Byted Bytehouse Hybrid Search

                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from embedding import MultimodalEmbedding
from hybrid_search_client import ByteHouseHybridSearch

__all__ = ["MultimodalEmbedding", "ByteHouseHybridSearch"]

# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
多模态向量化模块
基于豆包多模态向量化模型实现文本、图片、视频的向量化
"""

import os
import json
import numpy as np
from volcenginesdkarkruntime import Ark
from typing import List, Union, Dict


class MultimodalEmbedding:
    """多模态向量化客户端"""
    
    def __init__(self):
        # 先尝试从环境变量读取配置
        api_key = os.environ.get("BH_ARK_API_KEY")
        base_url = os.environ.get("BH_ARK_BASE_URL")
        
        # 如果环境变量没有配置，尝试从OpenClaw配置文件读取
        if not api_key or not base_url:
            config_path = os.path.expanduser("~/.openclaw/openclaw.json")
            if os.path.exists(config_path):
                try:
                    with open(config_path, "r", encoding="utf-8") as f:
                        config = json.load(f)
                    ark_config = config.get("models", {}).get("providers", {}).get("ark", {})
                    if not api_key:
                        api_key = ark_config.get("apiKey")
                    if not base_url:
                        base_url = ark_config.get("baseUrl")
                except Exception as e:
                    print(f"读取OpenClaw配置文件失败: {str(e)}")
        
        # 检查必要配置是否存在
        if not api_key:
            raise ValueError("未找到ARK API Key，请配置BH_ARK_API_KEY环境变量或在openclaw.json中配置models.providers.ark.apiKey")
        if not base_url:
            raise ValueError("未找到ARK Base URL，请配置BH_ARK_BASE_URL环境变量或在openclaw.json中配置models.providers.ark.baseUrl")
        
        self.client = Ark(
            api_key=api_key,
            base_url=base_url
        )
        self.model = os.environ.get("BH_EMBEDDING_MODEL", "doubao-embedding-vision-251215")
        self.dimensions = int(os.environ.get("EMBEDDING_DIMENSIONS", 2048))
    
    def encode(self, 
               input_data: Union[str, List[Dict]], 
               modality: str = "text",
               instruction: str = None) -> List[float]:
        """
        多模态向量化接口
        
        Args:
            input_data: 输入数据
                - 文本：直接传入字符串
                - 图片/视频：传入 {"type": "image_url"/"video_url", "url": "xxx"} 格式
            modality: 数据类型，可选 text/image/video
            instruction: 自定义指令，用于提升特定场景检索精度
        
        Returns:
            向量列表
        """
        try:
            if isinstance(input_data, str):
                input_item = {"type": "text", "text": input_data}
            else:
                input_item = input_data
            
            # 输入格式校验
            if modality in ["image", "video"] and not isinstance(input_item, dict):
                raise ValueError(f"{modality}类型输入必须为包含url的字典格式")
            
            # 构造请求参数
            request_params = {
                "model": self.model,
                "encoding_format": "float",
                "input": [input_item],
                "dimensions": self.dimensions
            }
            
            # 添加自定义指令（251215及以上版本支持）
            if instruction and "251215" in self.model:
                request_params["instructions"] = instruction
            
            # 调用 API
            resp = self.client.multimodal_embeddings.create(**request_params)
            
            if hasattr(resp, 'data'):
                embedding = resp.data.embedding
                vec = np.array(embedding).flatten().tolist()
                
                
                return vec
            else:
                raise ValueError("API响应格式错误，未找到embedding字段")

        except Exception as e:
            error_msg = str(e).lower()
            if "api key" in error_msg or "unauthorized" in error_msg or "permission" in error_msg:
                raise PermissionError(f"向量化失败：API密钥无效或权限不足。错误详情：{e}")
            elif "connection" in error_msg or "timeout" in error_msg or "network" in error_msg:
                raise ConnectionError(f"向量化失败：网络连接异常。错误详情：{e}")
            elif "invalid" in error_msg or "parameter" in error_msg or "format" in error_msg:
                raise ValueError(f"向量化失败：输入参数或格式错误。错误详情：{e}")
            else:
                raise Exception(f"向量化失败：{e}")
    
    def encode_text(self, text: str, instruction: str = None) -> List[float]:
        """文本向量化"""
        return self.encode(text, "text", instruction)
    
    def encode_image(self, image_url: str, instruction: str = None) -> List[float]:
        """图片URL向量化"""
        input_item = {"type": "image_url", "image_url": {"url": image_url}}
        return self.encode(input_item, "image", instruction)
    
    def encode_video(self, video_url: str, instruction: str = None) -> List[float]:
        """视频URL向量化"""
        input_item = {"type": "video_url", "video_url": {"url": video_url}}
        return self.encode(input_item, "video", instruction)

def main():
    """命令行入口"""
    print("Hello, World!")
    multimodal_embedding = MultimodalEmbedding()
    print(multimodal_embedding.encode_text("你好"))

if __name__ == "__main__":
    main()

# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
ByteHouse 混合检索使用示例
"""
from hybrid_search_client import ByteHouseHybridSearch

def main():
    # 初始化客户端
    search = ByteHouseHybridSearch(host="",
                                   user="",
                                   password="",
                                   database="",
                                   connection_type="")
    
    table_name = "demo_hybrid_index"
    
    print("=== 清理旧表 ===")
    search.client.command(f"DROP TABLE IF EXISTS {table_name}")
    
    # 1. 创建混合检索表
    print("=== 创建混合检索表 ===")
    search.create_hybrid_table(table_name, if_not_exists=True)
    
    # 2. 插入测试数据
    print("\n=== 插入测试数据 ===")
    documents = [
        {
            "doc_id": 1,
            "title": "ByteHouse 全文检索",
            "content": "ByteHouse 企业版支持全文检索能力，基于倒排索引实现，支持BM25相似度计算，可快速检索文本内容。"
        },
        {
            "doc_id": 2,
            "title": "ByteHouse 向量检索",
            "content": "ByteHouse 支持向量检索功能，基于HNSW索引实现，支持余弦相似度、L2距离等多种相似度计算方式。"
        },
        {
            "doc_id": 3,
            "title": "混合检索最佳实践",
            "content": "结合全文检索和向量检索的优势，使用RRF重排算法可以实现更精准的检索效果，兼顾关键词匹配和语义匹配。"
        },
        {
            "doc_id": 4,
            "title": "RRF重排算法",
            "content": "RRF（Reciprocal Rank Fusion）是一种常用的多路召回融合算法，通过对不同召回源的排名进行加权融合，得到最终的排序结果。"
        },
        {
            "doc_id": 5,
            "title": "ClickHouse 二级索引",
            "content": "ClickHouse 支持二级索引功能，包括跳数索引、全文倒排索引、向量索引等，可大幅提升查询性能。"
        }
    ]
    search.batch_insert_documents(table_name, documents)
    print("测试数据插入完成")
    
    # 3. 全文检索示例
    print("\n=== 全文检索示例，查询：'ByteHouse 检索' ===")
    fulltext_results = search.fulltext_search(table_name, query="ByteHouse 检索", top_k=3)
    for i, res in enumerate(fulltext_results):
        print(f"排名 {i+1}: [doc_id={res['doc_id']}] {res['title']}，BM25分数：{res['bm25_score']:.4f}")
        print(f"内容摘要：{res['content'][:50]}...\n")
    
    # 4. 向量检索示例
    print("\n=== 向量检索示例，查询：'怎么实现更好的检索效果' ===")
    vector_results = search.vector_search(table_name, query="怎么实现更好的检索效果", top_k=3)
    for i, res in enumerate(vector_results):
        print(f"排名 {i+1}: [doc_id={res['doc_id']}] {res['title']}，向量相似度：{res['vector_score']:.4f}")
        print(f"内容摘要：{res['content'][:50]}...\n")
    
    # 5. 混合检索+RRF重排示例
    print("\n=== 混合检索+RRF重排示例，查询：'ByteHouse 检索效果优化' ===")
    hybrid_results = search.hybrid_search(table_name, query="ByteHouse 检索效果优化", top_k=3)
    for i, res in enumerate(hybrid_results):
        print(f"排名 {i+1}: [doc_id={res['doc_id']}] {res['title']}，RRF分数：{res['rrf_score']:.4f}")
        if 'bm25_score' in res:
            print(f"BM25分数：{res['bm25_score']:.4f}")
        if 'vector_score' in res:
            print(f"向量相似度：{res['vector_score']:.4f}")
        print(f"内容摘要：{res['content'][:80]}...\n")
    
    # 关闭连接
    search.close()

if __name__ == "__main__":
    main()

#!/bin/bash

load_config() {
  # 检查 jq 是否安装
  if ! command -v jq &> /dev/null; then
    echo "Error: jq is not installed. Please install jq first (e.g. brew install jq or sudo apt install jq)."
    return 1
  fi

  # 解析 json，将每个 key-value 转成 export KEY="VALUE" 的格式
  local exports
  exports=$(jq -r 'to_entries | .[] | "export \(.key)=\(.value | @sh)"' ~/.bytehouse_config.json)

  # 执行生成的 export 命令
  eval "$exports"
  echo "Configuration loaded from ~/.bytehouse_config.json"
}

load_config

# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
ByteHouse 混合检索客户端
支持全文检索、向量检索、RRF重排
"""
import os
import clickhouse_connect
from typing import List, Dict, Optional, Any
from embedding import MultimodalEmbedding

class ByteHouseHybridSearch:
    def __init__(self,
                 host: Optional[str] = None,
                 port: Optional[int] = None,
                 user: Optional[str] = None,
                 password: Optional[str] = None,
                 database: Optional[str] = None,
                 secure: Optional[bool] = None,
                 connection_type: str = "http"):
        """
        初始化ByteHouse客户端
        :param host: ByteHouse地址，默认从环境变量BYTEHOUSE_HOST读取
        :param port: ByteHouse端口，默认从环境变量BYTEHOUSE_PORT读取
        :param user: 用户名，默认从环境变量BYTEHOUSE_USER读取
        :param password: 密码，默认从环境变量BYTEHOUSE_PASSWORD读取
        :param database: 默认数据库，默认从环境变量BYTEHOUSE_DATABASE读取，默认default
        :param secure: 是否启用加密，默认从环境变量BYTEHOUSE_SECURE读取，默认True
        :param connection_type: 连接类型，http或native，默认http
        """
        self.host = host or os.getenv("BYTEHOUSE_HOST")
        self.port = port or int(os.getenv("BYTEHOUSE_PORT", "8123"))
        self.user = user or os.getenv("BYTEHOUSE_USER", "bytehouse")
        self.password = password or os.getenv("BYTEHOUSE_PASSWORD")
        self.database = database or os.getenv("BYTEHOUSE_DATABASE", "default")
        self.secure = secure if secure is not None else (os.getenv("BYTEHOUSE_SECURE", "true").lower() == "true")
        
        if not self.host or not self.password:
            raise ValueError("请配置BYTEHOUSE_HOST和BYTEHOUSE_PASSWORD环境变量")
        
        # 初始化ByteHouse连接
        self.client = clickhouse_connect.get_client(
            host=self.host,
            port=self.port,
            username=self.user,
            password=self.password,
            database=self.database,
            secure=self.secure,
            verify=False,
            connect_timeout=30,
            send_receive_timeout=60
        )
        
        # 初始化向量化客户端
        self.dimensions = int(os.environ.get("EMBEDDING_DIMENSIONS", 2048))
        self.embedding_client = MultimodalEmbedding()
    
    def create_hybrid_table(self, table_name: str, if_not_exists: bool = True) -> None:
        """
        创建混合检索表，自动构建全文倒排索引和向量索引
        :param table_name: 表名
        :param if_not_exists: 是否存在就跳过，默认True
        """
        exists_clause = "IF NOT EXISTS" if if_not_exists else ""
        vec_dimensions = self.dimensions
        # 兼容旧版本ByteHouse，先创建基础表，索引可后续手动添加
        create_sql = f"""
        CREATE TABLE {exists_clause} {table_name} (
            `doc_id` UInt64,
            `title` String,
            `content` String,
            `embedding` Array(Float32),
            `create_time` DateTime DEFAULT now(),
            INDEX content_idx content TYPE inverted('standard', '{{\"version\":\"v4\"}}') GRANULARITY 1,
            INDEX embedding_idx embedding TYPE HNSW_SQ('DIM={vec_dimensions}', 'metric=COSINE', 'M=32', 'EF_CONSTRUCTION=256') GRANULARITY 1
        )
        ENGINE = CnchMergeTree()
        ORDER BY doc_id
        SETTINGS
            index_granularity = 1024,
            enable_vector_index_preload = 1
        """
        self.client.command(create_sql)
        print(f"混合检索表 {table_name} 创建成功，向量维度：{vec_dimensions}")
    
    def insert_document(self, table_name: str, doc_id: int, title: str, content: str) -> None:
        """
        插入单个文档
        :param table_name: 表名
        :param doc_id: 文档ID
        :param title: 文档标题
        :param content: 文档内容
        """
        # 拼接标题和内容生成向量
        full_text = f"标题：{title} 内容：{content}"
        embedding = self.embedding_client.encode_text(full_text)
        
        insert_sql = f"""
        INSERT INTO {table_name} (doc_id, title, content, embedding)
        VALUES (%s, %s, %s, %s)
        """
        self.client.command(insert_sql, parameters=[doc_id, title, content, embedding])
    
    def batch_insert_documents(self, table_name: str, documents: List[Dict[str, Any]]) -> None:
        """
        批量插入文档
        :param table_name: 表名
        :param documents: 文档列表，每个元素包含doc_id, title, content字段
        """
        # 构建插入数据
        data = []
        for doc in documents:
            # 逐个生成向量
            full_text = f"标题：{doc['title']} 内容：{doc['content']}"
            emb = self.embedding_client.encode_text(full_text)
            
            # 验证向量维度正确性
            if len(emb) != self.dimensions:
                raise ValueError(f"向量维度错误：期望{self.dimensions}维，实际{len(emb)}维")
            
            data.append([
                doc['doc_id'],
                doc['title'],
                doc['content'],
                emb
            ])
        
        for row in data:
            self.client.command(f"INSERT INTO {table_name} (doc_id, title, content, embedding) VALUES (%s, %s, %s, %s)", parameters=row)
        print(f"成功插入 {len(documents)} 条文档，向量已自动生成并写入")
    
    def fulltext_search(self, table_name: str, query: str, top_k: int = 20) -> List[Dict[str, Any]]:
        """
        全文检索，基于BM25算法
        :param table_name: 表名
        :param query: 查询关键词
        :param top_k: 返回结果数量，默认20
        :return: 检索结果，包含doc_id, title, content, bm25_score字段
        """
        query_escaped = self.transform_string(query)
        search_sql = f"""
        SELECT 
            doc_id, 
            title, 
            content,
            _text_search_score as bm25_score
        FROM {table_name}
        WHERE textSearch(content, '{query_escaped}')
        ORDER BY bm25_score DESC
        LIMIT {top_k}
        """
        print(f"执行全文检索查询：{search_sql}")
        results = self.client.query(search_sql).result_rows
        return [
            {
                "doc_id": row[0],
                "title": row[1],
                "content": row[2],
                "bm25_score": float(row[3])
            }
            for row in results
        ]
    
    def vector_search(self, table_name: str, query: str, top_k: int = 20) -> List[Dict[str, Any]]:
        """
        向量检索，基于余弦相似度
        :param table_name: 表名
        :param query: 查询文本
        :param top_k: 返回结果数量，默认20
        :return: 检索结果，包含doc_id, title, content, vector_score字段
        """
        # 生成查询向量
        query_embedding = self.embedding_client.encode_text(query)
        
        search_sql = f"""
        SELECT 
            doc_id, 
            title, 
            content,
            cosineDistance(embedding, %s) as vector_score
        FROM {table_name}
        ORDER BY vector_score ASC
        LIMIT {top_k}
        """
        print(f"执行向量检索查询：{search_sql}")
        results = self.client.query(search_sql, parameters=[query_embedding]).result_rows
        return [
            {
                "doc_id": row[0],
                "title": row[1],
                "content": row[2],
                "vector_score": float(row[3])
            }
            for row in results
        ]
    
    def rrf_rerank(self, 
                   fulltext_results: List[Dict[str, Any]], 
                   vector_results: List[Dict[str, Any]], 
                   top_k: int = 10,
                   rrf_k: int = 60) -> List[Dict[str, Any]]:
        """
        RRF重排算法，融合全文检索和向量检索结果
        :param fulltext_results: 全文检索结果
        :param vector_results: 向量检索结果
        :param top_k: 返回重排后的结果数量，默认10
        :param rrf_k: RRF算法k参数，默认60
        :return: 重排后的结果，包含rrf_score字段
        """
        # 构建文档分数字典
        doc_scores: Dict[int, Dict[str, Any]] = {}
        
        # 处理全文检索结果
        for rank, result in enumerate(fulltext_results):
            doc_id = result["doc_id"]
            if doc_id not in doc_scores:
                doc_scores[doc_id] = result.copy()
                doc_scores[doc_id]["rrf_score"] = 0.0
            # 累加RRF分数
            doc_scores[doc_id]["rrf_score"] += 1.0 / (rrf_k + rank + 1)
        
        # 处理向量检索结果
        for rank, result in enumerate(vector_results):
            doc_id = result["doc_id"]
            if doc_id not in doc_scores:
                doc_scores[doc_id] = result.copy()
                doc_scores[doc_id]["rrf_score"] = 0.0
            # 累加RRF分数
            doc_scores[doc_id]["rrf_score"] += 1.0 / (rrf_k + rank + 1)
        
        # 按RRF分数排序
        sorted_docs = sorted(doc_scores.values(), key=lambda x: x["rrf_score"], reverse=True)
        
        # 返回top_k结果
        return sorted_docs[:top_k]
    
    def hybrid_search(self, 
                      table_name: str, 
                      query: str, 
                      top_k: int = 10,
                      recall_k: int = 20,
                      rrf_k: int = 60) -> List[Dict[str, Any]]:
        """
        混合检索：全文+向量双路召回 + RRF重排
        :param table_name: 表名
        :param query: 查询文本
        :param top_k: 返回最终结果数量，默认10
        :param recall_k: 每路召回数量，默认20
        :param rrf_k: RRF算法k参数，默认60
        :return: 最终检索结果
        """
        # 两路召回
        fulltext_results = self.fulltext_search(table_name, query, top_k=recall_k)
        vector_results = self.vector_search(table_name, query, top_k=recall_k)
        
        # RRF重排
        reranked_results = self.rrf_rerank(fulltext_results, vector_results, top_k=top_k, rrf_k=rrf_k)
        
        return reranked_results
    
    def close(self) -> None:
        """关闭连接"""
        self.client.close()

    def transform_string(self, s: str) -> str:
        # Remove all single quotes
        s = s.replace("'", "")
        s = s.replace(" ", "")
        
        # Split each character with |
        return "|".join(s)