0.00341796875,
+            -0.0198974609375,
+            -0.03955078125,
+            -0.06640625,
+            -0.05712890625,
+            0.0133056640625,
+            -0.0277099609375,
+            -0.005462646484375,
+            -0.0224609375,
+            0.002166748046875,
+            0.0296630859375,
+            -0.030517578125,
+            -0.029052734375,
+            0.030517578125,
+            -0.0162353515625,
+            -0.0252685546875,
+            -0.0174560546875,
+            -0.023193359375,
+            0.005340576171875,
+            -0.026611328125,
+            -0.006011962890625,
+            -0.01611328125,
+            -0.033203125,
+            -0.000820159912109375,
+            0.04248046875,
+            -0.0301513671875,
+            0.019287109375,
+            0.00909423828125,
+            0.0400390625,
+            0.03564453125,
+            0.030517578125,
+            0.0140380859375,
+            -0.0014495849609375,
+            0.01251220703125,
+            -0.0556640625,
+            0.04248046875,
+            -0.056640625,
+            -0.030517578125,
+            -0.009033203125,
+            -0.01165771484375,
+            -0.0277099609375,
+            0.0087890625,
+            0.024658203125,
+            -0.043701171875,
+            0.0146484375,
+            -0.020751953125,
+            0.01007080078125,
+            0.0164794921875,
+            0.06591796875,
+            -0.06298828125,
+            0.0303955078125,
+            -0.020263671875,
+            -0.007171630859375,
+            0.004425048828125,
+            0.0020751953125,
+            -0.01373291015625,
+            0.050537109375,
+            -0.08203125,
+            -0.036865234375,
+            0.019775390625,
+            -0.0050048828125,
+            0.06640625,
+            -0.00823974609375,
+            0.04248046875,
+            -0.02734375,
+            0.004425048828125,
+            0.006500244140625,
+            -0.00537109375,
+            -0.0546875,
+            0.01470947265625,
+            0.0089111328125,
+            0.0025787353515625,
+            -0.00860595703125,
+            0.018310546875,
+            -0.0208740234375,
+            -0.06689453125,
+            -0.00592041015625,
+            -0.0303955078125,
+            -0.0021514892578125,
+            0.00372314453125,
+            0.0218505859375,
+            -0.0301513671875,
+            0.02587890625,
+            -0.01239013671875,
+            0.04541015625,
+            0.03662109375,
+            0.07421875,
+            0.0225830078125,
+            0.000385284423828125,
+            0.06396484375,
+            -0.0020294189453125,
+            0.008056640625,
+            0.0111083984375,
+            0.0081787109375,
+            0.033447265625,
+            -0.01544189453125,
+            0.09912109375,
+            -0.00994873046875,
+            0.0208740234375,
+            -0.044921875,
+            -0.017333984375,
+            0.0211181640625,
+            0.08056640625,
+            -0.02294921875,
+            0.062255859375,
+            0.01708984375,
+            -0.011474609375,
+            0.03125,
+            0.018798828125,
+            0.0019683837890625,
+            0.0390625,
+            -0.0052490234375,
+            -0.01312255859375,
+            -0.002044677734375,
+            -0.046630859375,
+            0.015625,
+            0.037353515625,
+            0.002777099609375,
+            -0.00811767578125,
+            0.0233154296875,
+            -0.007232666015625,
+            0.039794921875,
+            0.009765625,
+            0.01708984375,
+            0.043212890625,
+            0.0101318359375,
+            0.02783203125,
+            -0.021484375,
+            -0.01470947265625,
+            -0.013671875,
+            0.01470947265625,
+            -0.032470703125,
+            -0.0185546875,
+            -0.00506591796875,
+            0.03125,
+            -0.03125,
+            0.048095703125,
+            -0.01165771484375,
+            0.0296630859375,
+            0.017822265625,
+            -0.011474609375,
+            0.00787353515625,
+            0.005645751953125,
+            -0.0093994140625,
+            0.0380859375,
+            -0.017333984375,
+            0.0255126953125,
+            -0.01806640625,
+            0.033447265625,
+            -0.001739501953125,
+            -0.0191650390625,
+            0.0054931640625,
+            0.053466796875,
+            -0.0308837890625,
+            -0.006072998046875,
+            0.0179443359375,
+            0.025634765625,
+            -0.01318359375,
+            0.01214599609375,
+            -0.0040283203125,
+            0.03125,
+            0.047119140625,
+            0.056640625,
+            0.01116943359375,
+            -0.0235595703125,
+            0.00872802734375,
+            0.003936767578125,
+            -0.000652313232421875,
+            -0.004638671875,
+            -0.00341796875,
+            0.0035400390625,
+            0.0322265625,
+            0.0169677734375,
+            0.008056640625,
+            -0.0262451171875,
+            -0.080078125,
+            -0.04638671875,
+            0.017822265625,
+            -0.01544189453125,
+            -0.0296630859375,
+            0.033203125,
+            0.10693359375,
+            0.038330078125,
+            0.00286865234375,
+            0.04541015625,
+            0.021484375,
+            -0.04931640625,
+            0.01953125,
+            -0.035400390625,
+            -0.07958984375,
+            -0.07177734375,
+            -0.004119873046875,
+            0.0208740234375,
+            0.10498046875,
+            -0.006011962890625,
+            -0.04248046875,
+            -0.045654296875,
+            -0.001434326171875,
+            0.00994873046875,
+            0.0164794921875,
+            0.0277099609375,
+            0.006378173828125,
+            -0.0286865234375,
+            0.0191650390625,
+            -0.02587890625,
+            0.011474609375,
+            0.0703125,
+            0.00732421875,
+            -0.032470703125,
+            -0.0211181640625,
+            -0.05615234375,
+            0.01092529296875,
+            0.031494140625,
+            0.0247802734375,
+            -0.00372314453125,
+            -0.0013427734375,
+            -0.06982421875,
+            -0.00714111328125,
+            0.0196533203125,
+            0.017333984375,
+            0.01336669921875,
+            -0.00188446044921875,
+            -0.01019287109375,
+            -0.00836181640625,
+            0.035400390625,
+            -0.0400390625,
+            0.01177978515625,
+            0.009033203125,
+            0.004425048828125,
+            0.0157470703125,
+            0.0015716552734375,
+            0.007354736328125,
+            -0.037841796875,
+            0.01214599609375,
+            -0.002685546875,
+            -0.0233154296875,
+            0.0107421875,
+            -0.052001953125,
+            -0.057373046875,
+            0.007354736328125,
+            0.007171630859375,
+            -0.02734375,
+            -0.005523681640625,
+            -0.0010528564453125,
+            -0.0106201171875,
+            0.0022125244140625,
+            0.08642578125,
+            -0.033447265625,
+            0.03125,
+            -0.0225830078125,
+            -0.03125,
+            0.007049560546875,
+            -0.0712890625,
+            -0.0023956298828125,
+            0.006317138671875,
+            -0.056640625,
+            0.0206298828125,
+            -0.017333984375,
+            0.048828125,
+            0.0419921875,
+            -0.0037078857421875,
+            0.02978515625,
+            0.0159912109375,
+            0.04443359375,
+            -0.060302734375,
+            -0.038330078125,
+            0.0277099609375,
+            0.036865234375,
+            0.0322265625,
+            -0.006011962890625,
+            -0.022705078125,
+            -0.050537109375,
+            0.041748046875,
+            0.01507568359375,
+            0.007232666015625,
+            0.050048828125,
+            0.041015625,
+            -0.0240478515625,
+            0.006561279296875,
+            0.000301361083984375,
+            -0.01446533203125,
+            0.01507568359375,
+            -0.0556640625,
+            -0.02734375,
+            -0.0081787109375,
+            0.04736328125,
+            0.0025787353515625,
+            -0.0283203125,
+            0.01129150390625,
+            -0.0252685546875,
+            0.0225830078125,
+            0.00421142578125,
+            -0.004791259765625,
+            0.005401611328125,
+            0.006011962890625,
+            -0.057861328125,
+            -0.0289306640625,
+            0.008544921875,
+            -0.0115966796875,
+            0.022705078125,
+            -0.008056640625,
+            -0.01416015625,
+            0.0021209716796875,
+            -0.0038909912109375,
+            0.01025390625,
+            -0.0247802734375,
+            0.01275634765625,
+            0.031494140625,
+            -0.00015926361083984375,
+            -0.004119873046875,
+            0.041259765625,
+            -0.040283203125,
+            0.052734375,
+            -0.052734375,
+            -0.0225830078125,
+            -0.06884765625,
+            -0.07421875,
+            -0.0341796875,
+            0.0196533203125,
+            0.0038604736328125,
+            -0.041015625,
+            -0.005615234375,
+            -0.039794921875,
+            -0.0205078125,
+            0.04931640625,
+            -0.0289306640625,
+            0.006561279296875,
+            0.020751953125,
+            -0.03369140625,
+            0.020263671875,
+            -0.039794921875,
+            0.0081787109375,
+            -0.0020294189453125,
+            0.0218505859375,
+            0.01611328125,
+            -0.0281982421875,
+            -0.027099609375,
+            0.00131988525390625,
+            -0.0654296875,
+            0.023681640625,
+            -0.006256103515625,
+            -0.0211181640625,
+            -0.006103515625,
+            -0.034912109375,
+            -0.00299072265625,
+            -0.0059814453125,
+            -0.036376953125,
+            -0.0174560546875,
+            -0.056640625,
+            0.000316619873046875,
+            -0.033935546875,
+            0.00726318359375,
+            -0.033447265625,
+            0.06591796875,
+            0.0018768310546875,
+            0.02734375,
+            -0.04345703125,
+            0.032958984375,
+            -0.01953125,
+            -0.0034332275390625,
+            0.01300048828125,
+            0.000713348388671875,
+            -0.008056640625,
+            -0.004730224609375,
+            -0.0341796875,
+            0.030517578125,
+            -0.0255126953125,
+            0.0286865234375,
+            -0.04638671875,
+            0.025146484375,
+            -0.03515625,
+            0.001220703125,
+            -0.01068115234375,
+            0.043212890625,
+            -0.01416015625,
+            -0.0223388671875,
+            -0.03369140625,
+            -0.0059814453125,
+            0.007049560546875,
+            0.0220947265625,
+            -0.0281982421875,
+            -0.00811767578125,
+            -0.00799560546875,
+            0.0263671875,
+            0.01373291015625,
+            0.00194549560546875,
+            0.20703125,
+            -0.0076904296875,
+            0.06591796875,
+            -0.0059814453125,
+            0.01043701171875,
+            -0.01251220703125,
+            0.038330078125,
+            -0.0087890625,
+            0.09765625,
+            0.003082275390625,
+            0.0096435546875,
+            0.000152587890625,
+            0.02392578125,
+            -0.04638671875,
+            -0.007781982421875,
+            -0.0030975341796875,
+            -0.00098419189453125,
+            -0.0181884765625,
+            -0.007232666015625,
+            -0.0235595703125,
+            0.033447265625,
+            0.0125732421875,
+            -0.00171661376953125,
+            0.022216796875,
+            -0.000278472900390625,
+            -0.02392578125,
+            0.0294189453125,
+            -0.0128173828125,
+            0.039794921875,
+            -0.0247802734375,
+            -0.049560546875,
+            0.003631591796875,
+            0.0206298828125,
+            0.0164794921875,
+            0.028564453125,
+            -0.01251220703125,
+            0.02294921875,
+            -0.00099945068359375,
+            -0.022216796875,
+            -0.050537109375,
+            0.001861572265625,
+            -0.0191650390625,
+            -0.045654296875,
+            -0.023681640625,
+            0.004119873046875,
+            0.050048828125,
+            -0.007232666015625,
+            0.05029296875,
+            -0.027099609375,
+            -0.0169677734375,
+            0.035888671875,
+            -0.02001953125,
+            -0.0040283203125,
+            0.01043701171875,
+            0.0035400390625,
+            -0.0059814453125,
+            0.0263671875,
+            -0.01220703125,
+            -0.016357421875,
+            0.01483154296875,
+            -0.0390625,
+            -0.00396728515625,
+            0.04345703125,
+            0.023193359375,
+            -0.0172119140625,
+            0.021240234375,
+            -0.04736328125,
+            0.006866455078125,
+            0.036376953125,
+            -0.0289306640625,
+            0.0208740234375,
+            0.011474609375,
+            -0.0260009765625,
+            0.01904296875,
+            0.016357421875,
+            -0.04931640625,
+            -0.0478515625,
+            0.0213623046875,
+            -0.01275634765625,
+            -0.032470703125,
+            -0.0084228515625,
+            -0.001922607421875,
+            0.0191650390625,
+            0.008544921875,
+            -0.037353515625,
+            0.0111083984375,
+            -0.022705078125,
+            -0.04052734375,
+            0.033447265625,
+            -0.01116943359375,
+            -0.03369140625,
+            -0.0167236328125,
+            -0.0303955078125,
+            0.0191650390625,
+            -0.06591796875,
+            0.00433349609375,
+            -0.078125,
+            -0.00732421875,
+            0.04150390625,
+            0.00286865234375,
+            0.0157470703125,
+            -0.00008440017700195312,
+            0.041015625,
+            -0.034423828125,
+            0.053466796875,
+            0.005218505859375,
+            0.01239013671875,
+            -0.006072998046875,
+            -0.00628662109375,
+            0.018798828125,
+            0.00151824951171875,
+            0.01165771484375,
+            0.0164794921875,
+            0.0089111328125,
+            0.0247802734375,
+            0.024658203125,
+            -0.0031585693359375,
+            -0.0181884765625,
+            -0.0103759765625,
+            -0.04541015625,
+            0.00323486328125,
+            0.0157470703125,
+            -0.004791259765625,
+            0.0308837890625,
+            -0.03076171875,
+            0.00506591796875,
+            0.02392578125,
+            -0.0179443359375,
+            0.0269775390625,
+            -0.003509521484375,
+            -0.0181884765625,
+            0.020263671875,
+            0.03076171875,
+            0.00145721435546875,
+            -0.004547119140625,
+            0.0167236328125,
+            0.035400390625,
+            -0.0206298828125,
+            -0.0810546875,
+            -0.0113525390625,
+            -0.02294921875,
+            0.0022735595703125,
+            0.0250244140625,
+            -0.006561279296875,
+            0.0223388671875,
+            0.043212890625,
+            0.03564453125,
+            -0.009765625,
+            0.036376953125,
+            -0.0028228759765625,
+            -0.003204345703125,
+            -0.041748046875,
+            -0.001495361328125,
+            -0.05419921875,
+            -0.04248046875,
+            -0.01708984375,
+            -0.002777099609375,
+            -0.01251220703125,
+            -0.001739501953125,
+            -0.0084228515625,
+            0.00130462646484375,
+            -0.000579833984375,
+            -0.0262451171875,
+            0.01446533203125,
+            0.037841796875,
+            0.02001953125,
+            -0.0157470703125,
+            -0.017333984375,
+            0.006317138671875,
+            0.0125732421875,
+            -0.0206298828125,
+            0.02197265625,
+            0.012939453125,
+            -0.0162353515625,
+            -0.068359375,
+            0.0250244140625,
+            0.006317138671875,
+            0.00201416015625,
+            -0.005126953125,
+            -0.00872802734375,
+            -0.06591796875,
+            0.0233154296875,
+            -0.01806640625,
+            -0.01312255859375,
+            -0.042236328125,
+            -0.03125,
+            -0.0198974609375,
+            -0.00193023681640625,
+            -0.004364013671875,
+            -0.0262451171875,
+            -0.0439453125,
+            -0.020263671875,
+            -0.01043701171875,
+            -0.0250244140625,
+            0.036865234375,
+            0.00946044921875,
+            -0.012939453125,
+            0.0213623046875,
+            -0.032470703125,
+            -0.048095703125,
+            0.020263671875,
+            0.00482177734375,
+            0.048583984375,
+            0.0301513671875,
+            -0.046630859375,
+            -0.021728515625,
+            -0.00408935546875,
+            0.0164794921875,
+            -0.006591796875,
+            -0.01409912109375,
+            0.0439453125,
+            -0.003936767578125,
+            -0.053955078125,
+            -0.0123291015625,
+            -0.025146484375,
+            -0.0185546875,
+            -0.061767578125,
+            0.0045166015625,
+            -0.01348876953125,
+            -0.025634765625,
+            0.0013580322265625,
+            -0.033447265625,
+            -0.0093994140625,
+            -0.039794921875,
+            0.04638671875,
+            -0.00799560546875,
+            -0.03955078125,
+            -0.015869140625,
+            0.0322265625,
+            0.0093994140625,
+            0.02978515625,
+            0.005828857421875,
+            -0.00011873245239257812,
+            -0.003936767578125,
+            0.0274658203125,
+            0.00701904296875,
+            0.000858306884765625,
+            -0.0146484375,
+            0.020263671875,
+            0.04150390625,
+            0.0216064453125,
+            -0.0164794921875,
+            0.043212890625,
+            0.0546875,
+            0.050048828125,
+            0.01470947265625,
+            -0.006561279296875,
+            0.00958251953125,
+            -0.0164794921875,
+            -0.01177978515625,
+            -0.03564453125,
+            -0.009765625,
+            0.007598876953125,
+            -0.00133514404296875,
+            -0.0322265625,
+            0.0211181640625,
+            0.029296875,
+            0.009765625,
+            -0.00151824951171875,
+            -0.0019073486328125,
+            -0.00830078125,
+            -0.032958984375,
+            0.028564453125,
+            -0.0186767578125,
+            -0.03369140625,
+            0.00897216796875,
+            -0.0040283203125,
+            -0.01104736328125,
+            0.01434326171875,
+            0.05419921875,
+            0.012939453125,
+            -0.0341796875,
+            -0.002471923828125,
+            -0.01446533203125,
+            0.04150390625,
+            0.04541015625,
+            0.0203857421875,
+            0.01251220703125,
+            -0.01348876953125,
+            0.01312255859375,
+            0.0052490234375,
+            0.0419921875,
+            -0.01092529296875,
+            -0.022705078125,
+            -0.0252685546875,
+            0.00836181640625,
+            -0.03759765625,
+            -0.03076171875,
+            0.009033203125,
+            -0.017822265625,
+            -0.00982666015625,
+            0.04736328125,
+            0.025634765625,
+            0.01165771484375,
+            -0.032470703125,
+            -0.0267333984375,
+            0.03515625,
+            0.0012664794921875,
+            -0.061767578125,
+            -0.0089111328125,
+            0.050048828125,
+            0.01275634765625,
+            0.0250244140625,
+            0.0191650390625,
+            0.036376953125,
+            0.005828857421875,
+            -0.0047607421875,
+            0.0023956298828125,
+            -0.031494140625,
+            -0.003143310546875,
+            -0.004669189453125,
+            0.0194091796875,
+            0.00897216796875,
+            -0.01104736328125,
+            0.0849609375,
+            0.007232666015625,
+            -0.0201416015625,
+            -0.0260009765625,
+            -0.0172119140625,
+            0.08984375,
+            0.0517578125,
+            -0.0260009765625,
+            -0.0260009765625,
+            -0.01239013671875,
+            -0.0247802734375,
+            0.0164794921875,
+            -0.0225830078125,
+            0.018798828125,
+            -0.038330078125,
+            -0.0308837890625,
+            -0.024658203125,
+            -0.002227783203125,
+            0.003204345703125,
+            0.0185546875,
+            -0.04443359375,
+            -0.004302978515625,
+            0.03271484375,
+            -0.01507568359375,
+            -0.00080108642578125,
+            0.038818359375,
+            0.0040283203125,
+            0.007049560546875,
+            -0.0198974609375,
+            0.004364013671875,
+            -0.02392578125,
+            -0.029296875,
+            -0.0037994384765625,
+            -0.033447265625,
+            0.01348876953125,
+            0.058837890625,
+            0.00811767578125,
+            0.0341796875,
+            0.0064697265625,
+            0.025146484375,
+            -0.000492095947265625,
+            0.0289306640625,
+            -0.0074462890625,
+            0.0189208984375,
+            0.031494140625,
+            -0.00518798828125,
+            -0.0283203125,
+            -0.0011444091796875,
+            0.03857421875,
+            0.036376953125,
+            0.026611328125,
+            0.005615234375,
+            -0.0032958984375,
+            -0.025146484375,
+            -0.02197265625,
+            0.0194091796875,
+            0.0181884765625,
+            0.07275390625,
+            -0.0045166015625,
+            0.025634765625,
+            -0.0286865234375,
+            0.0103759765625,
+            -0.01141357421875,
+            -0.03564453125,
+            0.049560546875,
+            -0.03173828125,
+            -0.0269775390625,
+            0.02734375,
+            0.041015625,
+            -0.01953125,
+            -0.0003528594970703125,
+            -0.0133056640625,
+            0.0203857421875,
+            -0.011474609375,
+            0.0150146484375,
+            0.0001010894775390625,
+            -0.01165771484375,
+            -0.026611328125,
+            0.03564453125,
+            -0.012939453125,
+            0.00024127960205078125,
+            -0.01446533203125,
+            0.0322265625,
+            -0.03125,
+            -0.0093994140625,
+            0.00066375732421875,
+            -0.02197265625,
+            0.0115966796875,
+            -0.033935546875,
+            -0.045166015625,
+            0.0361328125,
+            0.017822265625,
+            0.0322265625,
+            -0.0263671875,
+            0.04345703125,
+            -0.0133056640625,
+            -0.0478515625,
+            0.0087890625,
+            0.0208740234375,
+            -0.014892578125,
+            0.0135498046875,
+            0.044921875,
+            -0.006011962890625,
+            -0.0042724609375,
+            -0.0242919921875,
+            0.025146484375,
+            -0.021728515625,
+            -0.033935546875,
+            -0.0198974609375,
+            0.0172119140625,
+            0.00958251953125,
+            0.01806640625,
+            0.04345703125,
+            -0.01104736328125,
+            0.036376953125,
+            0.00141143798828125,
+            -0.03466796875,
+            -0.0001964569091796875,
+            -0.035400390625,
+            0.0191650390625,
+            0.0031280517578125,
+            0.00848388671875,
+            0.03076171875,
+            -0.0277099609375,
+            0.01953125,
+            0.08447265625,
+            0.0169677734375,
+            -0.02783203125,
+            -0.045166015625,
+            0.0181884765625,
+            0.039794921875,
+            -0.023681640625,
+            -0.00701904296875,
+            0.040771484375,
+            -0.020751953125,
+            0.06689453125,
+            -0.048828125,
+            -0.00164031982421875,
+            0.006256103515625,
+            0.01007080078125,
+            0.00323486328125,
+            -0.03662109375,
+            0.0419921875,
+            0.0002651214599609375,
+            -0.0301513671875,
+            -0.0111083984375,
+            0.072265625,
+            0.10009765625,
+            0.03564453125,
+            -0.0032501220703125,
+            0.06103515625,
+            0.0103759765625,
+            0.011474609375,
+            -0.034912109375,
+            -0.0115966796875,
+            0.025634765625,
+            -0.062255859375,
+            -0.01416015625,
+            0.037841796875,
+            -0.006683349609375,
+            -0.04736328125,
+            0.04345703125,
+            0.0021514892578125,
+            -0.0311279296875,
+            0.00885009765625,
+            -0.0107421875,
+            0.00372314453125,
+            -0.021728515625,
+            -0.00020503997802734375,
+            0.000263214111328125,
+            -0.01446533203125,
+            0.0028228759765625,
+            0.0277099609375
+          ]
+    question_embedding = json.dumps(question_embedding)
+    question_ocr = "物理"
+    # res = search_question_text_and_embedding(book_id, question_ocr, question_embedding)
+    # print(res)
+
+
+    print("\nfinished.")
+
+
+

es_tst_vector_search.py

+# !/usr/bin/env python
+# -*- coding: utf-8 -*-
+from elasticsearch import Elasticsearch
+from elasticsearch.helpers import bulk
+import numpy as np
+import json
+
+
+# 连接 Elasticsearch
+es = Elasticsearch(
+    hosts = ["http://192.168.8.224:19200"],  # 王磊搭建的新的es索引
+    # basic_auth=("elastic", "password")  # 替换为你的认证信息
+)
+
+
+# 创建索引（如果不存在）
+def create_index(index_name):
+    if not es.indices.exists(index=index_name):
+        index_settings = {
+            "mappings": {
+                "properties": {
+                    "image_url": {"type": "keyword"},
+                    "image_description": {"type": "text"},
+                    "image_vector": {
+                        "type": "dense_vector",
+                        "dims": 2048,  # 向量维度，根据你的向量模型调整
+                        "index": True,
+                        "similarity": "cosine"
+                    }
+                }
+            }
+        }
+        es.indices.create(index=index_name, body=index_settings)
+        print(f"索引 {index_name} 创建成功")
+
+
+# 插入单条图片数据
+def insert_single_image(index_name, image_url, image_description, image_vector):
+    doc = {
+        "image_url": image_url,
+        "image_description": image_description,
+        "image_vector": image_vector
+    }
+    es.index(index=index_name, document=doc)
+    print(f"图片 {image_url} 已插入")
+
+
+# 批量插入图片数据
+def insert_bulk_images(index_name, image_data_list):
+    actions = []
+    for data in image_data_list:
+        action = {
+            "_index": index_name,
+            "_source": {
+                "image_url": data["image_url"],
+                "image_description": data["image_description"],
+                "image_vector": data["image_vector"]
+            }
+        }
+        actions.append(action)
+    bulk(es, actions)
+    print(f"批量插入 {len(actions)} 条数据成功")
+
+
+# 文本检索
+def text_search(index_name, query_text, size=10):
+    query = {
+        "match": {
+            "image_description": query_text
+        }
+    }
+    results = es.search(index=index_name, query=query, size=size)
+    return results['hits']['hits']
+
+
+# 向量检索
+def vector_search(index_name, query_vector, size=10):
+    query = {
+        "script_score": {
+            "query": {"match_all": {}},
+            "script": {
+                "source": "cosineSimilarity(params.query_vector, 'image_vector') + 1.0",
+                "params": {"query_vector": query_vector}
+            }
+        }
+    }
+    results = es.search(index=index_name, query=query, size=size)
+    return results['hits']['hits']
+
+
+# 向量-文本联合检索
+def hybrid_search(index_name, query_text, query_vector, text_weight=0.5, vector_weight=0.5, size=10):
+    query = {
+        "bool": {
+            "should": [
+                {
+                    "match": {
+                        "image_description": {
+                            "query": query_text,
+                            "boost": text_weight
+                        }
+                    }
+                },
+                {
+                    "script_score": {
+                        "query": {"match_all": {}},
+                        "script": {
+                            "source": "cosineSimilarity(params.query_vector, 'image_vector') * params.vector_weight",
+                            "params": {
+                                "query_vector": query_vector,
+                                "vector_weight": vector_weight
+                            }
+                        }
+                    }
+                }
+            ]
+        },
+
+    }
+    results = es.search(index=index_name, query=query, size=size)
+    return results['hits']['hits']
+
+
+# RRF融合函数
+def rrf_fusion(text_results, vector_results, k=60):
+    """
+    使用RRF算法融合两种检索结果
+    参数:
+        text_results: es文本检索结果
+        vector_results: es向量检索结果
+        k: RRF算法中的rank常数，一般取60
+    返回:
+        融合后的结果列表
+    """
+    # 构建文档ID到文本检索排名的映射
+    text_rank_map = {hit['_id']: rank + 1 for rank, hit in enumerate(text_results)}
+
+    # 构建文档ID到向量检索排名的映射
+    vector_rank_map = {hit['_id']: rank + 1 for rank, hit in enumerate(vector_results)}
+
+    # 合并所有文档ID
+    all_doc_ids = set(text_rank_map.keys()).union(set(vector_rank_map.keys()))
+
+    # 计算RRF分数
+    rrf_scores = {}
+    for doc_id in all_doc_ids:
+        text_rank = text_rank_map.get(doc_id, float('inf'))
+        vector_rank = vector_rank_map.get(doc_id, float('inf'))
+
+        # RRF公式: 1/(k + rank)
+        text_score = 1 / (k + text_rank) if text_rank != float('inf') else 0
+        vector_score = 1 / (k + vector_rank) if vector_rank != float('inf') else 0
+
+        rrf_scores[doc_id] = text_score + vector_score
+
+    # 按RRF分数排序
+    sorted_doc_ids = sorted(rrf_scores.items(), key=lambda x: x[1], reverse=True)
+
+    # 构建最终结果
+    final_results = []
+    # 优先从文本结果中获取完整信息
+    id_to_hit = {hit['_id']: hit for hit in text_results}
+    # 补充向量结果中的文档
+    for hit in vector_results:
+        if hit['_id'] not in id_to_hit:
+            id_to_hit[hit['_id']] = hit
+
+    for doc_id, score in sorted_doc_ids:
+        if doc_id in id_to_hit:
+            result = {
+                '_id': doc_id,
+                '_score': score,
+                '_source': id_to_hit[doc_id]['_source']
+            }
+            final_results.append(result)
+
+    return final_results
+
+
+# RRF向量-文本联合检索
+def hybrid_search_rrf(index_name, query_text, query_vector, size=10, rrf_k=60):
+    """使用RRF融合文本和向量检索结果"""
+    # 执行文本和向量检索
+    text_hits = text_search(index_name, query_text)
+    vector_hits = vector_search(index_name, query_vector)
+
+    # 使用RRF融合结果
+    fused_results = rrf_fusion(text_hits, vector_hits, k=rrf_k)
+
+    # 返回前size个结果
+    return fused_results[:size]
+
+
+# 示例用法
+if __name__ == "__main__":
+    INDEX_NAME = "tst_images_text"
+
+    # # 1、创建索引
+    create_index(INDEX_NAME)
+
+    # 示例数据
+    sample_images = [
+        {
+            "image_url": "https://oss.5rs.me/oss/upload/image/jpeg/b2f3fbaa98a3f2552f2dba7451decf7b_36_20250605135114454.jpeg",
+            "image_description": "、填一填。培优作业18 80 78 2.比 16 少9的数是( )多8的数是 17;27 );比( 与 30的和是( );47比3多( )个十和( )个一;7个十和2个一 3.83 里面有( 合起来是( )，它们 4.最大的两位数是(),最小的三位数是(相差(5.写一写,比一比。百位十位个位百位十位个位百位十位个位选择。(把正确答案的序号填在括号里)1.根据艾蒿叶子的影子判断生长时间最短的叶子是(2.在远古时代,为了记录猎物的多少,人们常用石子计数。假设用0表示10.用一表示1,那么下面表示的数最大的是",
+            "image_vector": np.random.random(2048).tolist()  # 替换为实际的图片向量
+        },
+        {
+            "image_url": "https://oss.5rs.me/oss/upload/image/jpeg/9579d101ec560c85f204fa11b7a792c0_2_20250605094300322.jpeg",
+            "image_description": "、直接写得数。培优作业1*18 x10=50 x90 =18 x41~51 x22~30x40 =12 x70 =32 x49 ~17 x78 ~20 x15 =44 x20 =78 x11~46 x23 ~二、填一填。1.13的30倍是(),10个22的和是()位数,积大约是(2.49 x28 的积是()。3.25x40的积的末尾有()个0。4.小亮平均每分钟走69米,他从家走到学校用了12分钟。小亮家离学校大约有()米。5.晶晶平均每分钟可以写25个字,照这样的速度,她15分钟可以写)个字。三、用竖式计算,并验算。18 x51 =32 x60 =46 x25 =四、在( )里填上“ >”“<”或“=”30 x30( )100070x12()80034 x56)36 x5415 x40( )60011 x44(訕興癪9 x13)450)13 x8921 x3425 x801圧ʌ帳八廈仈 x30)600)200023 x45",
+            "image_vector": np.random.random(2048).tolist()  # 替换为实际的图片向量
+        }
+    ]
+
+    # # 2、批量插入
+    # insert_bulk_images(INDEX_NAME, sample_images)
+
+    # # 3、文本检索示例
+    print("\n3、文本检索结果:")
+    text_results = text_search(INDEX_NAME, "填一填")
+    for hit in text_results:
+        print(f"得分: {hit['_score']}, \n描述: {hit['_source']['image_description']}")
+        print()
+
+    # # 4、向量检索示例
+    print("\n4、向量检索结果:")
+    vector_results = vector_search(INDEX_NAME, sample_images[0]["image_vector"])
+    for hit in vector_results:
+        print(f"得分: {hit['_score']}, \n描述: {hit['_source']['image_description']}")
+        print()
+
+    # # 5、联合检索示例
+    print("\n5、联合检索结果:")
+    hybrid_results = hybrid_search(
+        INDEX_NAME,
+        "可爱的动物",
+        sample_images[0]["image_vector"],
+        text_weight=0.4,
+        vector_weight=0.6
+    )
+    for hit in hybrid_results:
+        print(f"得分: {hit['_score']}, \n描述: {hit['_source']['image_description']}")
+        print()
+
+    # # 6、RRF联合检索示例
+    print("\n6、RRF联合检索结果:")
+    hybrid_results = hybrid_search_rrf(
+        INDEX_NAME,
+        "填一填。培优作业18 80 78 2.比 16 少9的数是( )多8的数是 17;27 );比( 与 30的和是( );47比3多( )个十和( )个一;7个十和2个",
+        sample_images[0]["image_vector"],
+        size=10,
+        rrf_k=60
+    )
+    for hit in hybrid_results:
+        print(f"得分: {hit['_score']:.4f}, \n描述: {hit['_source']['image_description']}")
+        print()
+
+
+    print("\nfinished.")
+

paddle_ocr.py

+from tritonclient import grpc as triton_grpc
+import numpy as np
+import json
+from PIL import Image
+import io
+import base64
+import time
+INPUT_NAME = "input"
+OUTPUT_NAME = "output"
+
+def _create_triton_input(data):
+    data = json.dumps(data, separators=(",", ":"))
+    data = data.encode("utf-8")
+    data = [[data]]
+    data = np.array(data, dtype=np.object_)
+    return data
+def _parse_triton_output(data):
+    data = data[0, 0]
+    data = data.decode("utf-8")
+    data = json.loads(data)
+    return data
+
+def triton_request(client, data, *, request_kwargs=None):
+    if request_kwargs is None:
+        request_kwargs = {}
+    input_ = triton_grpc.InferInput(INPUT_NAME, [1, 1], "BYTES")
+    input_.set_data_from_numpy(_create_triton_input(data))
+    results = client.infer('ocr', inputs=[input_], **request_kwargs)
+    output = results.as_numpy(OUTPUT_NAME)
+    return _parse_triton_output(output)
+
+def infer_paddle_ocr(im:Image.Image, client):
+    buffer = io.BytesIO()
+    im.save(buffer, format='JPEG')
+    buffer.seek(0)
+    base64_file = base64.b64encode(buffer.read()).decode("ascii")
+    input_ = {"file": base64_file,
+              "fileType": 1}
+    while True:
+        output_ocr = triton_request(client, input_)
+        errorCode = output_ocr["errorCode"]
+        if errorCode == 0:
+            result = output_ocr["result"]
+            res_ocr = result["ocrResults"][0]['prunedResult']
+            db_boxes = res_ocr['rec_boxes']
+            rec_texts = res_ocr['rec_texts']
+            break
+    return db_boxes, rec_texts
+
+
+if __name__=='__main__':
+    start_time = time.time()
+    paddle_ocr_url = '61.170.32.8:38896'
+    client_ocr = triton_grpc.InferenceServerClient(paddle_ocr_url)
+    im = '/data/liyaze/doc2xkey_server_v2/utils/my-obs-object-key-demo.jpg'
+    im = "/home/liuxin/work/search_book/data/12664728-课计划·七年级英语·RJ·上册/1.jpg"
+    im = "/home/liuxin/work/search_question/data/12664728-课计划·七年级英语·RJ·上册/93.jpg"
+    im = Image.open(im).convert('RGB')
+    db_boxes, rec_texts = infer_paddle_ocr(im, client_ocr)
+    print(f"耗时：{time.time()-start_time}")
+    print(rec_texts)
\ No newline at end of file

prepare_data.py

+import re,json,sys,os
+import pandas as pd
+import numpy as np
+
+
+class prepareData():
+    def __init__(self):
+
+        self.index = "index"                          # int
+        self.fileId = "bankId"                        # int
+        self.question_image_url = "question_image_url"
+        self.question_text = "question_text"
+        self.answer_image_url = "answer_image_url"
+        self.answer_text = "answer_text"
+        self.question_chapter = "question_chapter"
+        self.question_category = "question_category"
+        self.page_id = "page_id"                      # int
+        self.book_page_id = "book_page_id"
+        self.knowledge_point = "knowledge_point"
+        self.knowledge_point_code = "knowledge_point_code"
+        self.difficult = "difficult"
+        self.resolve = "resolve"
+        self.appendix = "appendix"
+        self.source_image_url = "source_image_url"
+        self.page_ocr = "page_ocr"
+        self.question_ocr = 'question_ocr'
+
+        self.title2tile = {
+            "序号": self.index,
+            "题目id": self.fileId,
+            "题目图片地址": self.question_image_url,
+            "题目文本": self.question_text,
+            "答案图片地址": self.answer_image_url,
+            "答案文本": self.answer_text,
+            "所属章节": self.question_chapter,
+            "题目类型": self.question_category,
+            "电子页码": self.page_id,
+            "纸书页码": self.book_page_id,
+            "知识点": self.knowledge_point,
+            "知识点代码": self.knowledge_point_code,
+            "难度": self.difficult,
+            "解析": self.resolve,
+            "附件": self.appendix,
+            "source_image_url": self.source_image_url,
+            "page_ocr": self.page_ocr,
+            "question_ocr": self.question_ocr,
+        }
+
+    def clean(self, text):
+        text = re.sub(r'<img[^>]*>', '', text)
+        text = re.sub(r"</p><p>", " ", text)
+        text = re.sub(r"<p>", " ", text)
+        text = re.sub(r"</p>", " ", text)
+        text = text.strip()
+
+        return text
+    def read_excel(self,excel_path, sheet_name="Sheet1", book_id=None, book_name=None):
+        data = pd.read_excel(excel_path, sheet_name)
+        data = data.rename(columns=self.title2tile)
+        data.fillna("")
+        data = data.to_dict(orient='records')
+        page_id2bank_id = {} # 整页的所有题目
+        for item in data:
+            item[self.index] = int(item[self.index])
+            item[self.fileId] = int(item[self.fileId])
+            item[self.question_image_url] = str(item[self.question_image_url])
+            item[self.question_text] = str(item[self.question_text])
+            item[self.answer_image_url] = str(item[self.answer_image_url])
+            item[self.answer_text] = str(item[self.answer_text])
+            item[self.question_chapter] = str(item[self.question_chapter])
+            item[self.question_category] = str(item[self.question_category])
+            page_id = int(item[self.page_id])
+            item[self.page_id] = int(item[self.page_id])
+            item[self.book_page_id] = str(item[self.book_page_id])
+            item[self.knowledge_point] = str(item[self.knowledge_point])
+            item[self.knowledge_point_code] = str(item[self.knowledge_point_code])
+            item[self.difficult] = str(item[self.difficult])
+            item[self.resolve] = str(item[self.resolve])
+            item[self.appendix] = str(item[self.appendix])
+            item['book_id'] = str(book_id)
+            item['book_name'] = book_name
+            item['book_id_page_id']=str(book_id)+"-"+str(page_id)
+
+            item.pop('question_category')
+            item.pop('appendix')
+
+            # 1、整页图片的paddleOCR结果
+            # page_ocr = json.loads(item[self.page_ocr])['rec_texts'] # paddleOCR
+            # page_ocr = " ".join(page_ocr)
+            page_ocr = item[self.page_ocr]  # 合合OCR
+            item[self.page_ocr] = page_ocr
+
+            # 2、题目的paddleOCR结果
+            # question_ocr = json.loads(item[self.question_ocr])['rec_texts']  # paddleOCR
+            # question_ocr = " ".join(question_ocr)
+
+            question_ocr = item[self.question_ocr]  # 合合OCR
+            item[self.question_ocr] = question_ocr
+
+            # 3、整页图片所有题目id
+            bank_id = int(item[self.fileId])
+            if page_id in page_id2bank_id:
+                page_id2bank_id[page_id].append(bank_id)
+            else:
+                page_id2bank_id[page_id] = [bank_id]
+
+            # 4、原始题目 图片 embedding
+            if "question_image_embedding" in item.keys():
+                item['question_image_embedding'] = json.loads(item['question_image_embedding'])
+            # 5、整页 图片 embedding
+            if "page_image_embedding" in item.keys():
+                item['page_image_embedding'] = json.loads(item['page_image_embedding'])
+
+        for item in data:
+            page_id = int(item[self.page_id])
+            bank_ids = page_id2bank_id[page_id]   # [12,2134,321]
+            item['page_id2bank_ids'] = bank_ids   # 整页图片所有题目id
+
+        return data
+
+
+    def write2json(self, path, data_list):
+        with open(path, "w", encoding='utf-8') as f:
+            data_list = json.dumps(data_list, ensure_ascii=False, indent=4)
+            f.write(data_list)
+
+            print(f"success save: {path} ")
+
+    def result(self):
+        excel_file = "/home/liuxin/work/search_question/data/12671977-暑假生活·学期总复习八年级物理通用版6-原图/12671977-暑假生活·学期总复习八年级物理通用版6.xlsx"
+        sheet_name = "题库数据"
+        book_id = 12671977
+        book_name = '暑假生活·学期总复习八年级物理通用版6'
+        data_list = self.read_excel( excel_file, sheet_name=sheet_name, book_id=book_id, book_name=book_name)
+        save_json_path = excel_file+".json"
+        self.write2json(save_json_path, data_list)
+
+
+if __name__ == "__main__":
+    prepare_data = prepareData()
+    prepare_data.result()
+
+
+    print("\nfinished.")
+
+
+
+

save_es_database.py

+# !/usr/bin/env python
+# -*- coding: utf-8 -*-
+import copy
+import asyncio
+import json,re,sys,os
+from elasticsearch import Elasticsearch, helpers # elasticsearch-8.11.0
+from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor, as_completed
+
+# 将拆题后的数据写入es库
+
+
+class EsHelper:
+    def __init__(self, hosts=None):
+        """初始化ES连接
+        Args:
+            hosts: ES服务器地址列表，默认为None使用已配置的地址
+        """
+        if hosts is None:
+            self.hosts = [{'host': '116.63.110.220', 'port': 9200}]
+            self.hosts = [{'host': 'localhost', 'port': 9200}]
+            self.hosts = ['http://localhost:9200']  # http://116.63.110.220:9200
+            self.hosts = ["http://192.168.8.224:19200"]  # 王磊搭建的新的es索引
+        self.es = Elasticsearch(hosts=self.hosts) # , timeout=1000
+
+        print("self.es.ping(): ", self.es.ping())
+
+    def create_index(self, index_name):
+        """创建索引
+        Args:
+            index_name: es索引名称
+        Returns:
+            创建结果
+        """
+        body = {}
+        settings = {
+            "index": {
+                "number_of_shards": 1,  # 定义索引的分片数量 方便在不同的节点部署
+                "number_of_replicas": 0,  # 定义索引中每个主分片的副本数量
+            }}
+
+        mappings = {
+                    "dynamic": True,
+                    "properties": {
+                            "book_id": {"type": "keyword"},
+                            "book_name": {
+                                "type": "text",
+                                "fields": {
+                                    "keyword": {
+                                        "type": "keyword",
+                                        "ignore_above": 256
+                                    }
+                                },
+                            },
+                            "book_id_page_id": { "type": "keyword" },
+                            "bankId": {
+                                "type": "integer",
+                                # "description": "题库ID"
+                            },
+                            "page_id2bank_ids": {
+                                "type": "integer"  # 对于整数列表，使用integer类型
+                                # Elasticsearch会自动处理数组类型，不需要特别指定array
+                            },
+                            "page_id": {
+                                "type": "integer",
+                                # "description": "页码"
+                            },
+                            "question_text": {
+                                "type": "text",
+                                "fields": {
+                                    "keyword": {
+                                        "type": "keyword",
+                                        "ignore_above": 256
+                                    }
+                                },
+                                # "description": "问题文本内容"
+                            },
+                            "answer_image_url": {
+                                "type": "keyword",
+                                # "description": "答案图片URL"
+                            },
+                            "answer_text": {
+                                "type": "text",
+                                "fields": {
+                                    "keyword": {
+                                        "type": "keyword",
+                                        "ignore_above": 256
+                                    }
+                                },
+                                # "description": "答案文本内容"
+                            },
+                            "question_chapter": {
+                                "type": "text",
+                                "fields": {
+                                    "keyword": {
+                                        "type": "keyword",
+                                        "ignore_above": 256
+                                    }
+                                },
+                            },
+                            "book_page_id": {
+                                "type": "keyword",
+                                # "description": "书籍页码标识"
+                            },
+                            "knowledge_point": {
+                                "type": "text",
+                                "fields": {
+                                    "keyword": {
+                                        "type": "keyword",
+                                        "ignore_above": 256
+                                    }
+                                },
+                                # "description": "知识点内容"
+                            },
+                            "knowledge_point_code": {
+                                "type": "keyword",
+                                # "description": "知识点编码"
+                            },
+                            "difficult": {
+                                "type": "text",
+                                # "description": "题目难度",
+                                "fields": {
+                                    "keyword": {
+                                        "type": "keyword",
+                                        "ignore_above": 256
+                                    },
+
+                                },
+                            },
+                            "resolve": {
+                                "type": "text",
+                                "fields": {
+                                    "keyword": {
+                                        "type": "keyword",
+                                        "ignore_above": 256
+                                    },
+                                },
+                                # "description": "解题思路"
+                            },
+                            "source_image_url": {
+                                "type": "keyword",
+                            },
+                            "page_ocr": {
+                                "type": "text",
+                                "fields": {
+                                    "keyword": {
+                                        "type": "keyword",
+                                        "ignore_above": 256
+                                    }
+                                },
+                            },
+                            "question_image_url": {
+                                "type": "keyword",
+                                # "description": "问题图片URL"
+                            },
+                            "question_ocr": {
+                            "type": "text",
+                            "fields": {
+                                "keyword": {
+                                    "type": "keyword",
+                                    "ignore_above": 256
+                                }
+                            },
+                        },
+                            "question_image_embedding": {
+                                "type": "dense_vector",
+                                "dims": 1024,  # question 图文向量维度 "doubao-embedding-vision-250615"
+                                "index": True,
+                                "similarity": "cosine"
+                            },
+                            "page_image_embedding": {
+                                "type": "dense_vector",
+                                "dims": 1024,  # 整页图片 图文向量维度  "doubao-embedding-vision-250615"
+                                "index": True,
+                                "similarity": "cosine"
+                            }
+                    }
+        }
+
+        if settings:
+            body['settings'] = settings
+        if mappings:
+            body['mappings'] = mappings
+        res = self.es.indices.create(index=index_name, body=body, timeout='100s', master_timeout="1200s")  # 关键：将默认30秒延长至120秒[4,9](@ref)
+
+        print(f"create index {index_name} success.")
+        return res
+
+    def delete_index(self, index_name):
+        """删除索引
+        Args:
+            index_name: 索引名称
+        Returns:
+            删除结果
+        """
+        res = self.es.indices.delete(index=index_name)
+        print(f"删除索引 {index_name} success.")
+        return res
+
+    def index_exists(self, index_name):
+        """判断索引是否存在
+
+        Args:
+            index_name: 索引名称
+        Returns:
+            bool: 是否存在
+        """
+        return self.es.indices.exists(index=index_name)
+
+    def read_dict(self, file):
+        # 1、读入中朝大辞典 ocr解析 并 gpt4o清洗后的数据
+        with open(file, 'r', encoding='utf-8') as f:
+            data_list = json.loads(f.read())
+
+            res = []
+            for item in data_list:
+                temp = {}
+                for k, v in item.items():
+                    if not v:
+                        pass
+                    else:
+                        temp[k] = v
+                res.append(copy.deepcopy(temp))
+
+            print("len(data_list): ", len(data_list))
+
+        return res
+
+    def insert_doc(self, index_name, doc_body, doc_id=None):
+        """插入文档
+        Args:
+            index_name: 索引名称
+            doc_body: 文档内容
+            doc_id: 文档ID,可选
+        Returns:
+            插入结果
+        """
+        return self.es.index(index=index_name, body=doc_body, id=doc_id)
+
+    def insert_doc_batch(self, index_name, doc_batch: list):
+        # 批量插入es数据库
+        actions = []
+        for idx, body in enumerate(doc_batch):
+            _id = body['bankId']
+            temp = {"_index": index_name, "_id": _id}
+            temp['_source'] = body
+            actions.append(temp)
+
+        # 使用helpers.bulk方法批量插入文档
+        helpers.bulk(self.es, actions)
+
+    def insert_doc_file(self, index_name):
+        # 插入所有的清洗好的数据
+        path = "/home/liuxin/work/search_question/data"
+        files = [
+
+            "12671977-暑假生活·学期总复习八年级物理通用版6-原图/12671977-暑假生活·学期总复习八年级物理通用版6.xlsx.json"
+            ]
+        for file in files:
+            file = os.path.join(path, file)
+            data_list = self.read_dict( file)
+            self.insert_doc_batch( index_name, data_list)
+            print(f"{file} 成功插入{index_name} es库.")
+
+    def get_doc(self, index_name, doc_id):
+        """获取文档
+        Args:
+            index_name: 索引名称
+            doc_id: 文档ID
+        Returns:
+            文档内容
+        """
+        return self.es.get(index=index_name, id=doc_id)
+
+    def update_doc(self, index_name, doc_id, doc_body):
+        """更新文档
+
+        Args:
+            index_name: 索引名称
+            doc_id: 文档ID
+            doc_body: 更新的内容
+        Returns:
+            更新结果
+        """
+        return self.es.update(index=index_name, id=doc_id, body={'doc': doc_body})
+
+    def delete_doc(self, index_name, doc_id):
+        """删除文档
+
+        Args:
+            index_name: 索引名称
+            doc_id: 文档ID
+        Returns:
+            删除结果
+        """
+        return self.es.delete(index=index_name, id=doc_id)
+
+    def delete_book_id(self, index_name, book_id):
+        def delete_book(index_name, book_id):
+            # 依据 book_id 删除某本书的所有数据
+            book_id = str(book_id)
+            for doc in helpers.scan(
+                    self.es,
+                    query={"query": {"term": {"book_id": book_id}}},
+                    index=index_name,
+                    _source=False,  # 不返回文档内容[1](@ref)
+                    scroll="10m"
+            ):
+                yield {
+                    "_op_type": "delete",
+                    "_index": doc["_index"],
+                    "_id": doc["_id"]
+                }
+
+        # 批量执行删除
+        helpers.bulk(
+            self.es,
+            delete_book(index_name, book_id),
+            chunk_size=5000,  # 每批次删除量[1](@ref)
+            request_timeout=120  # 延长请求超时
+        )
+
+        print(f"成功删除 book_id：{book_id} 的数据.")
+
+    def search(self, index_name, query_body):
+        """搜索文档
+        """
+        return self.es.search(index=index_name, body=query_body)
+
+    def delete_res_key(self, hits):
+        # 踢除 embedding 向量字段内容后再返回
+        for hit in hits:
+            if '_source' in hit and 'page_image_embedding' in hit['_source']:
+                hit['_source'].pop('page_image_embedding')
+            if '_source' in hit and 'question_image_embedding' in hit['_source']:
+                hit['_source'].pop('question_image_embedding')
+
+        return hits
+
+    async def search_page(self, index_name, book_id, page_ocr, top_k=3):
+        # 依据用户上传的整图paddleOCR结果和图书book_id，搜索es中的 指定图书的整页图片
+        query = {
+            "bool": {
+                "must": [
+                    {"term": {"book_id": book_id}},  # 精确匹配 book_id
+                    {"match": {"page_ocr": page_ocr}},  # 全文匹配 page_ocr 字段
+                ]
+            }
+        }
+
+        response = self.es.search(
+            index=index_name,
+            body={"query": query},
+            size=top_k  # 返回结果数量
+        )
+        hits = response["hits"]["hits"]
+        hits = self.delete_res_key( hits)
+
+        return hits
+
+    async def search_question(self, index_name, book_id, question_ocr, top_k=3, page_ids=None):
+        # 依据用户上传的整题paddleOCR结果和图书book_id，搜索es中的 相关题目
+        if not page_ids:
+            query = {
+                "bool": {
+                    "must": [
+                        {"term": {"book_id": book_id}},  # 精确匹配 book_id
+                        {"match": {"question_ocr": question_ocr}},  # 全文匹配 question_ocr 字段
+                    ]
+                }
+            }
+        else:
+            query = {
+                "bool": {
+                    "must": [
+                        {"term": {"book_id": book_id}},  # 精确匹配 book_id
+                        {"terms": {"page_id": page_ids}},   # 精确匹配 电子页码
+                        {"match": {"question_ocr": question_ocr}}, # 全文匹配 question_ocr 字段
+                    ]
+                }
+            }
+
+        response = self.es.search(
+            index=index_name,
+            body={"query": query},
+            size=top_k  # 返回结果数量
+        )
+        hits = response["hits"]["hits"]
+        hits = self.delete_res_key(hits)
+
+        return hits
+
+    async def search_page_question(self, index_name, book_id, page_ocr, question_ocr, top_k=2):
+        # 先使用整页图片的paddleOCR结果搜索题目所在的page_id， 再依据page_id和题目的paddle_ocr结果搜索 es数据库中的题目。
+        # 每一页的最后一个题，可能在本页和下一页都有部分题目内容，拆书平台下载的excel数据 题目只出现在第一页，固题目会出现在本页或上一页
+        hits = []
+        page_res = await self.search_page(index_name, book_id, page_ocr, top_k=1)
+        if page_res and '_source' in page_res[0] and 'page_id' in page_res[0]['_source']:
+            page_id = page_res[0]['_source']['page_id']
+            page_id = int(page_id)
+            page_ids = [page_id, page_id-1]  # 题目会出现在本页或上一页
+            hits = await self.search_question( index_name, book_id, question_ocr, top_k=top_k, page_ids=page_ids)
+
+        hits = self.delete_res_key(hits)
+
+        return hits
+
+    async def search_question_embedding(self, index_name, book_id,  question_image_embedding, top_k=2 ):
+        # 联合用户拍摄的题目图片以及图片的OCR结果 得到的embedding数据 “question_image_embedding”搜题目。搜题只用了 搜题只用了 embedding数据。
+        query = {
+                "bool": {
+                    "filter": [{"term": {"book_id": book_id}}],
+                    "must": [
+                        {
+                            "script_score": {
+                                "query": {"match_all": {}},
+                                "script": {
+                                    "source": "cosineSimilarity(params.query_vector, 'question_image_embedding') + 1.0",
+                                    "params": {
+                                        "query_vector": question_image_embedding,
+                                    }
+                                }
+                            }
+                        }
+                    ]
+                }
+            }
+        response = self.es.search(
+            index=index_name,
+            body={"query": query},
+            size=top_k  # 返回结果数量
+        )
+        hits = response["hits"]["hits"]
+        hits = self.delete_res_key(hits)
+
+        return hits
+
+    async def search_question_textAndEmbedding(self, index_name, book_id, question_ocr, question_image_embedding, top_k=2 ):
+        """
+        :param question_ocr: 用户拍摄的题目图片ocr结果
+        :param question_image_embedding:  用户拍摄题目图片ocr和题目图片一起输入模型得到的 embedding
+        """
+        query = {
+            "script_score": {
+                "query": {
+                    "bool": {
+                        "filter": [
+                            {"term": {"book_id": book_id}}
+                        ],
+                        "should": [
+                            {"match": {"question_ocr": question_ocr}}
+                        ],
+                        "minimum_should_match": 0
+                    }
+                },
+                # 1、如果没有文本匹配，给个基础分 _score=0.1; 2、余弦相似度计算向量得分；3、使用Sigmoid函数分别归一化分数; 4、加权合并文本匹配和向量匹配
+                "script": {
+                    "source": """
+                    double rawScore = _score;
+                    double textScore = rawScore <= 0.1 ? 0.1 : (rawScore > 2.0 ? 2.0 : rawScore); 
+                  double imageScore = cosineSimilarity(params.query_vector, 'question_image_embedding')+ 1.0;
+
+                  double normalizedTextScore = 1.0 / (1.0 + Math.exp(-params.text_scale * (textScore - params.text_bias)));
+                  double normalizedImageScore = 1.0 / (1.0 + Math.exp(-params.image_scale * (imageScore - params.image_bias)));
+
+                  return params.text_weight * normalizedTextScore + params.image_weight * normalizedImageScore;
+                """,
+                    "params": {
+                        "query_vector": question_image_embedding,
+                        "text_weight": 0.2,
+                        "image_weight": 0.8,
+                        "text_scale": 2.0,
+                        "image_scale": 2.0,
+                        "text_bias": 0.5,
+                        "image_bias": 0.5
+                    }
+                }
+            }
+        }
+
+        response = self.es.search(
+            index=index_name,
+            body={"query": query},
+            size=top_k  # 返回结果数量
+        )
+        hits = response["hits"]["hits"]
+        hits = self.delete_res_key(hits)
+
+        return hits
+
+
+if __name__ == "__main__":
+    index_name = "search_question"  # rays 搜题
+    es = EsHelper()
+
+    ## 0、查看es中有多少条数据
+    # count = es.es.count(index=index_name)
+    # print(f'{index_name} ：{count} ')  # {'count': 307, '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0}}
+
+    # # # 1、创建新的es索引
+    # # if es.index_exists( index_name):
+    #     es.delete_index(index_name)  # 删除索引
+    # create_index_res = es.create_index(index_name)  # 建立一个新的es 索引
+    # print('create_index_res: ', create_index_res)
+
+    # # 2、es中批量插入数据
+    # es.insert_doc_file(index_name)
+
+    # ## 3、测试查询es库中的数据
+    # id = '1190766'
+    # res = es.get_doc(index_name, id)
+    # print(res)
+
+    # ## 4、测试查询es库中的整页数据
+    # print("\n4、测试查询es库中的整页数据")
+    # book_id = "12671977" #
+    # input_ocr = "某篮球运动员在比赛中由于飞身扣篮用力过猛,将篮板玻璃打碎了,他的手腕也同时受伤. 说明了"
+    # res = es.search_page( index_name, book_id, input_ocr, top_k=3)
+    # res = asyncio.run(res)
+    # res = json.dumps(res, ensure_ascii=False, indent=4)
+    # print(res)
+
+    # ## 5、直接查询es库中题目
+    # print("\n5、查询es库中题目")
+    # book_id = "12671977"
+    # question_ocr = "某篮球运动员在比赛中由于飞身扣篮用力过猛,将篮板玻璃打碎了,他的手腕也同时受伤. 说明了"
+    # res = es.search_question(index_name, book_id, question_ocr, top_k=3)
+    # res = asyncio.run(res)
+    # res = json.dumps(res, ensure_ascii=False, indent=4)
+    # print(res)
+
+    # ## 6、先查询es库中page_id，再查询本页或前一页的题目
+    # print("\n6、先查询es库中page_id，再查询本页或前一页的题目")
+    # book_id = "12671977"
+    # page_ocr = "某篮球运动员在比赛中由于飞身扣篮用力过猛,将篮板玻璃打碎了,他的手腕也同时受伤. 说明了"
+    # question_ocr = "某篮球运动员在比赛中由于飞身扣篮用力过猛,将篮板玻璃打碎了,他的手腕也同时受伤. 说明了"
+    # res = es.search_page_question( index_name, book_id, page_ocr, question_ocr, top_k=2)
+    # res = asyncio.run(res)
+    # res = json.dumps(res, ensure_ascii=False, indent=4)
+    # print(res)
+
+
+    # 7 依据 book_id 批量删除 某本书的的所有数据
+    # book_ids =[ '12671977','12670279','12667382', '12664728' ]
+    # for book_id in book_ids:
+    #     es.delete_book_id(index_name, book_id)
+
+    # 8、使用题目向量 搜索 库中题目
+    book_id = "12667382"
+    question_image_embedding = [
+            0.00543212890625,
+            -0.005035400390625,
+            0.00714111328125,
+            0.06591796875,
+            -0.032958984375,
+            -0.0380859375,
+            -0.0255126953125,
+            -0.046630859375,
+            0.01031494140625,
+            0.036376953125,
+            0.013916015625,
+            0.0255126953125,
+            -0.0107421875,
+            -0.04345703125,
+            0.0008697509765625,
+            0.02587890625,
+            -0.0201416015625,
+            -0.02099609375,
+            -0.00830078125,
+            0.033203125,
+            -0.01007080078125,
+            0.0224609375,
+            -0.04931640625,
+            0.0206298828125,
+            0.009765625,
+            0.02392578125,
+            0.00095367431640625,
+            0.03369140625,
+            0.005035400390625,
+            0.07373046875,
+            0.0262451171875,
+            0.015625,
+            -0.021728515625,
+            0.0054931640625,
+            0.0308837890625,
+            0.055419921875,
+            -0.0517578125,
+            0.011474609375,
+            -0.023681640625,
+            0.0235595703125,
+            -0.00128173828125,
+            0.0096435546875,
+            0.003936767578125,
+            -0.01953125,
+            -0.05126953125,
+            0.001617431640625,
+            -0.005218505859375,
+            -0.01409912109375,
+            -0.026611328125,
+            0.0198974609375,
+            0.02001953125,
+            0.004974365234375,
+            0.053955078125,
+            -0.0634765625,
+            -0.0654296875,
+            -0.03369140625,
+            -0.08154296875,
+            0.06005859375,
+            0.0223388671875,
+            -0.044921875,
+            -0.0283203125,
+            0.01483154296875,
+            0.150390625,
+            0.026611328125,
+            0.02392578125,
+            -0.00125885009765625,
+            -0.053955078125,
+            -0.03759765625,
+            -0.0390625,
+            0.02734375,
+            -0.01385498046875,
+            0.00140380859375,
+            0.0218505859375,
+            -0.01025390625,
+            -0.0205078125,
+            0.04638671875,
+            0.0145263671875,
+            -0.00927734375,
+            0.01025390625,
+            -0.0225830078125,
+            -0.00909423828125,
+            -0.0142822265625,
+            0.02978515625,
+            0.0101318359375,
+            -0.072265625,
+            -0.049560546875,
+            0.0311279296875,
+            0.0101318359375,
+            -0.00445556640625,
+            -0.03369140625,
+            0.0615234375,
+            -0.021240234375,
+            -0.034912109375,
+            -0.004150390625,
+            0.07177734375,
+            0.0262451171875,
+            -0.013671875,
+            0.03369140625,
+            0.021728515625,
+            0.0252685546875,
+            -0.00982666015625,
+            -0.0028228759765625,
+            -0.00151824951171875,
+            0.003753662109375,
+            0.004791259765625,
+            -0.03759765625,
+            0.025146484375,
+            0.0235595703125,
+            -0.0103759765625,
+            0.0084228515625,
+            -0.0191650390625,
+            0.044921875,
+            0.052001953125,
+            -0.053955078125,
+            0.0206298828125,
+            0.036376953125,
+            0.01202392578125,
+            0.0196533203125,
+            0.025146484375,
+            -0.000457763671875,
+            -0.0033721923828125,
+            -0.0101318359375,
+            0.005035400390625,
+            0.0089111328125,
+            0.002227783203125,
+            -0.041015625,
+            0.00927734375,
+            0.10693359375,
+            0.01043701171875,
+            0.00616455078125,
+            0.013916015625,
+            0.0035858154296875,
+            -0.0283203125,
+            -0.06591796875,
+            0.016845703125,
+            -0.0615234375,
+            -0.01385498046875,
+            -0.05029296875,
+            -0.01556396484375,
+            -0.0128173828125,
+            -0.0140380859375,
+            0.00732421875,
+            -0.0164794921875,
+            0.01239013671875,
+            0.0150146484375,
+            -0.0169677734375,
+            -0.142578125,
+            -0.0008087158203125,
+            -0.007171630859375,
+            0.0033416748046875,
+            0.03662109375,
+            -0.00341796875,
+            -0.0198974609375,
+            -0.03955078125,
+            -0.06640625,
+            -0.05712890625,
+            0.0133056640625,
+            -0.0277099609375,
+            -0.005462646484375,
+            -0.0224609375,
+            0.002166748046875,
+            0.0296630859375,
+            -0.030517578125,
+            -0.029052734375,
+            0.030517578125,
+            -0.0162353515625,
+            -0.0252685546875,
+            -0.0174560546875,
+            -0.023193359375,
+            0.005340576171875,
+            -0.026611328125,
+            -0.006011962890625,
+            -0.01611328125,
+            -0.033203125,
+            -0.000820159912109375,
+            0.04248046875,
+            -0.0301513671875,
+            0.019287109375,
+            0.00909423828125,
+            0.0400390625,
+            0.03564453125,
+            0.030517578125,
+            0.0140380859375,
+            -0.0014495849609375,
+            0.01251220703125,
+            -0.0556640625,
+            0.04248046875,
+            -0.056640625,
+            -0.030517578125,
+            -0.009033203125,
+            -0.01165771484375,
+            -0.0277099609375,
+            0.0087890625,
+            0.024658203125,
+            -0.043701171875,
+            0.0146484375,
+            -0.020751953125,
+            0.01007080078125,
+            0.0164794921875,
+            0.06591796875,
+            -0.06298828125,
+            0.0303955078125,
+            -0.020263671875,
+            -0.007171630859375,
+            0.004425048828125,
+            0.0020751953125,
+            -0.01373291015625,
+            0.050537109375,
+            -0.08203125,
+            -0.036865234375,
+            0.019775390625,
+            -0.0050048828125,
+            0.06640625,
+            -0.00823974609375,
+            0.04248046875,
+            -0.02734375,
+            0.004425048828125,
+            0.006500244140625,
+            -0.00537109375,
+            -0.0546875,
+            0.01470947265625,
+            0.0089111328125,
+            0.0025787353515625,
+            -0.00860595703125,
+            0.018310546875,
+            -0.0208740234375,
+            -0.06689453125,
+            -0.00592041015625,
+            -0.0303955078125,
+            -0.0021514892578125,
+            0.00372314453125,
+            0.0218505859375,
+            -0.0301513671875,
+            0.02587890625,
+            -0.01239013671875,
+            0.04541015625,
+            0.03662109375,
+            0.07421875,
+            0.0225830078125,
+            0.000385284423828125,
+            0.06396484375,
+            -0.0020294189453125,
+            0.008056640625,
+            0.0111083984375,
+            0.0081787109375,
+            0.033447265625,
+            -0.01544189453125,
+            0.09912109375,
+            -0.00994873046875,
+            0.0208740234375,
+            -0.044921875,
+            -0.017333984375,
+            0.0211181640625,
+            0.08056640625,
+            -0.02294921875,
+            0.062255859375,
+            0.01708984375,
+            -0.011474609375,
+            0.03125,
+            0.018798828125,
+            0.0019683837890625,
+            0.0390625,
+            -0.0052490234375,
+            -0.01312255859375,
+            -0.002044677734375,
+            -0.046630859375,
+            0.015625,
+            0.037353515625,
+            0.002777099609375,
+            -0.00811767578125,
+            0.0233154296875,
+            -0.007232666015625,
+            0.039794921875,
+            0.009765625,
+            0.01708984375,
+            0.043212890625,
+            0.0101318359375,
+            0.02783203125,
+            -0.021484375,
+            -0.01470947265625,
+            -0.013671875,
+            0.01470947265625,
+            -0.032470703125,
+            -0.0185546875,
+            -0.00506591796875,
+            0.03125,
+            -0.03125,
+            0.048095703125,
+            -0.01165771484375,
+            0.0296630859375,
+            0.017822265625,
+            -0.011474609375,
+            0.00787353515625,
+            0.005645751953125,
+            -0.0093994140625,
+            0.0380859375,
+            -0.017333984375,
+            0.0255126953125,
+            -0.01806640625,
+            0.033447265625,
+            -0.001739501953125,
+            -0.0191650390625,
+            0.0054931640625,
+            0.053466796875,
+            -0.0308837890625,
+            -0.006072998046875,
+            0.0179443359375,
+            0.025634765625,
+            -0.01318359375,
+            0.01214599609375,
+            -0.0040283203125,
+            0.03125,
+            0.047119140625,
+            0.056640625,
+            0.01116943359375,
+            -0.0235595703125,
+            0.00872802734375,
+            0.003936767578125,
+            -0.000652313232421875,
+            -0.004638671875,
+            -0.00341796875,
+            0.0035400390625,
+            0.0322265625,
+            0.0169677734375,
+            0.008056640625,
+            -0.0262451171875,
+            -0.080078125,
+            -0.04638671875,
+            0.017822265625,
+            -0.01544189453125,
+            -0.0296630859375,
+            0.033203125,
+            0.10693359375,
+            0.038330078125,
+            0.00286865234375,
+            0.04541015625,
+            0.021484375,
+            -0.04931640625,
+            0.01953125,
+            -0.035400390625,
+            -0.07958984375,
+            -0.07177734375,
+            -0.004119873046875,
+            0.0208740234375,
+            0.10498046875,
+            -0.006011962890625,
+            -0.04248046875,
+            -0.045654296875,
+            -0.001434326171875,
+            0.00994873046875,
+            0.0164794921875,
+            0.0277099609375,
+            0.006378173828125,
+            -0.0286865234375,
+            0.0191650390625,
+            -0.02587890625,
+            0.011474609375,
+            0.0703125,
+            0.00732421875,
+            -0.032470703125,
+            -0.0211181640625,
+            -0.05615234375,
+            0.01092529296875,
+            0.031494140625,
+            0.0247802734375,
+            -0.00372314453125,
+            -0.0013427734375,
+            -0.06982421875,
+            -0.00714111328125,
+            0.0196533203125,
+            0.017333984375,
+            0.01336669921875,
+            -0.00188446044921875,
+            -0.01019287109375,
+            -0.00836181640625,
+            0.035400390625,
+            -0.0400390625,
+            0.01177978515625,
+            0.009033203125,
+            0.004425048828125,
+            0.0157470703125,
+            0.0015716552734375,
+            0.007354736328125,
+            -0.037841796875,
+            0.01214599609375,
+            -0.002685546875,
+            -0.0233154296875,
+            0.0107421875,
+            -0.052001953125,
+            -0.057373046875,
+            0.007354736328125,
+            0.007171630859375,
+            -0.02734375,
+            -0.005523681640625,
+            -0.0010528564453125,
+            -0.0106201171875,
+            0.0022125244140625,
+            0.08642578125,
+            -0.033447265625,
+            0.03125,
+            -0.0225830078125,
+            -0.03125,
+            0.007049560546875,
+            -0.0712890625,
+            -0.0023956298828125,
+            0.006317138671875,
+            -0.056640625,
+            0.0206298828125,
+            -0.017333984375,
+            0.048828125,
+            0.0419921875,
+            -0.0037078857421875,
+            0.02978515625,
+            0.0159912109375,
+            0.04443359375,
+            -0.060302734375,
+            -0.038330078125,
+            0.0277099609375,
+            0.036865234375,
+            0.0322265625,
+            -0.006011962890625,
+            -0.022705078125,
+            -0.050537109375,
+            0.041748046875,
+            0.01507568359375,
+            0.007232666015625,
+            0.050048828125,
+            0.041015625,
+            -0.0240478515625,
+            0.006561279296875,
+            0.000301361083984375,
+            -0.01446533203125,
+            0.01507568359375,
+            -0.0556640625,
+            -0.02734375,
+            -0.0081787109375,
+            0.04736328125,
+            0.0025787353515625,
+            -0.0283203125,
+            0.01129150390625,
+            -0.0252685546875,
+            0.0225830078125,
+            0.00421142578125,
+            -0.004791259765625,
+            0.005401611328125,
+            0.006011962890625,
+            -0.057861328125,
+            -0.0289306640625,
+            0.008544921875,
+            -0.0115966796875,
+            0.022705078125,
+            -0.008056640625,
+            -0.01416015625,
+            0.0021209716796875,
+            -0.0038909912109375,
+            0.01025390625,
+            -0.0247802734375,
+            0.01275634765625,
+            0.031494140625,
+            -0.00015926361083984375,
+            -0.004119873046875,
+            0.041259765625,
+            -0.040283203125,
+            0.052734375,
+            -0.052734375,
+            -0.0225830078125,
+            -0.06884765625,
+            -0.07421875,
+            -0.0341796875,
+            0.0196533203125,
+            0.0038604736328125,
+            -0.041015625,
+            -0.005615234375,
+            -0.039794921875,
+            -0.0205078125,
+            0.04931640625,
+            -0.0289306640625,
+            0.006561279296875,
+            0.020751953125,
+            -0.03369140625,
+            0.020263671875,
+            -0.039794921875,
+            0.0081787109375,
+            -0.0020294189453125,
+            0.0218505859375,
+            0.01611328125,
+            -0.0281982421875,
+            -0.027099609375,
+            0.00131988525390625,
+            -0.0654296875,
+            0.023681640625,
+            -0.006256103515625,
+            -0.0211181640625,
+            -0.006103515625,
+            -0.034912109375,
+            -0.00299072265625,
+            -0.0059814453125,
+            -0.036376953125,
+            -0.0174560546875,
+            -0.056640625,
+            0.000316619873046875,
+            -0.033935546875,
+            0.00726318359375,
+            -0.033447265625,
+            0.06591796875,
+            0.0018768310546875,
+            0.02734375,
+            -0.04345703125,
+            0.032958984375,
+            -0.01953125,
+            -0.0034332275390625,
+            0.01300048828125,
+            0.000713348388671875,
+            -0.008056640625,
+            -0.004730224609375,
+            -0.0341796875,
+            0.030517578125,
+            -0.0255126953125,
+            0.0286865234375,
+            -0.04638671875,
+            0.025146484375,
+            -0.03515625,
+            0.001220703125,
+            -0.01068115234375,
+            0.043212890625,
+            -0.01416015625,
+            -0.0223388671875,
+            -0.03369140625,
+            -0.0059814453125,
+            0.007049560546875,
+            0.0220947265625,
+            -0.0281982421875,
+            -0.00811767578125,
+            -0.00799560546875,
+            0.0263671875,
+            0.01373291015625,
+            0.00194549560546875,
+            0.20703125,
+            -0.0076904296875,
+            0.06591796875,
+            -0.0059814453125,
+            0.01043701171875,
+            -0.01251220703125,
+            0.038330078125,
+            -0.0087890625,
+            0.09765625,
+            0.003082275390625,
+            0.0096435546875,
+            0.000152587890625,
+            0.02392578125,
+            -0.04638671875,
+            -0.007781982421875,
+            -0.0030975341796875,
+            -0.00098419189453125,
+            -0.0181884765625,
+            -0.007232666015625,
+            -0.0235595703125,
+            0.033447265625,
+            0.0125732421875,
+            -0.00171661376953125,
+            0.022216796875,
+            -0.000278472900390625,
+            -0.02392578125,
+            0.0294189453125,
+            -0.0128173828125,
+            0.039794921875,
+            -0.0247802734375,
+            -0.049560546875,
+            0.003631591796875,
+            0.0206298828125,
+            0.0164794921875,
+            0.028564453125,
+            -0.01251220703125,
+            0.02294921875,
+            -0.00099945068359375,
+            -0.022216796875,
+            -0.050537109375,
+            0.001861572265625,
+            -0.0191650390625,
+            -0.045654296875,
+            -0.023681640625,
+            0.004119873046875,
+            0.050048828125,
+            -0.007232666015625,
+            0.05029296875,
+            -0.027099609375,
+            -0.0169677734375,
+            0.035888671875,
+            -0.02001953125,
+            -0.0040283203125,
+            0.01043701171875,
+            0.0035400390625,
+            -0.0059814453125,
+            0.0263671875,
+            -0.01220703125,
+            -0.016357421875,
+            0.01483154296875,
+            -0.0390625,
+            -0.00396728515625,
+            0.04345703125,
+            0.023193359375,
+            -0.0172119140625,
+            0.021240234375,
+            -0.04736328125,
+            0.006866455078125,
+            0.036376953125,
+            -0.0289306640625,
+            0.0208740234375,
+            0.011474609375,
+            -0.0260009765625,
+            0.01904296875,
+            0.016357421875,
+            -0.04931640625,
+            -0.0478515625,
+            0.0213623046875,
+            -0.01275634765625,
+            -0.032470703125,
+            -0.0084228515625,
+            -0.001922607421875,
+            0.0191650390625,
+            0.008544921875,
+            -0.037353515625,
+            0.0111083984375,
+            -0.022705078125,
+            -0.04052734375,
+            0.033447265625,
+            -0.01116943359375,
+            -0.03369140625,
+            -0.0167236328125,
+            -0.0303955078125,
+            0.0191650390625,
+            -0.06591796875,
+            0.00433349609375,
+            -0.078125,
+            -0.00732421875,
+            0.04150390625,
+            0.00286865234375,
+            0.0157470703125,
+            -0.00008440017700195312,
+            0.041015625,
+            -0.034423828125,
+            0.053466796875,
+            0.005218505859375,
+            0.01239013671875,
+            -0.006072998046875,
+            -0.00628662109375,
+            0.018798828125,
+            0.00151824951171875,
+            0.01165771484375,
+            0.0164794921875,
+            0.0089111328125,
+            0.0247802734375,
+            0.024658203125,
+            -0.0031585693359375,
+            -0.0181884765625,
+            -0.0103759765625,
+            -0.04541015625,
+            0.00323486328125,
+            0.0157470703125,
+            -0.004791259765625,
+            0.0308837890625,
+            -0.03076171875,
+            0.00506591796875,
+            0.02392578125,
+            -0.0179443359375,
+            0.0269775390625,
+            -0.003509521484375,
+            -0.0181884765625,
+            0.020263671875,
+            0.03076171875,
+            0.00145721435546875,
+            -0.004547119140625,
+            0.0167236328125,
+            0.035400390625,
+            -0.0206298828125,
+            -0.0810546875,
+            -0.0113525390625,
+            -0.02294921875,
+            0.0022735595703125,
+            0.0250244140625,
+            -0.006561279296875,
+            0.0223388671875,
+            0.043212890625,
+            0.03564453125,
+            -0.009765625,
+            0.036376953125,
+            -0.0028228759765625,
+            -0.003204345703125,
+            -0.041748046875,
+            -0.001495361328125,
+            -0.05419921875,
+            -0.04248046875,
+            -0.01708984375,
+            -0.002777099609375,
+            -0.01251220703125,
+            -0.001739501953125,
+            -0.0084228515625,
+            0.00130462646484375,
+            -0.000579833984375,
+            -0.0262451171875,
+            0.01446533203125,
+            0.037841796875,
+            0.02001953125,
+            -0.0157470703125,
+            -0.017333984375,
+            0.006317138671875,
+            0.0125732421875,
+            -0.0206298828125,
+            0.02197265625,
+            0.012939453125,
+            -0.0162353515625,
+            -0.068359375,
+            0.0250244140625,
+            0.006317138671875,
+            0.00201416015625,
+            -0.005126953125,
+            -0.00872802734375,
+            -0.06591796875,
+            0.0233154296875,
+            -0.01806640625,
+            -0.01312255859375,
+            -0.042236328125,
+            -0.03125,
+            -0.0198974609375,
+            -0.00193023681640625,
+            -0.004364013671875,
+            -0.0262451171875,
+            -0.0439453125,
+            -0.020263671875,
+            -0.01043701171875,
+            -0.0250244140625,
+            0.036865234375,
+            0.00946044921875,
+            -0.012939453125,
+            0.0213623046875,
+            -0.032470703125,
+            -0.048095703125,
+            0.020263671875,
+            0.00482177734375,
+            0.048583984375,
+            0.0301513671875,
+            -0.046630859375,
+            -0.021728515625,
+            -0.00408935546875,
+            0.0164794921875,
+            -0.006591796875,
+            -0.01409912109375,
+            0.0439453125,
+            -0.003936767578125,
+            -0.053955078125,
+            -0.0123291015625,
+            -0.025146484375,
+            -0.0185546875,
+            -0.061767578125,
+            0.0045166015625,
+            -0.01348876953125,
+            -0.025634765625,
+            0.0013580322265625,
+            -0.033447265625,
+            -0.0093994140625,
+            -0.039794921875,
+            0.04638671875,
+            -0.00799560546875,
+            -0.03955078125,
+            -0.015869140625,
+            0.0322265625,
+            0.0093994140625,
+            0.02978515625,
+            0.005828857421875,
+            -0.00011873245239257812,
+            -0.003936767578125,
+            0.0274658203125,
+            0.00701904296875,
+            0.000858306884765625,
+            -0.0146484375,
+            0.020263671875,
+            0.04150390625,
+            0.0216064453125,
+            -0.0164794921875,
+            0.043212890625,
+            0.0546875,
+            0.050048828125,
+            0.01470947265625,
+            -0.006561279296875,
+            0.00958251953125,
+            -0.0164794921875,
+            -0.01177978515625,
+            -0.03564453125,
+            -0.009765625,
+            0.007598876953125,
+            -0.00133514404296875,
+            -0.0322265625,
+            0.0211181640625,
+            0.029296875,
+            0.009765625,
+            -0.00151824951171875,
+            -0.0019073486328125,
+            -0.00830078125,
+            -0.032958984375,
+            0.028564453125,
+            -0.0186767578125,
+            -0.03369140625,
+            0.00897216796875,
+            -0.0040283203125,
+            -0.01104736328125,
+            0.01434326171875,
+            0.05419921875,
+            0.012939453125,
+            -0.0341796875,
+            -0.002471923828125,
+            -0.01446533203125,
+            0.04150390625,
+            0.04541015625,
+            0.0203857421875,
+            0.01251220703125,
+            -0.01348876953125,
+            0.01312255859375,
+            0.0052490234375,
+            0.0419921875,
+            -0.01092529296875,
+            -0.022705078125,
+            -0.0252685546875,
+            0.00836181640625,
+            -0.03759765625,
+            -0.03076171875,
+            0.009033203125,
+            -0.017822265625,
+            -0.00982666015625,
+            0.04736328125,
+            0.025634765625,
+            0.01165771484375,
+            -0.032470703125,
+            -0.0267333984375,
+            0.03515625,
+            0.0012664794921875,
+            -0.061767578125,
+            -0.0089111328125,
+            0.050048828125,
+            0.01275634765625,
+            0.0250244140625,
+            0.0191650390625,
+            0.036376953125,
+            0.005828857421875,
+            -0.0047607421875,
+            0.0023956298828125,
+            -0.031494140625,
+            -0.003143310546875,
+            -0.004669189453125,
+            0.0194091796875,
+            0.00897216796875,
+            -0.01104736328125,
+            0.0849609375,
+            0.007232666015625,
+            -0.0201416015625,
+            -0.0260009765625,
+            -0.0172119140625,
+            0.08984375,
+            0.0517578125,
+            -0.0260009765625,
+            -0.0260009765625,
+            -0.01239013671875,
+            -0.0247802734375,
+            0.0164794921875,
+            -0.0225830078125,
+            0.018798828125,
+            -0.038330078125,
+            -0.0308837890625,
+            -0.024658203125,
+            -0.002227783203125,
+            0.003204345703125,
+            0.0185546875,
+            -0.04443359375,
+            -0.004302978515625,
+            0.03271484375,
+            -0.01507568359375,
+            -0.00080108642578125,
+            0.038818359375,
+            0.0040283203125,
+            0.007049560546875,
+            -0.0198974609375,
+            0.004364013671875,
+            -0.02392578125,
+            -0.029296875,
+            -0.0037994384765625,
+            -0.033447265625,
+            0.01348876953125,
+            0.058837890625,
+            0.00811767578125,
+            0.0341796875,
+            0.0064697265625,
+            0.025146484375,
+            -0.000492095947265625,
+            0.0289306640625,
+            -0.0074462890625,
+            0.0189208984375,
+            0.031494140625,
+            -0.00518798828125,
+            -0.0283203125,
+            -0.0011444091796875,
+            0.03857421875,
+            0.036376953125,
+            0.026611328125,
+            0.005615234375,
+            -0.0032958984375,
+            -0.025146484375,
+            -0.02197265625,
+            0.0194091796875,
+            0.0181884765625,
+            0.07275390625,
+            -0.0045166015625,
+            0.025634765625,
+            -0.0286865234375,
+            0.0103759765625,
+            -0.01141357421875,
+            -0.03564453125,
+            0.049560546875,
+            -0.03173828125,
+            -0.0269775390625,
+            0.02734375,
+            0.041015625,
+            -0.01953125,
+            -0.0003528594970703125,
+            -0.0133056640625,
+            0.0203857421875,
+            -0.011474609375,
+            0.0150146484375,
+            0.0001010894775390625,
+            -0.01165771484375,
+            -0.026611328125,
+            0.03564453125,
+            -0.012939453125,
+            0.00024127960205078125,
+            -0.01446533203125,
+            0.0322265625,
+            -0.03125,
+            -0.0093994140625,
+            0.00066375732421875,
+            -0.02197265625,
+            0.0115966796875,
+            -0.033935546875,
+            -0.045166015625,
+            0.0361328125,
+            0.017822265625,
+            0.0322265625,
+            -0.0263671875,
+            0.04345703125,
+            -0.0133056640625,
+            -0.0478515625,
+            0.0087890625,
+            0.0208740234375,
+            -0.014892578125,
+            0.0135498046875,
+            0.044921875,
+            -0.006011962890625,
+            -0.0042724609375,
+            -0.0242919921875,
+            0.025146484375,
+            -0.021728515625,
+            -0.033935546875,
+            -0.0198974609375,
+            0.0172119140625,
+            0.00958251953125,
+            0.01806640625,
+            0.04345703125,
+            -0.01104736328125,
+            0.036376953125,
+            0.00141143798828125,
+            -0.03466796875,
+            -0.0001964569091796875,
+            -0.035400390625,
+            0.0191650390625,
+            0.0031280517578125,
+            0.00848388671875,
+            0.03076171875,
+            -0.0277099609375,
+            0.01953125,
+            0.08447265625,
+            0.0169677734375,
+            -0.02783203125,
+            -0.045166015625,
+            0.0181884765625,
+            0.039794921875,
+            -0.023681640625,
+            -0.00701904296875,
+            0.040771484375,
+            -0.020751953125,
+            0.06689453125,
+            -0.048828125,
+            -0.00164031982421875,
+            0.006256103515625,
+            0.01007080078125,
+            0.00323486328125,
+            -0.03662109375,
+            0.0419921875,
+            0.0002651214599609375,
+            -0.0301513671875,
+            -0.0111083984375,
+            0.072265625,
+            0.10009765625,
+            0.03564453125,
+            -0.0032501220703125,
+            0.06103515625,
+            0.0103759765625,
+            0.011474609375,
+            -0.034912109375,
+            -0.0115966796875,
+            0.025634765625,
+            -0.062255859375,
+            -0.01416015625,
+            0.037841796875,
+            -0.006683349609375,
+            -0.04736328125,
+            0.04345703125,
+            0.0021514892578125,
+            -0.0311279296875,
+            0.00885009765625,
+            -0.0107421875,
+            0.00372314453125,
+            -0.021728515625,
+            -0.00020503997802734375,
+            0.000263214111328125,
+            -0.01446533203125,
+            0.0028228759765625,
+            0.0277099609375
+          ]
+    # res = es.search_question_embedding( index_name, book_id, question_image_embedding, top_k=2)
+    # res = asyncio.run(res)
+    # res = json.dumps(res, ensure_ascii=False, indent=4)
+    # print(res)
+
+    # 9、联合向量搜索和文本搜索，合并二则的打分排序
+    book_id = "12667382"
+    question_image_embedding = [
+            0.00543212890625,
+            -0.005035400390625,
+            0.00714111328125,
+            0.06591796875,
+            -0.032958984375,
+            -0.0380859375,
+            -0.0255126953125,
+            -0.046630859375,
+            0.01031494140625,
+            0.036376953125,
+            0.013916015625,
+            0.0255126953125,
+            -0.0107421875,
+            -0.04345703125,
+            0.0008697509765625,
+            0.02587890625,
+            -0.0201416015625,
+            -0.02099609375,
+            -0.00830078125,
+            0.033203125,
+            -0.01007080078125,
+            0.0224609375,
+            -0.04931640625,
+            0.0206298828125,
+            0.009765625,
+            0.02392578125,
+            0.00095367431640625,
+            0.03369140625,
+            0.005035400390625,
+            0.07373046875,
+            0.0262451171875,
+            0.015625,
+            -0.021728515625,
+            0.0054931640625,
+            0.0308837890625,
+            0.055419921875,
+            -0.0517578125,
+            0.011474609375,
+            -0.023681640625,
+            0.0235595703125,
+            -0.00128173828125,
+            0.0096435546875,
+            0.003936767578125,
+            -0.01953125,
+            -0.05126953125,
+            0.001617431640625,
+            -0.005218505859375,
+            -0.01409912109375,
+            -0.026611328125,
+            0.0198974609375,
+            0.02001953125,
+            0.004974365234375,
+            0.053955078125,
+            -0.0634765625,
+            -0.0654296875,
+            -0.03369140625,
+            -0.08154296875,
+            0.06005859375,
+            0.0223388671875,
+            -0.044921875,
+            -0.0283203125,
+            0.01483154296875,
+            0.150390625,
+            0.026611328125,
+            0.02392578125,
+            -0.00125885009765625,
+            -0.053955078125,
+            -0.03759765625,
+            -0.0390625,
+            0.02734375,
+            -0.01385498046875,
+            0.00140380859375,
+            0.0218505859375,
+            -0.01025390625,
+            -0.0205078125,
+            0.04638671875,
+            0.0145263671875,
+            -0.00927734375,
+            0.01025390625,
+            -0.0225830078125,
+            -0.00909423828125,
+            -0.0142822265625,
+            0.02978515625,
+            0.0101318359375,
+            -0.072265625,
+            -0.049560546875,
+            0.0311279296875,
+            0.0101318359375,
+            -0.00445556640625,
+            -0.03369140625,
+            0.0615234375,
+            -0.021240234375,
+            -0.034912109375,
+            -0.004150390625,
+            0.07177734375,
+            0.0262451171875,
+            -0.013671875,
+            0.03369140625,
+            0.021728515625,
+            0.0252685546875,
+            -0.00982666015625,
+            -0.0028228759765625,
+            -0.00151824951171875,
+            0.003753662109375,
+            0.004791259765625,
+            -0.03759765625,
+            0.025146484375,
+            0.0235595703125,
+            -0.0103759765625,
+            0.0084228515625,
+            -0.0191650390625,
+            0.044921875,
+            0.052001953125,
+            -0.053955078125,
+            0.0206298828125,
+            0.036376953125,
+            0.01202392578125,
+            0.0196533203125,
+            0.025146484375,
+            -0.000457763671875,
+            -0.0033721923828125,
+            -0.0101318359375,
+            0.005035400390625,
+            0.0089111328125,
+            0.002227783203125,
+            -0.041015625,
+            0.00927734375,
+            0.10693359375,
+            0.01043701171875,
+            0.00616455078125,
+            0.013916015625,
+            0.0035858154296875,
+            -0.0283203125,
+            -0.06591796875,
+            0.016845703125,
+            -0.0615234375,
+            -0.01385498046875,
+            -0.05029296875,
+            -0.01556396484375,
+            -0.0128173828125,
+            -0.0140380859375,
+            0.00732421875,
+            -0.0164794921875,
+            0.01239013671875,
+            0.0150146484375,
+            -0.0169677734375,
+            -0.142578125,
+            -0.0008087158203125,
+            -0.007171630859375,
+            0.0033416748046875,
+            0.03662109375,
+            -0.00341796875,
+            -0.0198974609375,
+            -0.03955078125,
+            -0.06640625,
+            -0.05712890625,
+            0.0133056640625,
+            -0.0277099609375,
+            -0.005462646484375,
+            -0.0224609375,
+            0.002166748046875,
+            0.0296630859375,
+            -0.030517578125,
+            -0.029052734375,
+            0.030517578125,
+            -0.0162353515625,
+            -0.0252685546875,
+            -0.0174560546875,
+            -0.023193359375,
+            0.005340576171875,
+            -0.026611328125,
+            -0.006011962890625,
+            -0.01611328125,
+            -0.033203125,
+            -0.000820159912109375,
+            0.04248046875,
+            -0.0301513671875,
+            0.019287109375,
+            0.00909423828125,
+            0.0400390625,
+            0.03564453125,
+            0.030517578125,
+            0.0140380859375,
+            -0.0014495849609375,
+            0.01251220703125,
+            -0.0556640625,
+            0.04248046875,
+            -0.056640625,
+            -0.030517578125,
+            -0.009033203125,
+            -0.01165771484375,
+            -0.0277099609375,
+            0.0087890625,
+            0.024658203125,
+            -0.043701171875,
+            0.0146484375,
+            -0.020751953125,
+            0.01007080078125,
+            0.0164794921875,
+            0.06591796875,
+            -0.06298828125,
+            0.0303955078125,
+            -0.020263671875,
+            -0.007171630859375,
+            0.004425048828125,
+            0.0020751953125,
+            -0.01373291015625,
+            0.050537109375,
+            -0.08203125,
+            -0.036865234375,
+            0.019775390625,
+            -0.0050048828125,
+            0.06640625,
+            -0.00823974609375,
+            0.04248046875,
+            -0.02734375,
+            0.004425048828125,
+            0.006500244140625,
+            -0.00537109375,
+            -0.0546875,
+            0.01470947265625,
+            0.0089111328125,
+            0.0025787353515625,
+            -0.00860595703125,
+            0.018310546875,
+            -0.0208740234375,
+            -0.06689453125,
+            -0.00592041015625,
+            -0.0303955078125,
+            -0.0021514892578125,
+            0.00372314453125,
+            0.0218505859375,
+            -0.0301513671875,
+            0.02587890625,
+            -0.01239013671875,
+            0.04541015625,
+            0.03662109375,
+            0.07421875,
+            0.0225830078125,
+            0.000385284423828125,
+            0.06396484375,
+            -0.0020294189453125,
+            0.008056640625,
+            0.0111083984375,
+            0.0081787109375,
+            0.033447265625,
+            -0.01544189453125,
+            0.09912109375,
+            -0.00994873046875,
+            0.0208740234375,
+            -0.044921875,
+            -0.017333984375,
+            0.0211181640625,
+            0.08056640625,
+            -0.02294921875,
+            0.062255859375,
+            0.01708984375,
+            -0.011474609375,
+            0.03125,
+            0.018798828125,
+            0.0019683837890625,
+            0.0390625,
+            -0.0052490234375,
+            -0.01312255859375,
+            -0.002044677734375,
+            -0.046630859375,
+            0.015625,
+            0.037353515625,
+            0.002777099609375,
+            -0.00811767578125,
+            0.0233154296875,
+            -0.007232666015625,
+            0.039794921875,
+            0.009765625,
+            0.01708984375,
+            0.043212890625,
+            0.0101318359375,
+            0.02783203125,
+            -0.021484375,
+            -0.01470947265625,
+            -0.013671875,
+            0.01470947265625,
+            -0.032470703125,
+            -0.0185546875,
+            -0.00506591796875,
+            0.03125,
+            -0.03125,
+            0.048095703125,
+            -0.01165771484375,
+            0.0296630859375,
+            0.017822265625,
+            -0.011474609375,
+            0.00787353515625,
+            0.005645751953125,
+            -0.0093994140625,
+            0.0380859375,
+            -0.017333984375,
+            0.0255126953125,
+            -0.01806640625,
+            0.033447265625,
+            -0.001739501953125,
+            -0.0191650390625,
+            0.0054931640625,
+            0.053466796875,
+            -0.0308837890625,
+            -0.006072998046875,
+            0.0179443359375,
+            0.025634765625,
+            -0.01318359375,
+            0.01214599609375,
+            -0.0040283203125,
+            0.03125,
+            0.047119140625,
+            0.056640625,
+            0.01116943359375,
+            -0.0235595703125,
+            0.00872802734375,
+            0.003936767578125,
+            -0.000652313232421875,
+            -0.004638671875,
+            -0.00341796875,
+            0.0035400390625,
+            0.0322265625,
+            0.0169677734375,
+            0.008056640625,
+            -0.0262451171875,
+            -0.080078125,
+            -0.04638671875,
+            0.017822265625,
+            -0.01544189453125,
+            -0.0296630859375,
+            0.033203125,
+            0.10693359375,
+            0.038330078125,
+            0.00286865234375,
+            0.04541015625,
+            0.021484375,
+            -0.04931640625,
+            0.01953125,
+            -0.035400390625,
+            -0.07958984375,
+            -0.07177734375,
+            -0.004119873046875,
+            0.0208740234375,
+            0.10498046875,
+            -0.006011962890625,
+            -0.04248046875,
+            -0.045654296875,
+            -0.001434326171875,
+            0.00994873046875,
+            0.0164794921875,
+            0.0277099609375,
+            0.006378173828125,
+            -0.0286865234375,
+            0.0191650390625,
+            -0.02587890625,
+            0.011474609375,
+            0.0703125,
+            0.00732421875,
+            -0.032470703125,
+            -0.0211181640625,
+            -0.05615234375,
+            0.01092529296875,
+            0.031494140625,
+            0.0247802734375,
+            -0.00372314453125,
+            -0.0013427734375,
+            -0.06982421875,
+            -0.00714111328125,
+            0.0196533203125,
+            0.017333984375,
+            0.01336669921875,
+            -0.00188446044921875,
+            -0.01019287109375,
+            -0.00836181640625,
+            0.035400390625,
+            -0.0400390625,
+            0.01177978515625,
+            0.009033203125,
+            0.004425048828125,
+            0.0157470703125,
+            0.0015716552734375,
+            0.007354736328125,
+            -0.037841796875,
+            0.01214599609375,
+            -0.002685546875,
+            -0.0233154296875,
+            0.0107421875,
+            -0.052001953125,
+            -0.057373046875,
+            0.007354736328125,
+            0.007171630859375,
+            -0.02734375,
+            -0.005523681640625,
+            -0.0010528564453125,
+            -0.0106201171875,
+            0.0022125244140625,
+            0.08642578125,
+            -0.033447265625,
+            0.03125,
+            -0.0225830078125,
+            -0.03125,
+            0.007049560546875,
+            -0.0712890625,
+            -0.0023956298828125,
+            0.006317138671875,
+            -0.056640625,
+            0.0206298828125,
+            -0.017333984375,
+            0.048828125,
+            0.0419921875,
+            -0.0037078857421875,
+            0.02978515625,
+            0.0159912109375,
+            0.04443359375,
+            -0.060302734375,
+            -0.038330078125,
+            0.0277099609375,
+            0.036865234375,
+            0.0322265625,
+            -0.006011962890625,
+            -0.022705078125,
+            -0.050537109375,
+            0.041748046875,
+            0.01507568359375,
+            0.007232666015625,
+            0.050048828125,
+            0.041015625,
+            -0.0240478515625,
+            0.006561279296875,
+            0.000301361083984375,
+            -0.01446533203125,
+            0.01507568359375,
+            -0.0556640625,
+            -0.02734375,
+            -0.0081787109375,
+            0.04736328125,
+            0.0025787353515625,
+            -0.0283203125,
+            0.01129150390625,
+            -0.0252685546875,
+            0.0225830078125,
+            0.00421142578125,
+            -0.004791259765625,
+            0.005401611328125,
+            0.006011962890625,
+            -0.057861328125,
+            -0.0289306640625,
+            0.008544921875,
+            -0.0115966796875,
+            0.022705078125,
+            -0.008056640625,
+            -0.01416015625,
+            0.0021209716796875,
+            -0.0038909912109375,
+            0.01025390625,
+            -0.0247802734375,
+            0.01275634765625,
+            0.031494140625,
+            -0.00015926361083984375,
+            -0.004119873046875,
+            0.041259765625,
+            -0.040283203125,
+            0.052734375,
+            -0.052734375,
+            -0.0225830078125,
+            -0.06884765625,
+            -0.07421875,
+            -0.0341796875,
+            0.0196533203125,
+            0.0038604736328125,
+            -0.041015625,
+            -0.005615234375,
+            -0.039794921875,
+            -0.0205078125,
+            0.04931640625,
+            -0.0289306640625,
+            0.006561279296875,
+            0.020751953125,
+            -0.03369140625,
+            0.020263671875,
+            -0.039794921875,
+            0.0081787109375,
+            -0.0020294189453125,
+            0.0218505859375,
+            0.01611328125,
+            -0.0281982421875,
+            -0.027099609375,
+            0.00131988525390625,
+            -0.0654296875,
+            0.023681640625,
+            -0.006256103515625,
+            -0.0211181640625,
+            -0.006103515625,
+            -0.034912109375,
+            -0.00299072265625,
+            -0.0059814453125,
+            -0.036376953125,
+            -0.0174560546875,
+            -0.056640625,
+            0.000316619873046875,
+            -0.033935546875,
+            0.00726318359375,
+            -0.033447265625,
+            0.06591796875,
+            0.0018768310546875,
+            0.02734375,
+            -0.04345703125,
+            0.032958984375,
+            -0.01953125,
+            -0.0034332275390625,
+            0.01300048828125,
+            0.000713348388671875,
+            -0.008056640625,
+            -0.004730224609375,
+            -0.0341796875,
+            0.030517578125,
+            -0.0255126953125,
+            0.0286865234375,
+            -0.04638671875,
+            0.025146484375,
+            -0.03515625,
+            0.001220703125,
+            -0.01068115234375,
+            0.043212890625,
+            -0.01416015625,
+            -0.0223388671875,
+            -0.03369140625,
+            -0.0059814453125,
+            0.007049560546875,
+            0.0220947265625,
+            -0.0281982421875,
+            -0.00811767578125,
+            -0.00799560546875,
+            0.0263671875,
+            0.01373291015625,
+            0.00194549560546875,
+            0.20703125,
+            -0.0076904296875,
+            0.06591796875,
+            -0.0059814453125,
+            0.01043701171875,
+            -0.01251220703125,
+            0.038330078125,
+            -0.0087890625,
+            0.09765625,
+            0.003082275390625,
+            0.0096435546875,
+            0.000152587890625,
+            0.02392578125,
+            -0.04638671875,
+            -0.007781982421875,
+            -0.0030975341796875,
+            -0.00098419189453125,
+            -0.0181884765625,
+            -0.007232666015625,
+            -0.0235595703125,
+            0.033447265625,
+            0.0125732421875,
+            -0.00171661376953125,
+            0.022216796875,
+            -0.000278472900390625,
+            -0.02392578125,
+            0.0294189453125,
+            -0.0128173828125,
+            0.039794921875,
+            -0.0247802734375,
+            -0.049560546875,
+            0.003631591796875,
+            0.0206298828125,
+            0.0164794921875,
+            0.028564453125,
+            -0.01251220703125,
+            0.02294921875,
+            -0.00099945068359375,
+            -0.022216796875,
+            -0.050537109375,
+            0.001861572265625,
+            -0.0191650390625,
+            -0.045654296875,
+            -0.023681640625,
+            0.004119873046875,
+            0.050048828125,
+            -0.007232666015625,
+            0.05029296875,
+            -0.027099609375,
+            -0.0169677734375,
+            0.035888671875,
+            -0.02001953125,
+            -0.0040283203125,
+            0.01043701171875,
+            0.0035400390625,
+            -0.0059814453125,
+            0.0263671875,
+            -0.01220703125,
+            -0.016357421875,
+            0.01483154296875,
+            -0.0390625,
+            -0.00396728515625,
+            0.04345703125,
+            0.023193359375,
+            -0.0172119140625,
+            0.021240234375,
+            -0.04736328125,
+            0.006866455078125,
+            0.036376953125,
+            -0.0289306640625,
+            0.0208740234375,
+            0.011474609375,
+            -0.0260009765625,
+            0.01904296875,
+            0.016357421875,
+            -0.04931640625,
+            -0.0478515625,
+            0.0213623046875,
+            -0.01275634765625,
+            -0.032470703125,
+            -0.0084228515625,
+            -0.001922607421875,
+            0.0191650390625,
+            0.008544921875,
+            -0.037353515625,
+            0.0111083984375,
+            -0.022705078125,
+            -0.04052734375,
+            0.033447265625,
+            -0.01116943359375,
+            -0.03369140625,
+            -0.0167236328125,
+            -0.0303955078125,
+            0.0191650390625,
+            -0.06591796875,
+            0.00433349609375,
+            -0.078125,
+            -0.00732421875,
+            0.04150390625,
+            0.00286865234375,
+            0.0157470703125,
+            -0.00008440017700195312,
+            0.041015625,
+            -0.034423828125,
+            0.053466796875,
+            0.005218505859375,
+            0.01239013671875,
+            -0.006072998046875,
+            -0.00628662109375,
+            0.018798828125,
+            0.00151824951171875,
+            0.01165771484375,
+            0.0164794921875,
+            0.0089111328125,
+            0.0247802734375,
+            0.024658203125,
+            -0.0031585693359375,
+            -0.0181884765625,
+            -0.0103759765625,
+            -0.04541015625,
+            0.00323486328125,
+            0.0157470703125,
+            -0.004791259765625,
+            0.0308837890625,
+            -0.03076171875,
+            0.00506591796875,
+            0.02392578125,
+            -0.0179443359375,
+            0.0269775390625,
+            -0.003509521484375,
+            -0.0181884765625,
+            0.020263671875,
+            0.03076171875,
+            0.00145721435546875,
+            -0.004547119140625,
+            0.0167236328125,
+            0.035400390625,
+            -0.0206298828125,
+            -0.0810546875,
+            -0.0113525390625,
+            -0.02294921875,
+            0.0022735595703125,
+            0.0250244140625,
+            -0.006561279296875,
+            0.0223388671875,
+            0.043212890625,
+            0.03564453125,
+            -0.009765625,
+            0.036376953125,
+            -0.0028228759765625,
+            -0.003204345703125,
+            -0.041748046875,
+            -0.001495361328125,
+            -0.05419921875,
+            -0.04248046875,
+            -0.01708984375,
+            -0.002777099609375,
+            -0.01251220703125,
+            -0.001739501953125,
+            -0.0084228515625,
+            0.00130462646484375,
+            -0.000579833984375,
+            -0.0262451171875,
+            0.01446533203125,
+            0.037841796875,
+            0.02001953125,
+            -0.0157470703125,
+            -0.017333984375,
+            0.006317138671875,
+            0.0125732421875,
+            -0.0206298828125,
+            0.02197265625,
+            0.012939453125,
+            -0.0162353515625,
+            -0.068359375,
+            0.0250244140625,
+            0.006317138671875,
+            0.00201416015625,
+            -0.005126953125,
+            -0.00872802734375,
+            -0.06591796875,
+            0.0233154296875,
+            -0.01806640625,
+            -0.01312255859375,
+            -0.042236328125,
+            -0.03125,
+            -0.0198974609375,
+            -0.00193023681640625,
+            -0.004364013671875,
+            -0.0262451171875,
+            -0.0439453125,
+            -0.020263671875,
+            -0.01043701171875,
+            -0.0250244140625,
+            0.036865234375,
+            0.00946044921875,
+            -0.012939453125,
+            0.0213623046875,
+            -0.032470703125,
+            -0.048095703125,
+            0.020263671875,
+            0.00482177734375,
+            0.048583984375,
+            0.0301513671875,
+            -0.046630859375,
+            -0.021728515625,
+            -0.00408935546875,
+            0.0164794921875,
+            -0.006591796875,
+            -0.01409912109375,
+            0.0439453125,
+            -0.003936767578125,
+            -0.053955078125,
+            -0.0123291015625,
+            -0.025146484375,
+            -0.0185546875,
+            -0.061767578125,
+            0.0045166015625,
+            -0.01348876953125,
+            -0.025634765625,
+            0.0013580322265625,
+            -0.033447265625,
+            -0.0093994140625,
+            -0.039794921875,
+            0.04638671875,
+            -0.00799560546875,
+            -0.03955078125,
+            -0.015869140625,
+            0.0322265625,
+            0.0093994140625,
+            0.02978515625,
+            0.005828857421875,
+            -0.00011873245239257812,
+            -0.003936767578125,
+            0.0274658203125,
+            0.00701904296875,
+            0.000858306884765625,
+            -0.0146484375,
+            0.020263671875,
+            0.04150390625,
+            0.0216064453125,
+            -0.0164794921875,
+            0.043212890625,
+            0.0546875,
+            0.050048828125,
+            0.01470947265625,
+            -0.006561279296875,
+            0.00958251953125,
+            -0.0164794921875,
+            -0.01177978515625,
+            -0.03564453125,
+            -0.009765625,
+            0.007598876953125,
+            -0.00133514404296875,
+            -0.0322265625,
+            0.0211181640625,
+            0.029296875,
+            0.009765625,
+            -0.00151824951171875,
+            -0.0019073486328125,
+            -0.00830078125,
+            -0.032958984375,
+            0.028564453125,
+            -0.0186767578125,
+            -0.03369140625,
+            0.00897216796875,
+            -0.0040283203125,
+            -0.01104736328125,
+            0.01434326171875,
+            0.05419921875,
+            0.012939453125,
+            -0.0341796875,
+            -0.002471923828125,
+            -0.01446533203125,
+            0.04150390625,
+            0.04541015625,
+            0.0203857421875,
+            0.01251220703125,
+            -0.01348876953125,
+            0.01312255859375,
+            0.0052490234375,
+            0.0419921875,
+            -0.01092529296875,
+            -0.022705078125,
+            -0.0252685546875,
+            0.00836181640625,
+            -0.03759765625,
+            -0.03076171875,
+            0.009033203125,
+            -0.017822265625,
+            -0.00982666015625,
+            0.04736328125,
+            0.025634765625,
+            0.01165771484375,
+            -0.032470703125,
+            -0.0267333984375,
+            0.03515625,
+            0.0012664794921875,
+            -0.061767578125,
+            -0.0089111328125,
+            0.050048828125,
+            0.01275634765625,
+            0.0250244140625,
+            0.0191650390625,
+            0.036376953125,
+            0.005828857421875,
+            -0.0047607421875,
+            0.0023956298828125,
+            -0.031494140625,
+            -0.003143310546875,
+            -0.004669189453125,
+            0.0194091796875,
+            0.00897216796875,
+            -0.01104736328125,
+            0.0849609375,
+            0.007232666015625,
+            -0.0201416015625,
+            -0.0260009765625,
+            -0.0172119140625,
+            0.08984375,
+            0.0517578125,
+            -0.0260009765625,
+            -0.0260009765625,
+            -0.01239013671875,
+            -0.0247802734375,
+            0.0164794921875,
+            -0.0225830078125,
+            0.018798828125,
+            -0.038330078125,
+            -0.0308837890625,
+            -0.024658203125,
+            -0.002227783203125,
+            0.003204345703125,
+            0.0185546875,
+            -0.04443359375,
+            -0.004302978515625,
+            0.03271484375,
+            -0.01507568359375,
+            -0.00080108642578125,
+            0.038818359375,
+            0.0040283203125,
+            0.007049560546875,
+            -0.0198974609375,
+            0.004364013671875,
+            -0.02392578125,
+            -0.029296875,
+            -0.0037994384765625,
+            -0.033447265625,
+            0.01348876953125,
+            0.058837890625,
+            0.00811767578125,
+            0.0341796875,
+            0.0064697265625,
+            0.025146484375,
+            -0.000492095947265625,
+            0.0289306640625,
+            -0.0074462890625,
+            0.0189208984375,
+            0.031494140625,
+            -0.00518798828125,
+            -0.0283203125,
+            -0.0011444091796875,
+            0.03857421875,
+            0.036376953125,
+            0.026611328125,
+            0.005615234375,
+            -0.0032958984375,
+            -0.025146484375,
+            -0.02197265625,
+            0.0194091796875,
+            0.0181884765625,
+            0.07275390625,
+            -0.0045166015625,
+            0.025634765625,
+            -0.0286865234375,
+            0.0103759765625,
+            -0.01141357421875,
+            -0.03564453125,
+            0.049560546875,
+            -0.03173828125,
+            -0.0269775390625,
+            0.02734375,
+            0.041015625,
+            -0.01953125,
+            -0.0003528594970703125,
+            -0.0133056640625,
+            0.0203857421875,
+            -0.011474609375,
+            0.0150146484375,
+            0.0001010894775390625,
+            -0.01165771484375,
+            -0.026611328125,
+            0.03564453125,
+            -0.012939453125,
+            0.00024127960205078125,
+            -0.01446533203125,
+            0.0322265625,
+            -0.03125,
+            -0.0093994140625,
+            0.00066375732421875,
+            -0.02197265625,
+            0.0115966796875,
+            -0.033935546875,
+            -0.045166015625,
+            0.0361328125,
+            0.017822265625,
+            0.0322265625,
+            -0.0263671875,
+            0.04345703125,
+            -0.0133056640625,
+            -0.0478515625,
+            0.0087890625,
+            0.0208740234375,
+            -0.014892578125,
+            0.0135498046875,
+            0.044921875,
+            -0.006011962890625,
+            -0.0042724609375,
+            -0.0242919921875,
+            0.025146484375,
+            -0.021728515625,
+            -0.033935546875,
+            -0.0198974609375,
+            0.0172119140625,
+            0.00958251953125,
+            0.01806640625,
+            0.04345703125,
+            -0.01104736328125,
+            0.036376953125,
+            0.00141143798828125,
+            -0.03466796875,
+            -0.0001964569091796875,
+            -0.035400390625,
+            0.0191650390625,
+            0.0031280517578125,
+            0.00848388671875,
+            0.03076171875,
+            -0.0277099609375,
+            0.01953125,
+            0.08447265625,
+            0.0169677734375,
+            -0.02783203125,
+            -0.045166015625,
+            0.0181884765625,
+            0.039794921875,
+            -0.023681640625,
+            -0.00701904296875,
+            0.040771484375,
+            -0.020751953125,
+            0.06689453125,
+            -0.048828125,
+            -0.00164031982421875,
+            0.006256103515625,
+            0.01007080078125,
+            0.00323486328125,
+            -0.03662109375,
+            0.0419921875,
+            0.0002651214599609375,
+            -0.0301513671875,
+            -0.0111083984375,
+            0.072265625,
+            0.10009765625,
+            0.03564453125,
+            -0.0032501220703125,
+            0.06103515625,
+            0.0103759765625,
+            0.011474609375,
+            -0.034912109375,
+            -0.0115966796875,
+            0.025634765625,
+            -0.062255859375,
+            -0.01416015625,
+            0.037841796875,
+            -0.006683349609375,
+            -0.04736328125,
+            0.04345703125,
+            0.0021514892578125,
+            -0.0311279296875,
+            0.00885009765625,
+            -0.0107421875,
+            0.00372314453125,
+            -0.021728515625,
+            -0.00020503997802734375,
+            0.000263214111328125,
+            -0.01446533203125,
+            0.0028228759765625,
+            0.0277099609375
+          ]
+    question_ocr = "画一画"
+    # res = es.search_question_textAndEmbedding( index_name, book_id, question_ocr, question_image_embedding, top_k=2)
+    # res = asyncio.run(res)
+    # res = json.dumps(res, ensure_ascii=False, indent=4)
+    # print(res)
+
+
+
+
+

tools.py

+import requests,re,os,sys
+import base64
+import json
+import time
+from volcenginesdkarkruntime import Ark  # pip install -U volcengine-python-sdk[ark]
+
+def get_file_content(filePath):
+    with open(filePath, 'rb') as fp:
+        return fp.read()
+
+
+ocr_example = {"/home/liuxin/work/search_question/data/12677472-语文1-160.pdf.xlsx-题目-原图/1151411.jpg": """"
+四、2022·浙江,7~9)阅读下面的文字,完成
+1~3题。
+中国食客说起中华美食之道，往往喜欢引用
+孔子的“食不厌精,脍不厌细”八个字。其实，孔
+子所言的“食不厌精,脍不厌细”，更侧重于祭祀
+时饮食的态度而非对味道的追求。孔子生活的
+春秋末期，烹饪、碓春、切肉工艺均相对原始，将
+“食”做“精”“脍”做“细”,体现了厨人与食者严
+肃认真的态度。孔子的饮食观背后，是其心怀的
+礼制。《礼记》所言“夫礼之初,始诸饮食”,大意
+即是“礼仪制度和风俗习惯始于饮食活动”
+古代中国对食物的“淡漠”不仅出于食材的
+积累、交融的缓慢，更在于儒家对口腹之欲的“打
+压”
+。一方面，孔子“君子谋道不谋食”的教诲让
+士大夫阶层往往远离庖厨而以修齐治平为已任:
+另一方面，自汉武帝刘彻“罢黜百家,独尊儒术
+后，士大夫阶层仕途通畅，“学而优则仕”也有着
+丰富的现实回报。至晚在唐代之前，文人对于饮
+食之事是少有重视的。
+隋唐时期饮食文化尤其是宴席之风虽有较
+大发展，但在盛世文治武功的影响下，士大夫阶
+层的追求依然在“提笔安天下、马上定乾坤”之
+中，“烹羊宰牛”式的盛筵并没有孕育出与之相当
+的饮食文化。唐代盛极一时的“烧尾宴”，也只是
+公卿士大夫的盛宴,远非平民百姓所能享受。
+转折来自于两宋:从个体角度来看，两宋文
+化昌盛导致读书人与日俱增以至于仕途门槛抬
+高，同时武功疲弱又令多少人壮志难酬;从朝廷
+角度来看，宋室有鉴于唐朝藩镇割据之痛，自宋
+太祖赵匡胤“杯酒释兵权”始便鼓励朝臣“择便好
+田宅市之，为子孙立永远之业，多致歌儿舞女，日
+饮酒相欢，以终其天年”。用舍行藏之下，也不由
+得士大夫们不将视线转向饮食了。
+元朝统一后，汉族士人愈加边缘化。明清易
+代，朝廷中枢又多为满族垄断，“学而优则仕”的
+路途不再畅通无阻，文人的兴趣自然而然愈加转
+向声色大马。如以“小品圣手”名世的张岱，便在
+《陶庵梦忆》中洋洋自得地夸口“越中清馋，无过
+余者”，从北京的革婆果到台州的江瑶柱，从山西
+的天花菜到临海的枕头瓜，大明两京一十三省的
+美食竟被他尝了个遍。又如戏曲大家李渔，一边
+醉心于梨园之乐，一边也不忘鲜衣美食这一类
+“家居有事”，并在理论巨著《闲情偶寄》中加入
+“饮馔”一部,系统阐述其“存原味、求真趣”的饮
+食美学思想与“宗自然、尊鲜味”饮食文化观念
+特殊的时代背景使得“饮食之人”不再被轻
+贱，于是一大批美食家在清代前半叶应运而生:
+在这一背景下，“食圣”袁枚登场了。
+袁枚在《与薛寿鱼书》中公然提出“夫所谓不
+朽者，非必周，孔而后不朽也
+羿之射，秋之变
+俞跗之医，皆可以不朽也”，而他自己则将饮食之
+道视为堪与周公孔子之为相媲美的事业，因此可
+以毫无顾忌地“每食于某氏而饱，必使家厨往彼
+灶觚，执弟子之礼”。
+袁枚作诗以“性灵说”为主张，认为诗应直抒
+心灵，表达真意，这一主张也融合到了饮食中:他
+认为在烹饪之前要了解食材、尊重物性，注意食
+材间的搭配和时间把握;他反对铺张浪费，提出
+看佳原不在钱多”，食材之美更在于物尽其用;
+他将人文主义引入饮食，宣扬“物为人用,使之死
+可也，使之求死不得不可也”。他强调烹饪理论
+的重要性，以为中国烹法完全依厨人经验不利于
+传承，为了给后世食客厨人树立典范，又煞费苦
+心撰写出了《随园食单》--这部南北美食集大
+成之作，再一次为中华美食的发展开启了新的
+纪元。
+《随园食单》之前，中国历代亦不乏饮食著
+作，但关于制法的记述往往过于简略，如隋代《食
+经》唐代《烧尾宴食单》之类甚至流于“报菜名
+宋元以降，饮食著作的烹饪方法逐渐明晰，但亦
+停留在“形而下”的层次。而《随园食单》则完成
+了饮食文化从经验向理论的最终蜕变，如“须知
+单”“戒单”中梳理了物性、作料、洗刷、调剂、搭
+配、火候、器具、上菜等方方面面，“上菜须知”中
+的“盐者宜先，淡者宜后;浓者宜先，薄者宜后
+等，都是对中国千年烹饪经验一次开创性的总结
+与编排
+在袁枚和他的《随园食单》之后，中国饮食文
+化从“形而上”的思想层面迈上了一个新台阶，在
+之后的百余年里，帮口菜渐渐发达，“四大菜系’
+大菜系”逐渐成形
+摘编自江隐龙《中华尚食之道里
+自有一个民族坚韧的初心》)
+1.下列对文中“中华饮食文化”的相关理解,不正
+确的一项是
+A.中华饮食文化跟礼仪关系紧密，“夫礼之
+初,始诸饮食”说明饮食活动从一开始就被
+赋予礼仪要求
+B.中华饮食文化发展的影响因素有很多,与国
+家的强弱并不一致，而与历代文人士大夫
+的态度有较大关联。
+C.中华饮食文化发展中,唐代以前的文人很少
+重视饮食,跟“君子谋道不谋食”的教诲和
+“学而优则仕”的现实回报有关。
+D.中华饮食文化在明清时代出现了“存原味、
+求真趣”的饮食美学思想与“宗自然、尊鲜
+味”的饮食文化观念，
+2.下列说法符合原文意思的一项是
+A.中国食客喜欢用“食不厌精,脍不厌细”标
+榜中华美食之道，这八个字从一个侧面反
+映了在孔子时代把饮食做到“精细”并非
+B.两宋时期饮食风气发生了变化,产生了转
+折，无论从个体角度还是从朝廷角度来看，
+这都是经济比较发达造成的。
+C.袁枚将自己的饮食之道当作与周公孔子的
+饮食之道相媲美的不朽事业，饮宴饱食归
+来,都派自己的厨子去对方家学习
+D.袁枚把人文主义融入饮食，大致表现在这
+样三方面:尊重物性,要了解食材;不要浪
+费,要物尽其用;物为人用,要保护生命。
+3.概括中华饮食文化得到发展的原因，
+""",
+               "/home/liuxin/work/search_question/data/12677472-语文1-160.pdf.xlsx-题目-原图/1151417.jpg":"""(2024·全国甲，4~6)阅读下面的文字，完成
+1~3题
+偷梁换柱”多指以假代真，用欺骗的手段改
+变事物的性质，然而在古建筑工程领域，偷梁换
+柱”却属于一种科学实用的修缮加固方法。
+梁是截面形状一般为长方形的木料，且木料
+的长度尺寸远大于截面尺寸。梁为水平放置，两
+端的底部有支撑构件。梁主要用于承担建筑上
+部构件及屋顶的全部重量，并把这些重量向下传
+给支撑构件。柱为梁的支撑构件。柱子截面形
+状一般为圆形，长度尺寸远大于截面直径。柱子
+为竖向放置，主要用于承担上部梁传来的重量，
+并向下传递给下部的梁或直接传至地面。梁与
+柱采用榫卯形式连接，形成稳固的大木结构体
+系。位于屋架内的若干梁在竖向被层层往上
+“抬”，上下梁之间由短柱支撑,底部的梁由立于
+地面的立柱支撑。梁、柱均为中国木结构古建筑
+的核心受力、传力构件，缺一不可。
+对于古建筑而言，立于地面的立柱，或因长
+期承受上部结构传来的重量而产生开裂残损，或
+因柱底部位长期受到地面潮气影响而出现糟朽
+残损，这导致木柱强度下降，无法正常支撑梁，
+此时可采用“偷梁换柱”的加固方法。“偷梁换
+柱”实际就是“托梁换柱”。其基本做法为:首先
+将“假柱”即临时的竖向支撑构件)安装在梁底
+部、原柱(原有立柱)旁边;再抽去原柱，使梁传来
+的重量暂时由“假柱”承担;然后安装新柱，新柱
+的材料、尺寸及安装位置与原有立柱相同;最后
+将“假柱”移去。
+完善的“偷梁换柱”加固方法具有科学性，其
+原理主要包括三个方面:其一，从梁的角度而言，
+它是水平受力构件，并把外力向下传给立柱。梁
+只有保持水平稳定状态，才能保证整个大木结构
+的稳定。在加固古建筑的过程中，梁始终受到支
+托，因而能一直保持水平稳定状态。其二，从柱
+的角度而言，它是竖向支撑构件，并最终把上部
+构件的重量传给地基。只有立柱具有充足的承载力，且与梁有可靠连接时，才能有效承担梁传
+来的作用力。加固过程中，技术人员虽然将原柱
+抽去，但是预先将“假柱”设置于原柱附近，让“假
+柱”代替原柱发挥支撑作用，因而换柱过程对结
+构整体的稳定基本无影响。换柱完成后，新柱与
+原柱有着同样的材料、尺寸，且与梁有着相同的
+可靠连接方式，它完全能够代替原柱发挥支撑作
+用。其三，从梁、柱整体结构角度而言，“偷梁换
+柱”方法对整体结构干扰小，且能达到良好的加
+固效果:原柱被新柱原位替换，新柱不仅有很好
+的支撑作用，而且与梁仍有可靠连接;“假柱”仅
+用于加固过程的临时支撑，且在原柱撤去后新柱
+安装前，能够与梁临时组成稳定的结构体系。因
+此，在“偷梁换柱”过程中，梁、柱结构整体始终处
+于稳定状态 1.下列对原文相关内容的理解和分析,不正确的
+一项是
+A.“偷梁换柱”这一成语在现今的使用中多含
+有贬义的色彩,但在古建筑工程领域,它是
+指一种修缮加固的科学方法，完全没有
+贬义。
+B.中国古建筑大木构架剖面示意图展示了几
+种不同位置、不同尺寸的柱，这些柱子中:
+立于地面的立柱比较容易发生糟朽残损的
+情况。
+C.结合图文可以发现,屋顶的重量由上层柱承
+担，然后传给梁，再由梁传递给其下的短
+柱,依次向下传递,最终由底部的立柱传至
+地面。
+D.“偷梁换柱”的加固方法包括托梁、抽柱、换
+柱等步骤,在每一个步骤中梁一直会得到
+很好的支撑,从而始终能够保持水平稳定
+状态。
+★2.请根据原文内容,在下面文段的横线处补写
+出恰当的词语。
+工程实例:故宫太和殿是我国最大的木构
+大殿，明清两代帝王即位或节日庆典都在此举
+行。2004年，技术人员在对太和殿进行勘查
+时，发现有一根立柱下部三分之一的位置出现
+了严重糟朽，于是采取了“偷梁换柱”的方法对
+该立柱进行加固。具体过程如下:先使用“假
+柱”托住原柱上部的梁。“假柱”为完好的木
+料，被安装在
+附近，用于临时支撑
+梁。再把柱子底部糟朽部分抽去，以便用
+代替。原柱糟朽部分去掉后，剩余的部
+分做成巴掌形，与新柱搭接。新柱与被抽去的
+糟朽部分同材料、同形状、同尺寸，且顶部亦做
+成巴掌榫形状。最后再把
+拆除，即
+完成了原有立柱的加固，
+3.清代的古籍中有另一种“偷梁换柱”的记载:当
+某根立柱损坏需要更换时，为节省工料，工匠
+只是在原柱旁边设一根新柱，再撤去原柱。为
+什么第2题“工程实例”中,太和殿修缮没有采用这种更简便的加固方式呢？请简要分析"""}
+
+# 合合ocr
+def recognize_pdf2md( image_path, options=None, is_url=False):
+    """
+    pdf to markdown 官网：https://www.textin.com/document/pdf_to_markdown
+    :param options: request params
+    :param image_path: string
+    :param is_url: bool
+    :return: response
+
+    options = {
+        'pdf_pwd': None,
+        'dpi': 144,  # 设置dpi为144
+        'page_start': 0,
+        'page_count': 1000,  # 设置解析的页数为1000页
+        'apply_document_tree': 0,
+        'markdown_details': 1,
+        'page_details': 0,  # 不包含页面细节信息
+        'table_flavor': 'md',
+        'get_image': 'none',
+        'parse_mode': 'scan',  # 解析模式设为scan
+    }
+    图像宽高需介于20到10000像素之间
+    """
+    _app_id = "2bae9d892b488e1d29f4ca0b650ad7a5"
+    _app_secret = "46d25182d74cb02b9fb8a06734fb73a4"
+    host = 'https://api.textin.com'
+
+    url = host + '/ai/service/v1/pdf_to_markdown'
+    if not options:
+        options = {
+
+        'table_flavor': 'none', # 不进行表格识别，把表格图像当成普通文字段落来识别
+        'parse_mode': 'scan',  # 设置解析模式为scan模式
+        'page_details': 0,  # 包含页面细节
+        'markdown_details': 0,
+        'apply_document_tree': 1,
+        'raw_ocr': 1,
+
+    }
+    headers = {
+        'x-ti-app-id': _app_id,
+        'x-ti-secret-code': _app_secret
+    }
+    if is_url:
+        image = image_path
+        headers['Content-Type'] = 'text/plain'
+    else:
+        image = get_file_content(image_path)
+        headers['Content-Type'] = 'application/octet-stream'
+
+    count = 0
+    res = {"result":{"markdown":""}}
+    while count < 5:
+        try:
+            resp = requests.post(url, data=image, headers=headers, params=options)
+            res = resp.text
+            res = json.loads(res)
+            text = res['result']['markdown']
+
+            break
+        except Exception as e:
+            count += 1
+            if image_path in ocr_example:
+                res = {"result": {"markdown": ocr_example[image_path]}}
+
+                break
+
+            print(f"合合ocr error：{image_path}； {e}")
+
+    res = json.dumps(res, ensure_ascii=False)
+
+    return res
+
+
+
+def image_to_base64( image_path: str) -> str:
+    # 读入图片转为base64位数据
+    with open(image_path, "rb") as f:
+        image_bytes = f.read()
+    # 获取图片格式（如jpg/png）
+    image_format = os.path.splitext(image_path)[1].lower().strip(".")
+    # 拼接豆包要求的Base64格式
+    image_base64 = f"data:image/{image_format};base64,{base64.b64encode(image_bytes).decode('utf-8')}"
+
+    return image_base64
+
+def doubao_image_embedding( image_file, text):
+    # 豆包图文 embedding 模型； 官网：https://www.volcengine.com/docs/82379/1523520
+    doubao_client = Ark(api_key="35f1674f-22b4-434b-9a8d-0d80e8d1ef6b")  # 豆包 图文embedding模型
+    base64_data = image_to_base64(image_file)
+    count = 0
+    while count < 5:
+        try:
+
+            text = text[:4096]
+            resp = doubao_client.multimodal_embeddings.create(
+                model="doubao-embedding-vision-250615",  # "doubao-embedding-vision-250615" embed_dim=2048
+                encoding_format="float",
+                dimensions= 1024,
+                input=[{"text":text,"type":"text"}, {"image_url": {"url": base64_data}, "type": "image_url"}]
+            )
+            image_embedding = resp.data['embedding']
+            break
+        except Exception as e:
+            count += 1
+            print(r"doubao embedding error: ", end=" ")
+            print(image_file)
+            pass
+
+    return image_embedding
+
+
+def doubao_text_embedding(text):
+    # # 豆包文本 embedding 模型
+    doubao_client = Ark(api_key="35f1674f-22b4-434b-9a8d-0d80e8d1ef6b")  # 豆包 图文embedding模型
+    text = text[:4096]
+    count = 0
+    while count < 5:
+        try:
+            resp = doubao_client.multimodal_embeddings.create(
+                model="doubao-embedding-vision-250615",  # "doubao-embedding-vision-250615" embed_dim=2048
+                encoding_format="float",
+                dimensions=1024,
+                input=[{"text": text, "type": "text"}]
+            )
+            text_embedding = resp.data['embedding']
+        except Exception as e:
+            print(f"doubao text embedding error:{e}; text:  {text}" )
+            count += 1
+
+    return text_embedding
+
+
+def monkey_ocr(file_path):
+    url = 'http://61.170.32.8:38878/ocr/text'
+    files = {  "file": (open(file_path, "rb"))     }
+    response = requests.post(
+        url=url,
+        files=files,
+    )
+    result = response.json()
+    return result
+
+if __name__ == "__main__":
+
+
+    start_time = time.time()
+    image = "/home/liuxin/work/search_question/data/人工标注的手机拍题图片/3-1151454.jpg"
+    image = "/home/liuxin/work/search_question/data/12664728-课计划·七年级英语·RJ·上册/93.jpg"
+    # image = "/home/liuxin/work/search_question/data/12677472-语文1-160.pdf.xlsx-题目-原图/1151411.jpg" # 图像尺寸大于10000,超过合合的阈值
+    image= "/home/liuxin/work/search_question/data/人工标注的手机拍题图片/3-1151454.jpg"
+    image = "/home/liuxin/work/search_question/data/人工标注的手机拍题图片/4-1151471.jpg"
+    image = "/home/liuxin/work/search_question/data/人工标注的手机拍题图片/7-1151505.jpg"
+    image= "/home/liuxin/work/search_question/data/12664728-课计划·七年级英语·RJ·上册/93.jpg"
+
+    #### 1、合合ocr：传输文件
+    resp = recognize_pdf2md(image, {
+
+        'table_flavor': 'none', # 不进行表格识别，把表格图像当成普通文字段落来识别
+        'parse_mode': 'scan',  # 设置解析模式为scan模式
+        'page_details': 0,  # 包含页面细节
+        'markdown_details': 0,
+        'apply_document_tree': 1,
+        'raw_ocr': 1,
+
+    })
+
+    print(f"耗时：{time.time()-start_time}")
+    result = json.loads(resp)
+    # result = json.dumps(result, ensure_ascii=False, indent=4)
+    text = result['result']['markdown']
+    print("合合ocr")
+    print(text)
+    #
+    # print("\n\n")
+    #
+    #
+    # image = "/home/liuxin/work/search_question/data/12677472-语文1-160.pdf.xlsx-题目-原图/1151411.jpg"
+    # res = doubao_image_embedding(image, text)
+    # print(res[:5])
+    #
+    # res = doubao_text_embedding(text)  # 接口调不通
+    # print(res[:5])
+
+    res = monkey_ocr(image)
+    print("monkey ocr:")
+    print(res)
+
+
+
+
+
+    print("\n.finished.")
+

tst_search_result.py

+import copy
+from datetime import datetime
+import json,re, os
+import pandas as pd
+from PIL import Image
+import requests
+import base64
+from tritonclient import grpc as triton_grpc
+from paddle_ocr import  infer_paddle_ocr
+from tools import recognize_pdf2md  # 合合ocr
+from volcenginesdkarkruntime import Ark  # pip install -U volcengine-python-sdk[ark]
+
+from api_tst import  get_page_image_url
+
+__path__ = os.path.dirname(os.path.abspath(__file__))
+
+class AddPaddleOCR():
+    # 给每张整图添加paddleOCR的结果，给每个题目添加paddleOCR结果
+    def __init__(self):
+        paddle_ocr_url = '61.170.32.8:38896'
+        self.client_ocr = triton_grpc.InferenceServerClient(paddle_ocr_url)  # 李亚泽部署的paddleOCR
+        self.doubao_client = Ark(api_key="35f1674f-22b4-434b-9a8d-0d80e8d1ef6b")  # 豆包 图文embedding模型
+
+    def read_excel(self, excel_file, sheet_name="题库数据"):
+
+        data = pd.read_excel(excel_file, sheet_name)
+        data.fillna("")
+        data = data.to_dict(orient='records')
+
+        return data
+
+    def save_excel(self, data_list, excel_file, sheet_name="题库数据" ):
+        data2 = pd.DataFrame(data_list)
+        data2.to_excel(excel_file, index=False, sheet_name=sheet_name)
+        print("保存数据成功：", excel_file)
+
+
+    def download_image(self, image_url, save_path):
+        # 发送HTTP请求获取图片内容
+        response = requests.get(image_url, stream=True, timeout=10)
+        # 检查请求是否成功
+        response.raise_for_status()
+
+        # 确保保存路径的目录存在
+        directory = os.path.dirname(save_path)
+        if not os.path.exists(directory):
+            os.makedirs(directory)
+
+        # 写入文件
+        with open(save_path, 'wb') as file:
+            for chunk in response.iter_content(chunk_size=8192):
+                if chunk:
+                    file.write(chunk)
+
+        return True
+
+    def image_to_base64(self, image_path: str) -> str:
+        # 读入图片转为base64位数据
+        with open(image_path, "rb") as f:
+            image_bytes = f.read()
+        # 获取图片格式（如jpg/png）
+        image_format = os.path.splitext(image_path)[1].lower().strip(".")
+        # 拼接豆包要求的Base64格式
+        image_base64 = f"data:image/{image_format};base64,{base64.b64encode(image_bytes).decode('utf-8')}"
+
+        return image_base64
+
+    def doubao_image_embedding(self, image_file, text):
+        # 豆包图文 embedding 模型； 官网：https://www.volcengine.com/docs/82379/1523520
+        base64_data = self.image_to_base64(image_file)
+        text = text[:4096]
+        resp = self.doubao_client.multimodal_embeddings.create(
+            model="doubao-embedding-vision-250615",  # "doubao-embedding-vision-250615" embed_dim=2048
+            encoding_format="float",
+            dimensions= 1024,
+            input=[{"text":text,"type":"text"}, {"image_url": {"url": base64_data}, "type": "image_url"}]
+        )
+        image_embedding = resp.data['embedding']
+        return image_embedding
+
+    def doubao_text_embedding(self, text):
+        # # 豆包文本 embedding 模型
+        text = text[:4096]
+        resp = self.doubao_client.multimodal_embeddings.create(
+            model="doubao-embedding-vision-250615", # "doubao-embedding-vision-250615" embed_dim=2048
+            encoding_format="float",
+            dimensions=1024,
+            input=[{"text": text, "type": "text"}]
+        )
+        text_embedding = resp.data['embedding']
+
+        return text_embedding
+
+    def paddle_ocr(self, file):
+        # im = "/home/liuxin/work/search_book/data/12664728-课计划·七年级英语·RJ·上册/1.jpg"
+        im = Image.open(file).convert('RGB')
+        db_boxes, rec_texts = infer_paddle_ocr(im, self.client_ocr)
+        paddle_ocr = {"db_boxes":db_boxes, "rec_texts":rec_texts}
+        paddle_ocr = json.dumps(paddle_ocr, ensure_ascii=False)
+
+        return paddle_ocr
+
+
+    def get_page_image_url(self, bankId):
+        # 获取整页图片的url
+        url = "https://rays7.5rs.me/matrix/v1.0/aIRecognized/getPageInfoByBankId"
+
+        headers = {
+            "token": "whlg2025!",
+            "Only-For-Backend": "y"
+        }
+        data = { "bankId": bankId }
+
+        response = requests.get(url, headers=headers, params=data)
+        response = response.text
+        sourceImageUrl = json.loads(response)['data']['sourceImageUrl']
+
+        return sourceImageUrl
+
+    def add_imageUrl_and_paddleOCR(self, excel_path,book_id, book_name):
+        # 输入 从拆书平台下载的excel数据，添加标准图片的url列 "source_image_url" 列，添加标准图片paddleOCR的结果 “page_ocr”列
+        sheet_name = "题库数据"
+        data2 = pd.read_excel(excel_path, sheet_name)
+        data2.fillna("")
+        # 获取每张标准图片的 image_url
+        question_ids = data2['题目id']
+        page_ids = data2['电子页码']
+
+        data2 = data2.to_dict(orient='records')
+
+        # 1、获取每个题目图片的paddleOCR结果
+        question_save_path = os.path.join(__path__, "data", str(book_id) + "-" + book_name + "-题目-原图")  # 标准题目原图保存文件夹
+        os.makedirs(question_save_path, exist_ok=True)
+        for line in data2:
+            question_image_url = line['题目图片地址']
+            question_id = str(line['题目id'])
+            question_save_file = os.path.join(question_save_path, question_id+".jpg")
+            print("question_save_file: ", question_save_file)
+            flag = self.download_image(question_image_url, question_save_file)
+            # # question_paddle_ocr = self.paddle_ocr(question_save_file)  # paddleOCR
+            try:
+                question_paddle_ocr = json.loads(recognize_pdf2md(question_save_file))['result']['markdown'] # 合合OCR;图像宽高需介于20到10000像素之间
+            except:
+                question_paddle_ocr = line['题目文本']
+            line['question_ocr']=question_paddle_ocr
+        print("获取每个题目的OCR结束。\n")
+
+        # 2、获取整图的url
+        page_ids2source_image_url = {} # 每张标准图片(整图)的url地址
+        for page_id, question_id in zip(page_ids,question_ids):
+            if page_id not in page_ids2source_image_url.keys():
+                source_image_url = get_page_image_url( question_id)
+                page_ids2source_image_url[page_id] = {"source_image_url":source_image_url}
+
+        print("获取 所有图片(整图)URL结束\n")
+
+        # 3、获取每张标准图片的(整图) paddleOCR结果
+        save_path = os.path.join(__path__, "data",  str(book_id)+"-"+book_name+"-原图")  # 标准原图(整图)保存文件夹
+        os.makedirs(save_path, exist_ok=True)
+        for page_id, source_image_url in page_ids2source_image_url.items():
+            source_image_url = source_image_url['source_image_url']
+            save_file = os.path.join(save_path, f"{page_id}.jpg")
+            print(save_file)
+            flag = self.download_image( source_image_url, save_file)
+            # page_ocr = self.paddle_ocr(save_file)
+            page_ocr = json.loads(recognize_pdf2md(save_file))['result']['markdown']  # 合合OCR
+            page_ids2source_image_url[page_id]['page_ocr'] = page_ocr
+
+        # 拆书平台下载的 excel数据添加  source_image_url 列，和 “page_ocr”列。
+        for line in data2:
+            page_id = line['电子页码']
+            source_image_url = page_ids2source_image_url[page_id]['source_image_url']
+            paddle_ocr = page_ids2source_image_url[page_id]['page_ocr']
+
+            line['source_image_url'] =source_image_url
+            line['page_ocr'] = paddle_ocr
+
+        return data2
+
+    def add_page_image_embedding(self, data_list, image_path):
+        # 添加整页图片 embedding
+        page_id2page_embedding = dict()
+        for line in data_list:
+            page_id = line['电子页码']
+            if page_id not in page_id2page_embedding.keys():
+                page_ocr = line['page_ocr']
+                image_file = os.path.join(image_path, f"{page_id}.jpg")
+                page_image_embedding = self.doubao_image_embedding(image_file, page_ocr)
+                line['page_image_embedding'] = json.dumps(page_image_embedding)
+                page_id2page_embedding[page_id] = page_image_embedding
+            else:
+                page_image_embedding = page_id2page_embedding[page_id]
+                line['page_image_embedding'] = json.dumps(page_image_embedding)
+
+        return data_list
+
+
+    def add_question_image_embedding(self, data_list, image_path):
+        # 添加 题目原图 embedding
+        for line in data_list:
+            bankId = line['题目id']
+            image_file = os.path.join(image_path, str(bankId) + ".jpg") # 题目图片文件
+            image_text = line['question_ocr']
+            question_image_embedding = self.doubao_image_embedding(image_file, image_text)
+            line['question_image_embedding'] = json.dumps(question_image_embedding)
+
+        return data_list
+
+    def get_excel_name(self, path, save_down_excel_path):
+        # 1、已经解析处理预处理的图书（ocr 和向量）
+        save_files = os.listdir(save_down_excel_path)
+        save_files = [item[:-5] for item in save_files if item.endswith('xlsx')]
+
+
+        # 2、从拆书平台下载的图书，还没有进行预处理
+        file_names = os.listdir(path)
+        file_names = [item for item in file_names if item.endswith('xlsx') and item not in save_files]
+        book_ids = [item.split("-")[0] for item in file_names]
+        book_names = ["-".join(item.split("-")[1:]) for item in file_names]
+
+        data = []
+        for file, book_id, book_name in zip(file_names, book_ids, book_names):
+            file = os.path.join(path, file)
+            temp = [file, book_id, book_name]
+            data.append(temp)
+        print(f"拆书平台下载了{len(data)}个excel文件。")
+        return data
+
+    def result(self):
+        # 从拆书平台下载excel数据，添加 图片url列，添加整页图片 paddleOCR结果列；添加题目paddleOCR列，添加以上三列数据后请求api接口将excel插入es数据库
+        # down_excel_data = [excel_path,book_id, book_name]
+        down_excel_data = [
+            # ["/home/liuxin/work/search_book/data/12668851-高二暑假作业化学.pdf.xlsx", "12668851",  "高二暑假作业化学"] ,
+            # ["/home/liuxin/work/search_book/data/12677035-2025《创新教程》新高考试题精选生物学.pdf.xlsx", "12677035",  "2025《创新教程》新高考试题精选生物学"],
+            # ["/home/liuxin/work/search_book/data/12677471-卷1-132.pdf.xlsx", "12677471",  "卷1-132"],
+            # ["/home/liuxin/work/search_book/data/12677472-语文1-160.pdf.xlsx", "12677472",  "语文1-160"],
+            # ["/home/liuxin/work/search_question/data/12663121-衔接教材 地理.pdf.xlsx", "12663121",  "衔接教材地理"],
+            # # ["/home/liuxin/work/search_question/data/12667382-25春北师一数暑假作业.pdf.xlsx", "12667382",  "25春北师一数暑假作业"],
+            # ["/home/liuxin/work/search_question/data/12664728-课计划·七年级英语·RJ·上册（出血文件）.pdf.xlsx", "12664728",  "课计划·七年级英语·RJ·上册（出血文件）"],
+            #
+            # ["/home/liuxin/work/search_question/data/12671977-暑假生活·学期总复习八年级物理通用版6印大度转曲PDF已加码  2025.6.12.pdf.xlsx", "12671977",  "暑假生活·学期总复习八年级物理通用版6"],
+            # ["/home/liuxin/work/search_question/data/12670279-2025版ZT7地-下册横版《锦上添花（期末大赢家）》下册-新编文件5.8.pdf.xlsx",  "12670279", "12670279-2025版ZT7地-下册横版《锦上添花（期末大赢家）》下册-新编文件5.8"],
+
+        ]
+        down_excel_path = "/home/liuxin/work/search_question/data/拆书平台下载excel文件"
+
+        save_down_excel_path = "/home/liuxin/work/search_question/data/拆书平台下载excel文件_添加字段内容"
+        down_excel_data = self.get_excel_name(down_excel_path, save_down_excel_path)
+
+        for item in down_excel_data:
+            excel_path = item[0]
+            book_id = item[1]
+            book_name = item[2]
+            print(f"excel_path: {excel_path}, book_id: {book_id}, book_name: {book_name}")
+            try:
+                question_image_save_path = os.path.join(__path__, "data", str(book_id) + "-" + book_name + "-题目-原图") # 标准题目原图保存文件夹
+                page_image_save_path = os.path.join(__path__, "data", str(book_id) + "-" + book_name + "-原图")  # 标准原图(整图)保存文件夹
+                data_list = AddPaddleocr.add_imageUrl_and_paddleOCR(excel_path, book_id, book_name )
+
+                data_list = self.add_page_image_embedding(data_list, page_image_save_path)          # 添加整页原图的 embedding
+                print("添加 page embedding 完成。")
+                data_list = self.add_question_image_embedding(data_list, question_image_save_path)  # 添加题目原图的 embedding
+                print("添加 question embedding 完成。")
+
+                save_excel_file = os.path.join(page_image_save_path, str(book_id) + "-" + book_name + ".xlsx")   # 保存excel文件
+                self.save_excel(data_list, save_excel_file)
+
+                save_excel_file = os.path.join(save_down_excel_path, str(book_id) + "-" + book_name + ".xlsx")  # 保存excel文件
+                self.save_excel(data_list, save_excel_file)
+            except Exception as e:
+                print(f"error {e}")
+                print(item)
+
+
+
+# 从拆书平台下载excel数据，添加 图片url列，添加整页图片 paddleOCR结果列；添加题目paddleOCR列，添加以上三列数据后请求api接口将excel插入es数据库
+AddPaddleocr = AddPaddleOCR()
+# AddPaddleocr.result()
+# image_path = ""
+# image_embedding = AddPaddleocr.doubao_image_embedding( image_path)
+
+
+
+
+# 测试搜整页图片、搜题目的效果
+class Test():
+    def __init__(self):
+        paddle_ocr_url = '61.170.32.8:38896'
+        self.client_ocr = triton_grpc.InferenceServerClient(paddle_ocr_url)
+        self.doubao_client = Ark(api_key="35f1674f-22b4-434b-9a8d-0d80e8d1ef6b")  # 豆包 图文embedding模型
+        pass
+
+    def image_to_base64(self, image_path: str) -> str:
+        # 读入图片转为base64位数据
+        with open(image_path, "rb") as f:
+            image_bytes = f.read()
+        # 获取图片格式（如jpg/png）
+        image_format = os.path.splitext(image_path)[1].lower().strip(".")
+        # 拼接豆包要求的Base64格式
+        image_base64 = f"data:image/{image_format};base64,{base64.b64encode(image_bytes).decode('utf-8')}"
+
+        return image_base64
+    def download_image(self, image_url, save_path):
+        count = 0
+        while count < 5:
+            try:
+                # 发送HTTP请求获取图片内容
+                response = requests.get(image_url, stream=True, timeout=100)
+                # 检查请求是否成功
+                response.raise_for_status()
+
+                # 确保保存路径的目录存在
+                directory = os.path.dirname(save_path)
+                if not os.path.exists(directory):
+                    os.makedirs(directory)
+
+                # 写入文件
+                with open(save_path, 'wb') as file:
+                    for chunk in response.iter_content(chunk_size=8192):
+                        if chunk:
+                            file.write(chunk)
+                break
+            except:
+                count += 1
+                pass
+
+        return True
+
+    def doubao_image_embedding(self, image_file, text):
+        # 豆包图文 embedding 模型； 官网：https://www.volcengine.com/docs/82379/1523520
+        count = 0
+        while count < 5:
+            try:
+                base64_data = self.image_to_base64(image_file)
+                text = text[:4096]
+                resp = self.doubao_client.multimodal_embeddings.create(
+                    model="doubao-embedding-vision-250615",  # "doubao-embedding-vision-250615" embed_dim=2048
+                    encoding_format="float",
+                    dimensions= 1024,
+                    input=[{"text":text,"type":"text"}, {"image_url": {"url": base64_data}, "type": "image_url"}]
+                )
+                image_embedding = resp.data['embedding']
+                break
+            except Exception as e:
+                count += 1
+                pass
+
+        return image_embedding
+
+    def doubao_text_embedding(self, text):
+        # # 豆包文本 embedding 模型
+        text = text[:4096]
+        resp = self.doubao_client.multimodal_embeddings.create(
+            model="doubao-embedding-vision-250615", # "doubao-embedding-vision-250615" embed_dim=2048
+            encoding_format="float",
+            dimensions=1024,
+            input=[{"text": text, "type": "text"}]
+        )
+        text_embedding = resp.data['embedding']
+
+        return text_embedding
+
+    def read_excel(self, excel_file, sheet_name="题库数据"):
+
+        data = pd.read_excel(excel_file, sheet_name)
+        data.fillna("")
+        data = data.to_dict(orient='records')
+        # data = data[:10]
+        print(f"成功读入excel数据：{excel_file}；len(data):{len(data)}")
+
+        return data
+
+    def read_excel_dir_anno_data(self, es_data_path, anno_data_path, save_phone_image_path):
+        # 入es库的数据：es_data_path； 标注的题目数据图片：anno_data_path; 下载用户手机拍摄的题目图片 save_phone_image_path
+
+        # 1、从excel中读入 写入es库的全量数据
+        bank_id2es_data = {}
+        es_excel_names = os.listdir(es_data_path)
+        es_excel_names = [name for name in es_excel_names if name.endswith('.xlsx')]
+        sheet_name = '题库数据'
+        for excel_name in es_excel_names:
+            book_id = excel_name.split("-")[0]
+            excel_file = os.path.join(es_data_path, excel_name)
+            data = pd.read_excel(excel_file, sheet_name)
+            data.fillna("")
+            data = data.to_dict(orient='records')
+            for line in data:
+                line['book_id'] = str(book_id)
+                bank_id = str(line['题目id'])
+
+                line.pop('page_image_embedding',"")
+                line.pop('question_image_embedding', "")
+                line.pop('序号', "")
+
+                bank_id2es_data[bank_id] = line
+        print("读入所有插入es库的数据 success")
+
+        # 2、读入标注的所有题目数据
+        save_data =[]
+        anno_excel_names = os.listdir(anno_data_path)
+        anno_excel_names = [name for name in anno_excel_names if name.endswith('.xlsx')]
+
+        image_name_all = os.listdir(save_phone_image_path)
+        image_name_all = [name for name in image_name_all if name.endswith('.jpg')]
+        image_name_all = set(image_name_all)
+
+        sheet_name = '题库数据'
+        for excel_name in anno_excel_names:
+            excel_file = os.path.join(anno_data_path, excel_name)
+            data = pd.read_excel(excel_file, sheet_name)
+            data.fillna("")
+            data = data.to_dict(orient='records')
+            for line in data:
+                bank_id = str(line['题目id'])
+                phone_image_url = line['题目图片地址']
+                if bank_id in bank_id2es_data.keys():
+                    es_line = bank_id2es_data[bank_id]
+                    page_id = es_line['电子页码']
+                    book_id = es_line['book_id']
+                    image_url = es_line['题目图片地址']
+                    image_name = f"{page_id}-{bank_id}.jpg"
+                    if image_name not in image_name_all:
+                        phone_image_file = os.path.join(save_phone_image_path, image_name )
+                        flag = self.download_image( phone_image_url, phone_image_file)  # 下载用户拍摄的图片
+
+                    temp = {"book_id":book_id, "电子页码": page_id, "题目id": bank_id,  "题目图片地址": image_url, "题目图片地址phone": phone_image_url}
+                    save_data.append(temp)
+
+                else:
+                    print(f"excel_name:{excel_name}; bank_id: {bank_id} 不在es库中")
+        print(f"人工标注了{len(save_data)}张手机拍摄的题目图片数据。")
+
+        return save_data
+
+
+
+    def save_excel(self, data_list_list, excel_file ):
+        # 一个excel文件保存多个 sheet
+        with pd.ExcelWriter(excel_file) as writer:
+            for index, data_list in enumerate(data_list_list):
+                data = pd.DataFrame(data_list)
+                data.to_excel(writer, sheet_name=f"sheet{index}", index=False)
+
+        print("保存数据成功：", excel_file)
+
+    def paddle_ocr(self, file):
+        # im = "/home/liuxin/work/search_book/data/12664728-课计划·七年级英语·RJ·上册/1.jpg"
+
+        im = Image.open(file).convert('RGB')
+        db_boxes, rec_texts = infer_paddle_ocr(im, self.client_ocr)
+        paddle_ocr = {"db_boxes":db_boxes, "rec_texts":rec_texts}
+        paddle_ocr = json.dumps(paddle_ocr, ensure_ascii=False)
+        paddle_ocr_text = " ".join(rec_texts)
+
+        return paddle_ocr, paddle_ocr_text
+
+    def es_search_page(self, book_id, image_ocr):
+        # es搜索整图的 source_image_url
+        url = 'http://localhost:31001/search_page'
+        url = 'http://61.170.32.8:31001/search_page'
+        headers = {
+            'accept': 'application/json',
+        }
+
+        # 表单数据
+        data = {
+            "book_id": str(book_id),
+            "image_ocr": image_ocr,
+            "top_k": 1
+        }
+        data = json.dumps(data, ensure_ascii=False)
+        response = requests.post(url, headers=headers, data=data)
+        # 输出响应结果
+        # print(f"状态码: {response.status_code}")
+        res = response.json()
+        source_image_url = res['es_search'][0]['_source']['source_image_url']
+        score = res['es_search'][0]['_score']
+
+        return source_image_url, score
+
+    def es_search_question(self, book_id, question_ocr, image_ocr=""):
+        # es 搜索题目的 bankId
+        url = 'http://localhost:31001/search_question_text'
+        url = 'http://61.170.32.8:31001/search_question_text'
+        headers = {
+            'accept': 'application/json',
+        }
+
+        # 表单数据
+        data = {
+            "book_id": str(book_id),
+            "image_ocr": image_ocr,
+            "question_ocr": question_ocr,
+            "top_k": 1
+        }
+        data = json.dumps(data, ensure_ascii=False)
+        response = requests.post(url, headers=headers, data=data)
+        # 输出响应结果
+        # print(f"状态码: {response.status_code}")
+        res = response.json()
+        bankId = res['es_search'][0]['_source']['bankId']
+        score = res['es_search'][0]['_score']
+
+        return bankId, score
+
+    def es_search_question_embedding(self, book_id, question_embedding):
+        # 4、搜题(只用题目的ocr和图片的embedding数据）
+        url = 'http://localhost:31001/search_question_embedding'
+        # url = 'http://61.170.32.8:31001/search_question_embedding'
+        headers = {
+            'accept': 'application/json',
+        }
+
+        # 表单数据
+        data = {
+            "book_id": str(book_id),
+            "question_embedding": json.dumps(question_embedding),
+            "top_k": 1
+        }
+        data = json.dumps(data, ensure_ascii=False)
+        response = requests.post(url, headers=headers, data=data)
+        # 输出响应结果
+        # print(f"状态码: {response.status_code}")
+        res = response.json()
+
+        bankId = res['es_search'][0]['_source']['bankId']
+        score = res['es_search'][0]['_score']
+        return bankId, score
+
+    def search_question_text_and_embedding(self, book_id, question_ocr, question_embedding):
+        # 5、搜题(使用题目ocr的文本搜题，再使用题目ocr和图片整体的向量搜题，联合两个搜索的得分）
+        url = 'http://localhost:31001/search_question_text_and_embedding'
+        # url = 'http://61.170.32.8:31001/search_question_text_and_embedding'
+        headers = {
+            'accept': 'application/json',
+        }
+
+        # 表单数据
+        data = {
+            "book_id": str(book_id),
+            "question_ocr": question_ocr,
+            "question_embedding": json.dumps(question_embedding),
+            "top_k": 1
+        }
+        data = json.dumps(data, ensure_ascii=False)
+        response = requests.post(url, headers=headers, data=data)
+        # 输出响应结果
+        # print(f"状态码: {response.status_code}")
+        res = response.json()
+
+        bankId = res['es_search'][0]['_source']['bankId']
+        score = res['es_search'][0]['_score']
+
+        return bankId, score
+
+    def es_search_page_list(self, book_id, data_list, page_image_path):
+        # 输入手机拍摄的整图，es搜索库中的对应图片。手机拍摄的所有图片文件夹 page_image_path
+        save_data = []
+        page_ids = []
+        true_count = 0  # 搜整图正确结果统计
+        false_count = 0 # 搜整图错误结果统计
+        score_all = 0
+        page_id2item={}
+        for line in data_list:
+            page_id = line['电子页码']
+            if page_id in page_ids:
+                continue
+
+            line_temp = copy.deepcopy(line)
+            if page_id not in page_id2item:
+                image_file = os.path.join(page_image_path, str(page_id)+".jpg")
+                # paddle_ocr, search_page_ocr = self.paddle_ocr(image_file)  # paddleOCR
+                search_page_ocr = json.loads(recognize_pdf2md(image_file))['result']['markdown']  # 合合OCR
+
+                line_temp["search_page_ocr"] = search_page_ocr
+                if 'book_id' in line:
+                    book_id = line['book_id']
+                search_page_url, score = self.es_search_page( book_id, search_page_ocr)
+                score_all += score
+                line_temp["search_page_url"] = search_page_url
+                line_temp["search_page_score"] = score
+                page_id2item[page_id] = {"search_page_ocr":search_page_ocr, "search_page_url":search_page_url, "search_page_score":score}
+            else:
+                item = page_id2item[page_id]
+                search_page_url = item['search_page_url']
+                search_page_score = item['search_page_score']
+                search_page_ocr = item['search_page_ocr']
+
+                line_temp["search_page_ocr"] = search_page_ocr
+                line_temp["search_page_url"] = search_page_url
+                line_temp["search_page_score"] = search_page_score
+
+
+            if search_page_url == line_temp['source_image_url']:
+                flag = 1
+                true_count += 1
+            else:
+                flag = 0
+                false_count += 1
+            line_temp["flag"] = flag
+
+            save_data.append(line_temp)
+
+        mean_score = score_all/len(data_list)
+        print(f"图书 book_id：{book_id}，搜整图正确{true_count}张图；错误{false_count}张图。es平均得分{mean_score}")
+
+        return save_data
+
+    def es_search_page_question_list(self, book_id, data_list, question_image_path, image_path): # 丢弃
+        # 使用题目图片和整页图片 搜索es库中对应题目。拍摄的题目图片文件夹 question_image_path。 拍摄的整页图片文件夹 image_path
+        true_count = 0  # 搜题正确结果统计
+        false_count = 0 # 搜题错误结果统计
+        score_all = 0
+        page_id2ocr = {}
+        for line in data_list:
+            page_id = line['电子页码']
+            bank_id = line['题目id']
+            if page_id not in page_id2ocr.keys():
+                image_file = os.path.join(image_path, str(page_id) + ".jpg")
+                paddle_ocr, paddle_ocr_text = self.paddle_ocr(image_file)
+                page_id2ocr[page_id] = paddle_ocr_text
+
+            question_image_file = os.path.join(question_image_path, f"{page_id}-{bank_id}.jpg")
+            paddle_ocr, question_ocr = self.paddle_ocr(question_image_file)
+            line["search_question_ocr"] = question_ocr
+            line["search_page_ocr"] = page_id2ocr[page_id]
+            try:
+                if 'book_id' in line:
+                    book_id = line['book_id']
+                search_bankId, search_score = self.es_search_question( book_id, question_ocr, page_id2ocr[page_id])
+                score_all += search_score
+            except Exception as e:
+                print(f"es_search_page_question_list error {e}")
+                print(question_image_file)
+                search_bankId = "error"
+                search_score = "error"
+
+            line['question_page_search_bankId'] = search_bankId
+            line['question_page_search_score'] = search_score
+            if str(search_bankId) == str(bank_id):
+                flag = 1
+                true_count += 1
+            else:
+                flag = 0
+                false_count += 1
+
+            line['question_page_flag'] = flag
+
+            if (true_count+false_count) % 100 == 0 and (true_count+false_count) != 0:
+                print(f"输入整图和题目OCR，搜整题正确{true_count}张图；错误{false_count}张图。正确率：{true_count / (true_count + false_count)}")
+
+        mean_score = score_all/len(data_list)
+        print(f"图书 book_id：{book_id}，输入整图和题目OCR，搜整题正确{true_count}张图；错误{false_count}张图。es平均得分：{mean_score}")
+
+        return data_list
+
+    def es_search_question_list(self, book_id, data_list, question_image_path):
+        # 只使用题目图片ocr搜索es库中对应题目。拍摄的题目图片文件夹 question_image_path。
+        true_count = 0  # 搜题正确结果统计
+        false_count = 0 # 搜题错误结果统计
+        score_all = 0
+        for line in data_list:
+            page_id = line['电子页码']
+            bank_id = line['题目id']
+
+            question_image_file = os.path.join(question_image_path, f"{page_id}-{bank_id}.jpg")  # 用户拍摄的题目图片
+            # paddle_ocr, question_ocr = self.paddle_ocr(question_image_file)  # paddleOCR
+
+            question_ocr = json.loads(recognize_pdf2md(question_image_file))['result']['markdown']  # 合合OCR
+            try:
+                if 'book_id' in line:
+                    book_id = line['book_id']
+                search_bankId, score = self.es_search_question( book_id, question_ocr)
+            except Exception as e:
+                search_bankId, score = "error", -1
+                print(f"es_search_question_list error :{e}")
+                print(question_image_file)
+            score_all += score
+            line['question_search_bankId'] = search_bankId
+            line["search_question_ocr"] = question_ocr
+            line["search_question_score"] = score
+            if str(search_bankId) == str(bank_id):
+                flag = 1
+                true_count += 1
+            else:
+                flag = 0
+                false_count += 1
+
+            line['question_flag'] = flag
+
+            if (true_count+false_count)%100==0 and (true_count+false_count)!=0:
+                print(f"只输入题目OCR，搜整题正确{true_count}张图；错误{false_count}张图。正确率：{true_count / (true_count + false_count)}")
+
+
+        print(f"图书 book_id：{book_id}，只输入题目OCR，搜整题正确{true_count}张图；错误{false_count}张图。正确率：{true_count/(true_count+false_count)}")
+
+        return data_list
+
+    def es_search_question_embedding_list(self, book_id, data_list, question_image_path):
+        # 只使用向量搜题。拍摄的题目图片文件夹 question_image_path。
+        true_count = 0  # 搜题正确结果统计
+        false_count = 0 # 搜题错误结果统计
+        for line in data_list:
+            page_id = line['电子页码']
+            bank_id = line['题目id']
+            search_question_ocr = line["search_question_ocr"]
+            question_image_file = os.path.join(question_image_path, f"{page_id}-{bank_id}.jpg")  # 用户拍摄的题目图片
+            question_embedding = self.doubao_image_embedding( question_image_file, search_question_ocr)
+            try:
+                if 'book_id' in line:
+                    book_id = line['book_id']
+                search_bankId, score = self.es_search_question_embedding( book_id, question_embedding)  # 只使用 题目图片的embedding搜题
+            except Exception as e:
+                search_bankId = "error"
+                score = "error"
+                print(f"es_search_question_embedding_list error {e}")
+                print(question_image_file)
+
+            line['question_search_embedding_bankId'] = search_bankId
+            line["search_question_embedding_score"] = score
+            if str(search_bankId) == str(bank_id):
+                flag = 1
+                true_count += 1
+            else:
+                flag = 0
+                false_count += 1
+
+            line['question_embedding_flag'] = flag
+
+            if (true_count+false_count) % 100 == 0 and (true_count+false_count) != 0:
+                print(f"只输入题目embedding，搜整题正确{true_count}张图；错误{false_count}张图。正确率：{true_count / (true_count + false_count)}")
+
+        print(f"图书 book_id：{book_id}，只输入题目embedding，搜整题正确{true_count}张图；错误{false_count}张图。正确率：{true_count/(true_count+false_count)}")
+
+        return data_list
+
+
+    def es_search_question_text_and_embedding_list(self, book_id, data_list, question_image_path):
+        # 使用向量搜题,和es文本搜索，联合打分排序。拍摄的题目图片文件夹 question_image_path。
+        true_count = 0  # 搜题正确结果统计
+        false_count = 0 # 搜题错误结果统计
+        for line in data_list:
+            page_id = line['电子页码']
+            bank_id = line['题目id']
+            search_question_ocr = line["search_question_ocr"]
+            question_image_file = os.path.join(question_image_path, f"{page_id}-{bank_id}.jpg")  # 用户拍摄的题目图片
+            question_embedding = self.doubao_image_embedding( question_image_file, search_question_ocr)
+            try:
+                if 'book_id' in line:
+                    book_id = line['book_id']
+                search_bankId, score = self.search_question_text_and_embedding( book_id, search_question_ocr, question_embedding) # 使用题目图片embedding和 题目ocr文本联合搜索
+            except Exception as e:
+                search_bankId, score ='error' , 'error'
+                print(f"es_search_question_text_and_embedding_list error {e} ")
+                print(question_image_file)
+
+            line['question_search_embedding_and_text_bankId'] = search_bankId
+            line["search_question_embedding_and_text_score"] = score
+            if str(search_bankId) == str(bank_id):
+                flag = 1
+                true_count += 1
+            else:
+                flag = 0
+                false_count += 1
+
+            line['question_embedding_and_text_flag'] = flag
+
+        print(f"图书 book_id：{book_id}，题目ocr和embedding联合搜索，搜整题正确{true_count}张图；错误{false_count}张图。正确率：{true_count/(true_count+false_count)}")
+
+        return data_list
+
+
+    def result1(self):
+        book_id = 12667382
+        question_image_path = "/home/liuxin/work/search_question/data/12667382-25春北师一数暑假作业-题目"  # 用户拍摄的题目图片文件夹
+        page_image_path = "/home/liuxin/work/search_question/data/12667382-25春北师一数暑假作业"  # 用户拍摄的整图文件夹
+
+        source_image_path = "/home/liuxin/work/search_question/data/12667382-25春北师一数暑假作业-原图"  # 原图保存文件夹
+        excel_file = os.path.join(source_image_path, "12667382-25春北师一数暑假作业.xlsx")
+        data_list = self.read_excel(excel_file, sheet_name="题库数据")
+
+        # # page_data_list = self.es_search_page_list(book_id, data_list, page_image_path)  # 搜整页图片
+
+        question_data_list = self.es_search_question_list( book_id, data_list, question_image_path)  # es 文本直接搜题
+        # # # page_question_data_list = self.es_search_page_question_list(book_id, data_list, question_image_path,  page_image_path)  # 搜整页图片再搜题
+
+        question_data_list = self.es_search_question_embedding_list( book_id, question_data_list, question_image_path)  # es 向量直接搜题
+        question_data_list = self.es_search_question_text_and_embedding_list( book_id, question_data_list, question_image_path) # 联合向量搜索和文本搜索
+
+        data_list_list = [
+            # page_data_list,
+            question_data_list,
+        ]
+
+        timestamp_8 = int(datetime.now().strftime("%Y%m%d"))
+        save_file = os.path.join(source_image_path, f"{str(book_id)}-测试{str(timestamp_8)}.xlsx")
+        self.save_excel(data_list_list, save_file)
+
+    def result2(self):
+        # 只搜整页的图片
+        # book_id = 12664728 #
+        # page_image_path = "/home/liuxin/work/search_question/data/12664728-课计划·七年级英语·RJ·上册"  # 用户拍摄的整图文件夹
+        # source_image_path = "/home/liuxin/work/search_question/data/12664728-课计划·七年级英语·RJ·上册（出血文件）-原图"  # 原图保存文件夹
+        # excel_file = os.path.join(source_image_path, "12664728-课计划·七年级英语·RJ·上册（出血文件）.xlsx")
+
+        # book_id = 12670279 #
+        # page_image_path = "/home/liuxin/work/search_question/data/12670279-地理"  # 用户拍摄的整图文件夹
+        # source_image_path = "/home/liuxin/work/search_question/data/12670279-12670279-2025版ZT7地-下册横版《锦上添花（期末大赢家）》下册-新编文件5.8-原图"  # 原图保存文件夹
+        # excel_file = os.path.join(source_image_path, "12670279-12670279-2025版ZT7地-下册横版《锦上添花（期末大赢家）》下册-新编文件5.8.xlsx")
+
+        book_id = 12667382 #
+        page_image_path = "/home/liuxin/work/search_question/data/12667382-25春北师一数暑假作业"  # 用户拍摄的整图文件夹
+        source_image_path = "/home/liuxin/work/search_question/data/12667382-25春北师一数暑假作业-原图"  # 原图保存文件夹
+        excel_file = os.path.join(source_image_path, "12667382-25春北师一数暑假作业.xlsx")
+
+        data_list = self.read_excel(excel_file, sheet_name="题库数据")
+
+        page_data_list = self.es_search_page_list(book_id, data_list, page_image_path)  # 搜整页图片
+
+
+        data_list_list = [
+            page_data_list,
+            # question_data_list,
+        ]
+
+        timestamp_8 = int(datetime.now().strftime("%Y%m%d"))
+        save_file = os.path.join(source_image_path, f"{str(book_id)}-测试整页{str(timestamp_8)}.xlsx")
+        self.save_excel(data_list_list, save_file)
+
+    def result3(self):
+        # 只搜题。 测试整个文件夹的多个excel题目标注数据
+        es_data_path = "/home/liuxin/work/search_question/data/拆书平台下载excel文件_添加字段内容" # 入es库的所有数据文件夹
+        anno_data_path = "/home/liuxin/work/search_question/data/人工标注的手机拍题excel" # 人工标注的题目数据图片
+        save_phone_image_path = "/home/liuxin/work/search_question/data/人工标注的手机拍题图片" # 下载的手机拍题图片
+        data_list = self.read_excel_dir_anno_data( es_data_path, anno_data_path, save_phone_image_path)
+
+        question_image_path = save_phone_image_path  # 用户拍摄的题目图片文件夹
+
+        book_id = None
+        question_data_list = self.es_search_question_list( book_id, data_list, question_image_path)  # es 文本直接搜题
+
+        question_data_list = self.es_search_question_embedding_list( book_id, question_data_list, question_image_path)  # es 向量直接搜题
+        # question_data_list = self.es_search_question_text_and_embedding_list( book_id, question_data_list, question_image_path) # 联合向量搜索和文本搜索
+
+        data_list_list = [
+            # page_data_list,
+            question_data_list,
+
+        ]
+
+        timestamp_8 = int(datetime.now().strftime("%Y%m%d"))
+        save_file = os.path.join(save_phone_image_path, f"搜题-测试{str(timestamp_8)}.xlsx")
+        self.save_excel(data_list_list, save_file)
+
+
+if __name__ == "__main__":
+    test = Test()
+    # test.result2()   # 测试搜整页图片的效果
+    test.result3()   # 测试搜题的效果
+
+    # # 测试paddleOCR的效果
+    # image_file_list =[
+    #     "/home/liuxin/work/search_question/data/12667382一年级数学-题目/19-764148.jpg",
+    #     "/home/liuxin/work/search_question/data/12667382一年级数学-题目/19-764148.jpg.jpg",
+    #     # "",
+    #     # ""
+    # ]
+    # for image_file in image_file_list:
+    #     paddle_ocr, paddle_ocr_text = test.paddle_ocr( image_file)
+    #     print(image_file)
+    #     print(paddle_ocr_text)
+
+    print("\nfinished.")
+
+
+
+"""  es 计算的分数利用词频信息，库里的数据不同 得分不同 
+
+图书 book_id：12664728，搜整图正确301张图；错误0张图。 合合ocr
+图书 book_id：12670279，搜整图正确159张图；错误0张图。 合合ocr
+
+
+搜题 es库里的数据和用户手机拍摄的数据都用paddleOCR
+图书 book_id：12667382，只输入题目OCR，搜整题正确138张图；错误3张图。正确率：0.9787234042553191 
+图书 book_id：12667382，只输入题目embedding，搜整题正确141张图；错误0张图。正确率：1.0
+图书 book_id：12667382，题目ocr和embedding联合搜索，搜整题正确140张图；错误1张图。正确率：0.9929078014184397
+
+搜题 es库里的数据和用户手机拍摄的题目图片都用paddleOCR
+只输入题目OCR，搜整题正确465张图；错误11张图。正确率：0.976890756302521
+只输入题目embedding，搜整题正确476张图；错误0张图。正确率：1.0    （题目embedding：将题目ocr和图片作为一个整体输入embedding模型获取向量）
+
+
+搜题 es库里的题目图片和用户手机拍摄的题目图片都用合合ocr
+1、只输入题目OCR，搜整题正确649张图；错误3张图。正确率：0.995。
+2、只输入题目embedding，搜整题正确651张图；错误1张图。正确率：0.998。（有一条数据标错了）
+
+"""
+
+
+
+# nohup python -u tst_search_result.py > tst_search_result.log 2>&1 &
+# tail -f tst_search_result.log
+
+
+