Merge branch 'main' of https://github.com/xerrors/Yuxi-Know

.gitignore

@@ -33,6 +33,8 @@ src/data
 */package-lock.json
 web/package-lock.json
 saves
+saves_dev
 notebooks
 graphrag
-docker/volumes
+docker/volumes
+.cursorrules

README.md

@@ -12,9 +12,8 @@
 > [!NOTE]
 > 当前项目还处于开发的早期，还存在一些 BUG，有问题随时提 issue。
 
-已知问题：
+- [ ] Ollma Embedding 支持（Open-like Embedding 支持）
-
+- [x] DeepSeek-R1 支持，需配置 `DEEPSEEK_API_KEY` 或者 `SILICONFLOW_API_KEY` 使用
-- [ ] 从 Flask 更换到 Fast API 之后，并行命令还存在问题。
 
 ## 概述
 
@@ -31,12 +30,12 @@ ZHIPUAI_API_KEY=270ea********8bfa97.e3XOMd****Q1Sk
 OPENAI_API_KEY=sk-*********[可选]
 ```
 
-本项目的基础对话服务可以在不含显卡的设备上运行，大模型使用在线服务商的接口。但是如果想要完整的知识库对话体验，则需要 8G 以上的显存。因为需要本地运行 embedding 模型和 rerank 模型。
+本项目的基础对话服务可以在不含显卡的设备上运行，大模型使用在线服务商的接口。但是如果想要完整的知识库对话体验，则需要 8G 以上的显存。因为需要本地运行 embedding 模型和 rerank 模型。如果需要指定本地模型所在路径，需要配置 `MODEL_DIR` 参数。
 
 **提醒**：下面的脚本会启动开发版本，源代码的修改会自动更新（含前端和后端）。如果生产环境部署，请使用 `docker/docker-compose.yml` 启动。
 
 ```bash
-docker-compose -f docker/docker-compose.dev.yml up --build
+docker compose -f docker/docker-compose.dev.yml --env-file src/.env up --build
 ```
 
 **也可以加上 `-d` 参数，后台运行。*
@@ -63,7 +62,7 @@ docker-compose -f docker/docker-compose.dev.yml up --build
 关闭 docker 服务：
 
 ```bash
-docker-compose -f docker/docker-compose.dev.yml down
+docker compose -f docker/docker-compose.dev.yml --env-file src/.env down
 ```
 
 查看日志：
@@ -72,26 +71,10 @@ docker-compose -f docker/docker-compose.dev.yml down
 docker logs <CONTAINER_NAME>  # 例如：docker logs api-dev
 ```
 
-如果需要使用到本地模型（不推荐手动指定），比如向量模型或者重排序模型，则需要将环境变量中设置的 `MODEL_ROOT_DIR` 做映射，比如本地模型都是存放在 `/hdd/models` 里面，则需要在 `docker-compose.yml` 和 `docker-compose.dev.yml`  中添加：
-
-```yml
-services:
-  api:
-    build:
-      context: ..
-      dockerfile: docker/api.Dockerfile
-    container_name: api-dev
-    working_dir: /app
-    volumes:
-      - ../src:/app/src
-      - ../saves:/app/saves
-      - /hdd/zwj/models:/hdd/zwj/models  # <== 修改这一行
-```
-
 **生产环境部署**：本项目同时支持使用 Docker 部署生产环境，只需要更换 `docker-compose` 文件就可以了。
 
 ```bash
-docker-compose -f docker/docker-compose.yml up --build
+docker compose -f docker/docker-compose.yml --env-file src/.env up --build
 ```
 
 ## 模型支持
@@ -131,7 +114,7 @@ docker-compose -f docker/docker-compose.yml up --build
 
 对于**语言模型**，并不支持直接运行本地语言模型，请使用 vllm 或者 ollama 转成 API 服务之后使用。
 
-对于**向量模型**和**重排序模型**，可以不做修改会自动下载模型，如果下载过程中出现问题，请参考 [HF-Mirror](https://hf-mirror.com/) 配置相关内容。如果想要使用本地已经下载好的模型（不建议），可以在 `saves/config/config.yaml` 配置相关内容。同时注意要在 docker 中做映射，参考 README 中的 `docker/docker-compose.yml`。
+对于**向量模型**和**重排序模型**，可以不做修改会自动下载模型，如果下载过程中出现问题，请参考 [HF-Mirror](https://hf-mirror.com/) 配置相关内容。如果想要使用本地已经下载好的模型（不建议），可以在网页的 settings 里面做映射。
 
 例如：
 

docker/api.Dockerfile

@@ -10,7 +10,12 @@ COPY ../requirements.txt /app/requirements.txt
 # 安装依赖（Docker 会缓存这一步，除非 requirements.txt 发生变化）
 RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
 
-RUN pip install gunicorn
+RUN pip install -U gunicorn -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+RUN sed -i s@/archive.ubuntu.com/@/mirrors.aliyun.com/@g /etc/apt/sources.list
+RUN sed -i s@/security.ubuntu.com/@/mirrors.aliyun.com/@g /etc/apt/sources.list
+RUN apt-get clean
+RUN apt-get update && apt-get install ffmpeg libsm6 libxext6  -y
 
 # 复制代码到容器中
 COPY ../src /app/src

docker/docker-compose.dev.yml

@@ -7,8 +7,9 @@ services:
     working_dir: /app
     volumes:
       - ../src:/app/src
-      - ../saves:/app/saves
+      - ../saves_dev:/app/saves
-      - /hdd/zwj/models:/hdd/zwj/models
+      - ../src/static/config.dev.yaml:/app/src/static/config.yaml
+      - ${MODEL_DIR}:${MODEL_DIR}
     ports:
       - "5000:5000"
     depends_on:
@@ -21,6 +22,7 @@ services:
       - NEO4J_USERNAME=neo4j
       - NEO4J_PASSWORD=0123456789
       - MILVUS_URI=http://milvus:19530
+      - MODEL_DIR=${MODEL_DIR}  # 优先级高于 .env 中的 MODEL_DIR
     command: uvicorn src.main:app --host 0.0.0.0 --port 5000 --reload
 
   web:

requirements.txt

@@ -1,7 +1,7 @@
 dashscope>=1.20.3
 PyMuPDF==1.23.26
 peft>=0.11.1
-FlagEmbedding>=1.2.11
+FlagEmbedding>=1.3.2
 Flask>=3.0.3
 Flask_Cors>=4.0.1
 llama_index>=0.11.8
@@ -24,4 +24,5 @@ opencv-python-headless
 docx2txt
 uvicorn[standard]
 fastapi
-python-multipart
+python-multipart
+tavily-python

scripts/init.sh

@@ -1,25 +0,0 @@
-#!/bin/bash
-
-# 检查是否提供了 API_KEY 参数
-if [ -z "$1" ]; then
-    echo "请提供 API_KEY。"
-    exit 1
-fi
-
-# 获取当前目录路径
-CURRENT_DIR=$(pwd)
-
-# 如果 src 目录不存在则创建
-if [! -d "${CURRENT_DIR}/src" ]; then
-    mkdir -p "${CURRENT_DIR}/src"
-fi
-
-# 如果.env 文件不存在，则从.env.template 复制一份创建
-if [! -f "${CURRENT_DIR}/src/.env" ]; then
-    cp "${CURRENT_DIR}/src/.env.template" "${CURRENT_DIR}/src/.env"
-fi
-
-# 将 API_KEY 写入.env 文件
-echo "ZHIPUAI_API_KEY=$1" > "${CURRENT_DIR}/src/.env"
-
-echo "API_KEY 已成功写入 src/.env 文件。"

src/config/__init__.py

@@ -6,7 +6,7 @@ from src.utils.logging_config import setup_logger
 
 logger = setup_logger("Config")
 
-with open(Path("src/config/models.yaml"), "r") as f:
+with open(Path("src/static/models.yaml"), "r") as f:
     _models = yaml.safe_load(f)
 
 MODEL_NAMES = _models["MODEL_NAMES"]
@@ -17,7 +17,7 @@ RERANKER_LIST = _models["RERANKER_LIST"]
 class SimpleConfig(dict):
 
     def __key(self, key):
-        return "" if key is None else key.lower()
+        return "" if key is None else key.lower()  # 目前忘记了这里为什么要 lower 了，只能说配置项最好不要有大写的
 
     def __str__(self):
         return json.dumps(self)
@@ -40,32 +40,33 @@ class SimpleConfig(dict):
 
 class Config(SimpleConfig):
 
-    def __init__(self, filename=None):
+    def __init__(self):
         super().__init__()
         self._config_items = {}
+        self.save_dir = "saves"
+        self.filename = str(Path("src/static/config.yaml"))
+        os.makedirs(os.path.dirname(self.filename), exist_ok=True)
 
         ### >>> 默认配置
         # 可以在 config/base.yaml 中覆盖
         self.add_item("stream", default=True, des="是否开启流式输出")
-        self.add_item("save_dir", default="saves", des="保存目录")
         # 功能选项
         self.add_item("enable_reranker", default=False, des="是否开启重排序")
         self.add_item("enable_knowledge_base", default=False, des="是否开启知识库")
         self.add_item("enable_knowledge_graph", default=False, des="是否开启知识图谱")
         self.add_item("enable_search_engine", default=False, des="是否开启搜索引擎")
-
+        self.add_item("enable_web_search", default=False, des="是否开启网页搜索")
         # 模型配置
         ## 注意这里是模型名，而不是具体的模型路径，默认使用 HuggingFace 的路径
-        ## 如果需要自定义路径，则在 config/base.yaml 中配置 model_local_paths
+        ## 如果需要自定义本地模型路径，则在 src/.env 中配置 MODEL_DIR
         self.add_item("model_provider", default="zhipu", des="模型提供商", choices=list(MODEL_NAMES.keys()))
         self.add_item("model_name", default=None, des="模型名称")
         self.add_item("embed_model", default="zhipu-embedding-3", des="Embedding 模型", choices=list(EMBED_MODEL_INFO.keys()))
         self.add_item("reranker", default="bge-reranker-v2-m3", des="Re-Ranker 模型", choices=list(RERANKER_LIST.keys()))
         self.add_item("model_local_paths", default={}, des="本地模型路径")
+        self.add_item("use_rewrite_query", default="off", des="重写查询", choices=["off", "on", "hyde"])
         ### <<< 默认配置结束
 
-        self.filename = filename or os.path.join(self.save_dir, "config", "config.yaml")
-        os.makedirs(os.path.dirname(self.filename), exist_ok=True)
 
         self.load()
         self.handle_self()
@@ -89,7 +90,9 @@ class Config(SimpleConfig):
     def handle_self(self):
         self.model_names = MODEL_NAMES
         model_provider_info = self.model_names.get(self.model_provider, {})
+        self.model_dir = os.environ.get("MODEL_DIR", "")
 
+        # 检查模型提供商是否存在
         if self.model_provider != "custom":
             if self.model_name not in model_provider_info["models"]:
                 logger.warning(f"Model name {self.model_name} not in {self.model_provider}, using default model name")
@@ -103,6 +106,7 @@ class Config(SimpleConfig):
                 logger.warning(f"Model name {self.model_name} not in custom models, using default model name")
                 self.model_name = self.custom_models[0]["custom_id"]
 
+        # 检查模型提供商的环境变量
         conds = {}
         self.model_provider_status = {}
         for provider in self.model_names:
@@ -110,10 +114,14 @@ class Config(SimpleConfig):
             conds_bool = [bool(os.getenv(_k)) for _k in conds[provider]]
             self.model_provider_status[provider] = all(conds_bool)
 
+        # 检查web_search的环境变量
+        if self.enable_web_search and not os.getenv("TAVILY_API_KEY"):
+            logger.warning("TAVILY_API_KEY not set, web search will be disabled")
+            self.enable_web_search = False
+
         self.valuable_model_provider = [k for k, v in self.model_provider_status.items() if v]
         assert len(self.valuable_model_provider) > 0, f"No model provider available, please check your `.env` file. API_KEY_LIST: {conds}"
 
-        
 
     def load(self):
         """根据传入的文件覆盖掉默认配置"""

src/core/retriever.py

@@ -14,6 +14,10 @@ class Retriever:
         if self.config.enable_reranker:
             self.reranker = Reranker(config)
 
+        if self.config.enable_web_search:
+            from src.utils.web_search import WebSearcher
+            self.web_searcher = WebSearcher()
+
     def retrieval(self, query, history, meta):
 
         refs = {"query": query, "history": history, "meta": meta}
@@ -21,6 +25,7 @@ class Retriever:
         refs["entities"] = self.reco_entities(query, history, refs)
         refs["knowledge_base"] = self.query_knowledgebase(query, history, refs)
         refs["graph_base"] = self.query_graph(query, history, refs)
+        refs["web_search"] = self.query_web(query, history, refs)
 
         return refs
 
@@ -44,6 +49,12 @@ class Retriever:
             )
             external_parts.extend(["图数据库信息:", db_text])
 
+        # 解析网络搜索的结果
+        web_res = refs.get("web_search", {}).get("results", [])
+        if web_res:
+            web_text = "\n".join(f"{r['title']}: {r['snippet']}" for r in web_res)
+            external_parts.extend(["网络搜索信息:", web_text])
+
         # 构造查询
         from src.utils.prompts import knowbase_qa_template
         if external_parts and len(external_parts) > 0:
@@ -60,8 +71,6 @@ class Retriever:
         raise NotImplementedError
 
     def query_graph(self, query, history, refs):
-        # res = model.predict("qiansdgsa, dasdh ashdsakjdk ak ").content
-
         results = []
         if refs["meta"].get("use_graph") and self.config.enable_knowledge_base:
             for entity in refs["entities"]:
@@ -70,6 +79,7 @@ class Retriever:
                     results.extend(result)
         return {"results": self.format_query_results(results)}
 
+
     def query_knowledgebase(self, query, history, refs):
         """查询知识库"""
 
@@ -116,9 +126,27 @@ class Retriever:
 
         return {"results": kb_res, "all_results": all_kb_res, "rw_query": rw_query}
 
+    def query_web(self, query, history, refs):
+        """查询网络"""
+
+        if not (refs["meta"].get("enable_web_search") and self.config.enable_web_search):
+            return {"results": [], "message": "Web search is disabled"}
+
+        try:
+            search_results = self.web_searcher.search(query)
+        except Exception as e:
+            logger.error(f"Web search error: {str(e)}")
+            return {"results": [], "message": "Web search error"}
+
+        return {"results": search_results}
+
     def rewrite_query(self, query, history, refs):
         """重写查询"""
-        rewrite_query_span = refs["meta"].get("rewriteQuery", "off")
+        if refs["meta"].get("mode") == "search":  # 如果是搜索模式，就使用 meta 的配置，否则就使用全局的配置
+            rewrite_query_span = refs["meta"].get("use_rewrite_query", "off")
+        else:
+            rewrite_query_span = self.config.use_rewrite_query
+
         if rewrite_query_span == "off":
             rewritten_query = query
         else:

src/core/startup.py

@@ -1,3 +1,4 @@
+import os
 from src.core import DataBaseManager
 from src.core.retriever import Retriever
 from src.models import select_model
@@ -17,6 +18,10 @@ class Startup:
         self.dbm = DataBaseManager(self.config)
         self.retriever = Retriever(self.config, self.dbm, self.model)
 
+        self.model_lite = select_model(self.config,
+                                       model_provider=self.config.model_provider_lite or "zhipu",
+                                       model_name=self.config.model_name_lite or "glm-4-flash")
+
     def restart(self):
         logger.info("Restarting...")
         self.start()

src/models/__init__.py

@@ -1,10 +1,10 @@
 from src.utils.logging_config import logger
 
 
-def select_model(config):
+def select_model(config, model_provider=None, model_name=None):
 
-    model_provider = config.model_provider
+    model_provider = model_provider or config.model_provider
-    model_name = config.model_name
+    model_name = model_name or config.model_name
 
     logger.info(f"Selecting model from {model_provider} with {model_name}")
 

src/models/chat_model.py

@@ -50,8 +50,8 @@ class OpenModel(OpenAIBase):
 class DeepSeek(OpenAIBase):
     def __init__(self, model_name=None):
         model_name = model_name or "deepseek-chat"
-        api_key = os.getenv("DEEPSEEK_API_KEY")
+        api_key = os.getenv("DEEPSEEK_API_KEY", "your-default-api-key")
-        base_url = "https://api.deepseek.com"
+        base_url = os.getenv("DEEPSEEK_API_BASE", "https://api.deepseek.com/v1")
         super().__init__(api_key=api_key, base_url=base_url, model_name=model_name)
 
 

src/models/embedding.py

@@ -1,5 +1,4 @@
 import os
-import uuid
 from FlagEmbedding import FlagModel, FlagReranker
 
 from src.config import EMBED_MODEL_INFO, RERANKER_LIST
@@ -15,11 +14,7 @@ GLOBAL_EMBED_STATE = {}
 class EmbeddingModel(FlagModel):
     def __init__(self, model_info, config, **kwargs):
         self.info = model_info
-        model_name_or_path = handle_local_model(
+        model_name_or_path = config.model_local_paths.get(model_info["name"], model_info.get("default_path"))
-            paths=config.model_local_paths,
-            model_name=model_info["name"],
-            default_path=model_info.get("default_path", None))
-
         logger.info(f"Loading embedding model {model_info['name']} from {model_name_or_path}")
 
         super().__init__(model_name_or_path,
@@ -34,11 +29,8 @@ class Reranker(FlagReranker):
 
         assert config.reranker in RERANKER_LIST.keys(), f"Unsupported Reranker: {config.reranker}, only support {RERANKER_LIST.keys()}"
 
-        model_name_or_path = handle_local_model(
+        model_info = RERANKER_LIST[config.reranker]
-            paths=config.model_local_paths,
+        model_name_or_path = config.model_local_paths.get(model_info["name"], model_info.get("default_path"))
-            model_name=config.reranker,
-            default_path=RERANKER_LIST[config.reranker])
-
         logger.info(f"Loading Reranker model {config.reranker} from {model_name_or_path}")
 
         super().__init__(model_name_or_path, use_fp16=True, **kwargs)
@@ -113,6 +105,4 @@ def get_embedding_model(config):
 
 def handle_local_model(paths, model_name, default_path):
     model_path = paths.get(model_name, default_path)
-    if os.getenv("MODEL_ROOT_DIR") and not os.path.isabs(model_path):
-        model_path = os.path.join(os.getenv("MODEL_ROOT_DIR"), model_path)
     return model_path

src/models/ollama_embedding.py

@@ -0,0 +1,179 @@
+import os
+import requests
+import numpy as np
+from typing import List, Union, Dict
+from src.utils.logging_config import setup_logger
+
+logger = setup_logger("OllamaEmbedding")
+
+class OllamaEmbedding:
+    """
+    使用 Ollama API 进行文本嵌入的类
+    """
+    def __init__(self, model_info: Dict, config) -> None:
+        """
+        初始化 Ollama Embedding 模型
+        
+        Args:
+            model_info: 模型信息字典
+            config: 配置对象
+        """
+        self.config = config
+        self.model_info = model_info
+        self.base_url = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
+        self.model_name = model_info.get("name", "nomic-embed-text")
+        self.query_instruction_for_retrieval = "为这个句子生成表示以用于检索相关文章："
+        logger.info(f"Ollama Embedding model {self.model_name} initialized")
+
+    def _get_embedding(self, text: str) -> List[float]:
+        """
+        获取单个文本的嵌入向量
+        
+        Args:
+            text: 输入文本
+            
+        Returns:
+            嵌入向量
+        """
+        url = f"{self.base_url}/api/embeddings"
+        try:
+            response = requests.post(url, json={
+                "model": self.model_name,
+                "prompt": text
+            })
+            response.raise_for_status()
+            return response.json()["embedding"]
+        except Exception as e:
+            logger.error(f"Error getting embedding: {str(e)}")
+            raise
+
+    def predict(self, messages: List[str]) -> List[List[float]]:
+        """
+        批量获取文本嵌入向量
+        
+        Args:
+            messages: 文本列表
+            
+        Returns:
+            嵌入向量列表
+        """
+        embeddings = []
+        batch_size = 20
+
+        for i in range(0, len(messages), batch_size):
+            batch = messages[i:i + batch_size]
+            logger.info(f"Processing batch {i//batch_size + 1}, size: {len(batch)}")
+            
+            batch_embeddings = []
+            for text in batch:
+                embedding = self._get_embedding(text)
+                batch_embeddings.append(embedding)
+            
+            embeddings.extend(batch_embeddings)
+            
+        return embeddings
+
+    def encode(self, messages: Union[str, List[str]]) -> List[List[float]]:
+        """
+        编码文本
+        
+        Args:
+            messages: 单个文本或文本列表
+            
+        Returns:
+            嵌入向量列表
+        """
+        if isinstance(messages, str):
+            messages = [messages]
+        return self.predict(messages)
+
+    def encode_queries(self, queries: List[str]) -> List[List[float]]:
+        """
+        编码查询文本
+        
+        Args:
+            queries: 查询文本列表
+            
+        Returns:
+            查询文本的嵌入向量列表
+        """
+        return self.predict(queries)
+
+
+class OllamaReranker:
+    """
+    使用 Ollama API 进行文本重排序的类
+    """
+    def __init__(self, config) -> None:
+        """
+        初始化 Ollama Reranker
+        
+        Args:
+            config: 配置对象
+        """
+        self.config = config
+        self.base_url = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
+        self.model_name = config.reranker
+        logger.info(f"Ollama Reranker model {self.model_name} initialized")
+
+    def compute_score(self, query: str, passage: str) -> float:
+        """
+        计算查询和文本段落之间的相关性分数
+        
+        Args:
+            query: 查询文本
+            passage: 段落文本
+            
+        Returns:
+            相关性分数
+        """
+        prompt = f"Query: {query}\nPassage: {passage}\nRate the relevance of the passage to the query on a scale of 0 to 1:"
+        
+        try:
+            response = requests.post(
+                f"{self.base_url}/api/generate",
+                json={
+                    "model": self.model_name,
+                    "prompt": prompt,
+                    "stream": False
+                }
+            )
+            response.raise_for_status()
+            
+            # 提取生成的数字作为分数
+            result = response.json()["response"].strip()
+            try:
+                score = float(result)
+                return min(max(score, 0), 1)  # 确保分数在 0-1 之间
+            except ValueError:
+                logger.warning(f"Could not parse score from response: {result}")
+                return 0.0
+                
+        except Exception as e:
+            logger.error(f"Error computing rerank score: {str(e)}")
+            return 0.0
+
+    def rerank(self, query: str, passages: List[str], top_n: int = None) -> List[Dict]:
+        """
+        重新排序文本段落
+        
+        Args:
+            query: 查询文本
+            passages: 段落文本列表
+            top_n: 返回前 n 个结果
+            
+        Returns:
+            排序后的结果列表，每个元素包含索引和分数
+        """
+        scores = []
+        for i, passage in enumerate(passages):
+            score = self.compute_score(query, passage)
+            scores.append({"index": i, "score": score})
+        
+        # 按分数降序排序
+        sorted_results = sorted(scores, key=lambda x: x["score"], reverse=True)
+        
+        if top_n:
+            sorted_results = sorted_results[:top_n]
+            
+        return sorted_results 

src/plugins/oneke.py

@@ -16,8 +16,6 @@ logger = setup_logger("OneKE")
 
 dotenv.load_dotenv()
 
-MODEL_NAME_OR_PATH = os.path.join(os.getenv('MODEL_ROOT_DIR', './'), 'OneKE')
-
 instruction_mapper = {
     'NERzh': "你是专门进行实体抽取的专家。请从input中抽取出符合schema定义的实体，不存在的实体类型返回空列表。请按照JSON字符串的格式回答。",
     'REzh': "你是专门进行关系抽取的专家。请从input中抽取出符合schema定义的关系三元组。请按照JSON字符串的格式回答。",
@@ -42,7 +40,7 @@ class OneKE:
     def __init__(self, config=None):
 
         self.config = config
-        model_name_or_path = config.model_local_paths.get('oneke', "zjunlp/OneKE")
+        model_name_or_path = config.model_local_paths.get('zjunlp/OneKE', "zjunlp/OneKE")
         logger.info(f"Loading KGC model OneKE from {model_name_or_path}")
 
         model_config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)

src/routers/chat_router.py

@@ -27,9 +27,10 @@ def chat_post(
 
     history_manager = HistoryManager(history)
 
-    def make_chunk(content, status, history):
+    def make_chunk(content=None, status=None, history=None, reasoning_content=None):
         return json.dumps({
             "response": content,
+            "reasoning_response": reasoning_content,
             "history": history,
             "model_name": startup.config.model_name,
             "status": status,
@@ -37,33 +38,44 @@ def chat_post(
         }, ensure_ascii=False).encode('utf-8') + b"\n"
 
     def generate_response():
+        modified_query = query
 
-        if meta.get("enable_retrieval"):
+        # 处理知识库检索
-            chunk = make_chunk("", "searching", history=None)
+        if meta and meta.get("enable_retrieval"):
+            chunk = make_chunk(status="searching")
             yield chunk
 
-            new_query, refs = startup.retriever(query, history_manager.messages, meta)
+            modified_query, refs = startup.retriever(modified_query, history_manager.messages, meta)
             refs_pool[cur_res_id] = refs
-        else:
-            new_query = query
 
-        messages = history_manager.get_history_with_msg(new_query, max_rounds=meta.get('history_round'))
+        messages = history_manager.get_history_with_msg(modified_query, max_rounds=meta.get('history_round'))
-        history_manager.add_user(query)
+        history_manager.add_user(query)  # 注意这里使用原始查询
         logger.debug(f"Web history: {history_manager.messages}")
 
         content = ""
+        reasoning_content = ""
         for delta in startup.model.predict(messages, stream=True):
-            if not delta.content:
+            if not delta.content and hasattr(delta, 'reasoning_content'):
+                reasoning_content += delta.reasoning_content
+                chunk = make_chunk(reasoning_content=reasoning_content, status="reasoning")
+                yield chunk
                 continue
 
+            # 文心一言
             if hasattr(delta, 'is_full') and delta.is_full:
                 content = delta.content
             else:
-                content += delta.content
+                content += delta.content or ""
 
-            chunk = make_chunk(content, "loading", history=history_manager.update_ai(content))
+            chunk = make_chunk(content=content,
+                               reasoning_content=reasoning_content,
+                               status="loading",
+                               history=history_manager.update_ai(content))
             yield chunk
 
+        logger.debug(f"Final response: {content}")
+        logger.debug(f"Final reasoning response: {reasoning_content}")
+
     return StreamingResponse(generate_response(), media_type='application/json')
 
 @chat.post("/call")
@@ -77,6 +89,17 @@ async def call(query: str = Body(...), meta: dict = Body(None)):
 
     return {"response": response.content}
 
+@chat.post("/call_lite")
+async def call(query: str = Body(...), meta: dict = Body(None)):
+    async def predict_async(query):
+        loop = asyncio.get_event_loop()
+        return await loop.run_in_executor(executor, startup.model_lite.predict, query)
+
+    response = await predict_async(query)
+    logger.debug({"query": query, "response": response.content})
+
+    return {"response": response.content}
+
 @chat.get("/refs")
 def get_refs(cur_res_id: str):
     global refs_pool

src/static/models.yaml

@@ -18,6 +18,7 @@ MODEL_NAMES:
       - DEEPSEEK_API_KEY
     models:
       - deepseek-chat
+      - deepseek-reasoner
   zhipu:
     name: 智谱AI (Zhipu)
     url: https://open.bigmodel.cn/dev/api
@@ -74,13 +75,13 @@ MODEL_NAMES:
       - meta-llama/Meta-Llama-3.1-8B-Instruct
       - meta-llama/Meta-Llama-3.1-70B-Instruct
       - meta-llama/Meta-Llama-3.1-405B-Instruct
+      - deepseek-ai/DeepSeek-R1
 
 EMBED_MODEL_INFO:
-  bge-large-zh-v1.5:
+  bge-m3:
-    name: bge-large-zh-v1.5
+    name: BAAI/bge-m3
-    default_path: BAAI/bge-large-zh-v1.5
+    default_path: BAAI/bge-m3
     dimension: 1024
-    query_instruction: "为这个句子生成表示以用于检索相关文章："
   zhipu-embedding-2:
     name: zhipu-embedding-2
     default_path: embedding-2
@@ -91,4 +92,6 @@ EMBED_MODEL_INFO:
     dimension: 2048
 
 RERANKER_LIST:
-  bge-reranker-v2-m3: BAAI/bge-reranker-v2-m3
+  bge-reranker-v2-m3:
+    name: BAAI/bge-reranker-v2-m3
+    default_path: BAAI/bge-reranker-v2-m3

src/utils/web_search.py

@@ -0,0 +1,69 @@
+import os
+from typing import List, Dict
+from tavily import TavilyClient
+from src.utils.logging_config import setup_logger
+
+logger = setup_logger("web-search")
+
+class WebSearcher:
+    def __init__(self):
+        api_key = os.getenv("TAVILY_API_KEY")
+        if not api_key:
+            raise ValueError("TAVILY_API_KEY environment variable is not set")
+        self.client = TavilyClient(api_key)
+        logger.info("WebSearcher initialized with Tavily client")
+
+    def search(self, query: str, max_results: int = 1) -> List[Dict]:
+        """
+        使用 Tavily 搜索相关内容
+        
+        Args:
+            query: 搜索查询
+            max_results: 最大返回结果数
+            
+        Returns:
+            搜索结果列表
+        """
+        try:
+            search_results = self.client.search(
+                query=query,
+                search_depth="basic",
+                max_results=max_results
+            )
+            
+            # 提取需要的信息
+            formatted_results = []
+            for result in search_results['results'][:max_results]:
+                formatted_results.append({
+                    'title': result.get('title', ''),
+                    'content': result.get('content', ''),
+                    'url': result.get('url', ''),
+                    'score': result.get('score', 0)
+                })
+                
+            return formatted_results
+            
+        except Exception as e:
+            logger.error(f"Error during web search: {str(e)}")
+            return []
+
+    def format_search_results(self, results: List[Dict]) -> str:
+        """
+        将搜索结果格式化为文本
+        
+        Args:
+            results: 搜索结果列表
+            
+        Returns:
+            格式化后的文本
+        """
+        if not results:
+            return "没有找到相关的网络搜索结果。"
+            
+        formatted_text = "以下是相关的网络搜索结果：\n\n"
+        for i, result in enumerate(results, 1):
+            formatted_text += f"{i}. {result['title']}\n"
+            formatted_text += f"   {result['content']}\n"
+            formatted_text += f"   来源: {result['url']}\n\n"
+            
+        return formatted_text 

test/test_concurrency.py

@@ -0,0 +1,121 @@
+import asyncio
+import aiohttp
+import time
+import json
+from typing import List
+
+async def make_request(session: aiohttp.ClientSession, request_id: int) -> dict:
+    """发送单个请求到API"""
+    url = "http://localhost:5000/chat/call"
+    payload = {
+        "query": "写一个冒泡排序",
+        "meta": {}
+    }
+
+    start_time = time.time()
+    print(f"请求 {request_id} 开始时间: {time.strftime('%H:%M:%S', time.localtime(start_time))}")
+    try:
+        async with session.post(url, json=payload) as response:
+            result = await response.json()
+            end_time = time.time()
+            duration = end_time - start_time
+            print(f"请求 {request_id} 完成时间: {time.strftime('%H:%M:%S', time.localtime(end_time))} (耗时: {duration:.2f}秒)")
+            return {
+                "request_id": request_id,
+                "status": response.status,
+                "time": duration,
+                "start_time": start_time,
+                "end_time": end_time,
+                "success": True
+            }
+    except Exception as e:
+        end_time = time.time()
+        duration = end_time - start_time
+        print(f"请求 {request_id} 失败时间: {time.strftime('%H:%M:%S', time.localtime(end_time))} (耗时: {duration:.2f}秒)")
+        return {
+            "request_id": request_id,
+            "status": None,
+            "time": duration,
+            "start_time": start_time,
+            "end_time": end_time,
+            "success": False,
+            "error": str(e)
+        }
+
+async def run_concurrent_test(num_requests: int = 10) -> List[dict]:
+    """运行并发测试"""
+    async with aiohttp.ClientSession() as session:
+        tasks = [make_request(session, i) for i in range(num_requests)]
+        return await asyncio.gather(*tasks)
+
+def analyze_results(results: List[dict]) -> None:
+    """分析并打印测试结果"""
+    total_requests = len(results)
+    successful_requests = sum(1 for r in results if r["success"])
+    failed_requests = total_requests - successful_requests
+
+    response_times = [r["time"] for r in results if r["success"]]
+    if response_times:
+        avg_time = sum(response_times) / len(response_times)
+        max_time = max(response_times)
+        min_time = min(response_times)
+    else:
+        avg_time = max_time = min_time = 0
+
+    print(f"\n=== 并发测试结果 ===")
+    print(f"总请求数: {total_requests}")
+    print(f"成功请求: {successful_requests}")
+    print(f"失败请求: {failed_requests}")
+    print(f"平均响应时间: {avg_time:.2f} 秒")
+    print(f"最长响应时间: {max_time:.2f} 秒")
+    print(f"最短响应时间: {min_time:.2f} 秒")
+
+    if failed_requests > 0:
+        print("\n失败的请求:")
+        for result in results:
+            if not result["success"]:
+                print(f"请求 ID {result['request_id']}: {result.get('error', '未知错误')}")
+
+    # 添加请求时间线分析
+    print("\n=== 请求时间线分析 ===")
+    sorted_results = sorted(results, key=lambda x: x["start_time"])
+    test_start_time = sorted_results[0]["start_time"]
+
+    print("\n时间线详情:")
+    print("请求ID  开始时间    结束时间    耗时(秒)  重叠请求数")
+    active_requests = []
+
+    for result in sorted_results:
+        # 计算当前时间点的活跃请求数
+        start_time = result["start_time"]
+        end_time = result["end_time"]
+
+        # 清理已完成的请求
+        active_requests = [t for t in active_requests if t > start_time]
+        active_requests.append(end_time)
+
+        print(f"{result['request_id']:^7} {time.strftime('%H:%M:%S', time.localtime(start_time))}  "
+              f"{time.strftime('%H:%M:%S', time.localtime(end_time))}  "
+              f"{result['time']:^8.2f}  {len(active_requests):^6}")
+
+    # 计算最大并发数
+    max_concurrent = 0
+    timeline = []
+    for r in results:
+        timeline.append((r["start_time"], 1))
+        timeline.append((r["end_time"], -1))
+
+    timeline.sort(key=lambda x: x[0])
+    current_concurrent = 0
+    for _, change in timeline:
+        current_concurrent += change
+        max_concurrent = max(max_concurrent, current_concurrent)
+
+    print(f"\n最大并发请求数: {max_concurrent}")
+
+if __name__ == "__main__":
+    NUM_REQUESTS = 100  # 设置并发请求数
+
+    print(f"开始运行 {NUM_REQUESTS} 个并发请求的测试...")
+    results = asyncio.run(run_concurrent_test(NUM_REQUESTS))
+    analyze_results(results)

web/src/components/ChatComponent.vue

@@ -81,9 +81,12 @@
           <div class="flex-center" @click="meta.use_web = !meta.use_web" v-if="configStore.config.enable_search_engine && meta.enable_retrieval">
             搜索引擎（Bing） <div @click.stop><a-switch v-model:checked="meta.use_web" /></div>
           </div>
-          <div class="flex-center" v-if="configStore.config.enable_knowledge_base && meta.enable_retrieval">
+          <div class="flex-center" @click="meta.enable_web_search = !meta.enable_web_search" v-if="configStore.config.enable_search_engine && meta.enable_retrieval">
-            重写查询 <a-segmented v-model:value="meta.rewriteQuery" :options="['off', 'on', 'hyde']"/>
+            网页搜索 <div @click.stop><a-switch v-model:checked="meta.enable_web_search" /></div>
           </div>
+          <!-- <div class="flex-center" v-if="configStore.config.enable_knowledge_base && meta.enable_retrieval">
+            重写查询 <a-segmented v-model:value="meta.use_rewrite_query" :options="['off', 'on', 'hyde']"/>
+          </div> -->
         </div>
       </div>
     </div>
@@ -114,6 +117,7 @@
           <div></div>
         </div>
         <div v-else-if="message.status == 'searching' && isStreaming" class="searching-msg"><i>正在检索……</i></div>
+        <div v-else-if="message.status == 'reasoning' && isStreaming" class="searching-msg"><i>正在思考…… {{ message.reasoning }}</i></div>
         <div
           v-else-if="message.text.length == 0 || message.status == 'error' || (message.status != 'finished' && !isStreaming)"
           class="err-msg"
@@ -191,11 +195,7 @@ const panel = ref(null)
 const modelCard = ref(null)
 const examples = ref([
   '写一个冒泡排序',
-  '肉碱的分子量是多少？直接回答',
-  '总结大蒜的功效是什么？',
   '今天天气怎么样？',
-  '吃饭吃出苍蝇可以索赔吗？',
-  '帮我写一个请假条',
   '贾宝玉今年多少岁？',
 ])
 
@@ -210,11 +210,12 @@ const meta = reactive(JSON.parse(localStorage.getItem('meta')) || {
   enable_retrieval: false,
   use_graph: false,
   use_web: false,
+  enable_web_search: false,
   graph_name: "neo4j",
-  rewriteQuery: "off",
+  // use_rewrite_query: "off",
   selectedKB: null,
   stream: true,
-  summary_title: true,
+  summary_title: false,
   history_round: 5,
 })
 
@@ -313,11 +314,12 @@ const appendUserMessage = (message) => {
   scrollToBottom()
 }
 
-const appendAiMessage = (message, refs=null) => {
+const appendAiMessage = (text, refs=null) => {
   conv.value.messages.push({
     id: generateRandomHash(16),
     role: 'received',
-    text: message,
+    text: text,
+    reasoning: '',
     refs,
     status: "init",
     meta: {},
@@ -329,33 +331,42 @@ const updateMessage = (info) => {
   const message = conv.value.messages.find((message) => message.id === info.id);
 
   if (message) {
-    // 只有在 text 不为空时更新
+    try {
-    if (info.text !== null && info.text !== undefined && info.text !== '') {
+      // 只有在 text 不为空时更新
-      message.text = info.text;
+      if (info.text !== null && info.text !== undefined && info.text !== '') {
-    }
+        message.text = info.text;
+      }
 
-    // 只有在 refs 不为空时更新
+      if (info.reasoning !== null && info.reasoning !== undefined && info.reasoning !== '') {
-    if (info.refs !== null && info.refs !== undefined) {
+        message.reasoning = info.reasoning;
-      message.refs = info.refs;
+      }
-    }
 
-    if (info.model_name !== null && info.model_name !== undefined && info.model_name !== '') {
+      // 只有在 refs 不为空时更新
-      message.model_name = info.model_name;
+      if (info.refs !== null && info.refs !== undefined) {
-    }
+        message.refs = info.refs;
+      }
+
+      if (info.model_name !== null && info.model_name !== undefined && info.model_name !== '') {
+        message.model_name = info.model_name;
+      }
 
     // 只有在 status 不为空时更新
-    if (info.status !== null && info.status !== undefined && info.status !== '') {
+      if (info.status !== null && info.status !== undefined && info.status !== '') {
-      message.status = info.status;
+        message.status = info.status;
-    }
+      }
 
-    if (info.meta !== null && info.meta !== undefined) {
+      if (info.meta !== null && info.meta !== undefined) {
-      message.meta = info.meta;
+        message.meta = info.meta;
+      }
+      scrollToBottom();
+    } catch (error) {
+      console.error('Error updating message:', error);
+      message.status = 'error';
+      message.text = '消息更新失败';
     }
   } else {
-    console.error('Message not found');
+    console.error('Message not found:', info.id);
   }
-
-  scrollToBottom();
 };
 
 
@@ -378,7 +389,7 @@ const groupRefs = (id) => {
 
 const simpleCall = (message) => {
   return new Promise((resolve, reject) => {
-    fetch('/api/chat/call', {
+    fetch('/api/chat/call_lite', {
       method: 'POST',
       body: JSON.stringify({ query: message, }),
       headers: { 'Content-Type': 'application/json' }
@@ -457,10 +468,12 @@ const fetchChatResponse = (user_input, cur_res_id) => {
               updateMessage({
                 id: cur_res_id,
                 text: data.response,
+                reasoning: data.reasoning_response,
                 model_name: data.model_name,
                 status: data.status,
                 meta: data.meta,
               });
+              // console.log(data)
               // console.log("Last message", conv.value.messages[conv.value.messages.length - 1].text)
               // console.log("Last message", conv.value.messages[conv.value.messages.length - 1].status)
 
@@ -648,6 +661,17 @@ watch(
     &:hover {
       background-color: var(--main-light-3);
     }
+
+    .anticon {
+      margin-right: 8px;
+      font-size: 16px;
+    }
+
+    .ant-switch {
+      &.ant-switch-checked {
+        background-color: var(--main-500);
+      }
+    }
   }
 }
 
@@ -977,7 +1001,15 @@ watch(
   }
 }
 
+.controls {
+  display: flex;
+  align-items: center;
+  gap: 8px;
 
+  .search-switch {
+    margin-right: 8px;
+  }
+}
 </style>
 
 <style lang="less">

web/src/components/RefsComponent.vue

@@ -2,8 +2,8 @@
   <div class="refs" v-if="showRefs">
     <div class="tags">
       <span class="item btn" @click="copyText(msg.text)"><CopyOutlined /></span>
-      <span class="item btn" @click="likeThisResponse(msg)"><LikeOutlined /></span>
+      <!-- <span class="item btn" @click="likeThisResponse(msg)"><LikeOutlined /></span> -->
-      <span class="item btn" @click="dislikeThisResponse(msg)"><DislikeOutlined /></span>
+      <!-- <span class="item btn" @click="dislikeThisResponse(msg)"><DislikeOutlined /></span> -->
       <span class="item"><GlobalOutlined /> {{ msg.model_name }}</span>
       <span
         class="item btn"

web/src/components/TableConfigComponent.vue

@@ -0,0 +1,212 @@
+<template>
+  <a-card class="config-card" style="max-width: 960px">
+    <a-form layout="vertical">
+      <div
+        v-for="(item, index) in configList"
+        :key="index"
+        class="config-item"
+      >
+        <a-row :gutter="[16, 8]" align="middle">
+          <a-col :span="8">
+            <a-input
+              v-model:value="item.key"
+              placeholder="模型名称"
+              readonly
+              class="key-input"
+            />
+          </a-col>
+          <a-col :span="14">
+            <a-input
+              v-model:value="item.value"
+              @change="updateValue(index)"
+              placeholder="模型本地路径"
+              class="value-input"
+            />
+          </a-col>
+          <a-col :span="2" class="delete-btn-col">
+            <a-button
+              type="link"
+              danger
+              class="delete-btn"
+              @click="deleteConfig(index)"
+            >
+              <DeleteOutlined />
+            </a-button>
+          </a-col>
+        </a-row>
+      </div>
+
+      <a-button block @click="addConfig" class="add-btn" :disabled="isAdding">
+        <PlusOutlined /> 添加路径映射
+      </a-button>
+    </a-form>
+
+    <a-modal
+      title="添加路径映射"
+      v-model:open="addConfigModalVisible"
+      @ok="confirmAddConfig"
+      class="config-modal"
+    >
+      <a-form layout="vertical">
+        <a-form-item label="模型名称（与Huggingface名称一致，比如 BAAI/bge-large-zh-v1.5" required>
+          <a-input
+            v-model:value="newConfig.key"
+            placeholder="请输入模型名称"
+            class="modal-input"
+          />
+        </a-form-item>
+        <a-form-item label="模型本地路径（绝对路径，比如 /hdd/models/BAAI/bge-large-zh-v1.5）" required>
+          <a-input
+            v-model:value="newConfig.value"
+            placeholder="请输入模型本地路径"
+            class="modal-input"
+          />
+        </a-form-item>
+      </a-form>
+    </a-modal>
+  </a-card>
+</template>
+
+<script setup>
+import { ref, reactive, computed, watch } from 'vue';
+import { message } from 'ant-design-vue';
+import { DeleteOutlined, PlusOutlined } from '@ant-design/icons-vue';
+
+const props = defineProps({
+  config: {
+    type: Object,
+    default: () => ({})
+  }
+});
+
+const emit = defineEmits(['update:config']);
+
+// 配置列表
+const configList = reactive([]);
+
+// 初始化配置列表
+props.config && Object.entries(props.config).forEach(([key, value]) => {
+  configList.push({ key, value });
+});
+
+// 控制模态框显示
+const addConfigModalVisible = ref(false);
+const isAdding = ref(false); // 添加新的ref变量
+
+// 新增配置项数据
+const newConfig = ref({ key: '', value: '' });
+
+// 添加配置
+const addConfig = () => {
+  isAdding.value = true;  // 设置添加状态
+  addConfigModalVisible.value = true;
+};
+
+// 确认添加配置
+const confirmAddConfig = () => {
+  if (newConfig.value.key === '' || newConfig.value.value === '') {
+    message.warning('键或值不能为空');
+    return;
+  }
+  if (configList.some(item => item.key === newConfig.value.key)) {
+    message.warning('键已存在');
+    return;
+  }
+  configList.push({ key: newConfig.value.key, value: newConfig.value.value });
+  addConfigModalVisible.value = false;
+  newConfig.value = { key: '', value: '' };
+  isAdding.value = false;  // 重置添加状态
+};
+
+// 删除配置
+const deleteConfig = (index) => {
+  configList.splice(index, 1);
+};
+
+// 更新值
+const updateValue = (index) => {
+  // 值的更新实时反映在 configList 中，无需额外处理
+};
+
+// 将配置列表转换为对象
+const configObject = computed(() => {
+  return configList.reduce((acc, item) => {
+    acc[item.key] = item.value;
+    return acc;
+  }, {});
+});
+
+// 监听配置变化并传递回父组件
+watch(configObject, (newValue) => {
+  emit('update:config', newValue);
+}, { deep: true });
+
+// 监听模态框关闭
+watch(addConfigModalVisible, (newValue) => {
+  if (!newValue) {
+    isAdding.value = false;  // 当模态框关闭时重置添加状态
+  }
+});
+</script>
+
+<style scoped>
+.config-card {
+  background-color: var(--gray-10);
+  border-radius: 8px;
+  border: 1px solid var(--gray-300);
+}
+
+.config-item {
+  border-bottom: 1px solid #f0f0f0;
+  padding: 12px 0;
+  transition: background-color 0.3s ease;
+}
+
+.config-item:hover {
+  background-color: #fafafa;
+}
+
+.config-item:last-child {
+  border-bottom: none;
+}
+
+.key-input {
+  background-color: #f8f8f8;
+  border-color: #e8e8e8;
+}
+
+.delete-btn-col {
+  display: flex;
+  justify-content: center;
+  align-items: center;
+}
+
+.delete-btn {
+  opacity: 0.6;
+  transition: opacity 0.3s ease;
+}
+
+.delete-btn:hover {
+  opacity: 1;
+}
+
+.add-btn {
+  margin-top: 16px;
+  height: 40px;
+  transition: all 0.3s ease;
+  width: auto;
+}
+
+.modal-input {
+  margin-bottom: 8px;
+}
+
+:deep(.ant-modal-content) {
+  border-radius: 8px;
+}
+
+:deep(.ant-card-body) {
+  padding: 16px;
+}
+</style>
+

web/src/router/index.js

@@ -11,7 +11,7 @@ const router = createRouter({
       component: BlankLayout,
       children: [        {
           path: '',
-          name: 'home',
+          name: 'Home',
           component: () => import('../views/HomeView.vue'),
           meta: { keepAlive: true }
         }

web/src/views/DataBaseInfoView.vue

@@ -132,7 +132,7 @@
                 <div class="params-group">
                   <div class="params-item col">
                     <p>重写查询<small>（修改后需重新检索）</small>：</p>
-                    <a-segmented v-model:value="meta.rewriteQuery" :options="rewriteQueryOptions">
+                    <a-segmented v-model:value="meta.use_rewrite_query" :options="use_rewrite_queryOptions">
                       <template #label="{ payload }">
                         <div>
                           <p style="margin: 4px 0">{{ payload.subTitle }}</p>
@@ -251,13 +251,13 @@ const meta = reactive({
   mode: 'search',
   maxQueryCount: 30,
   filter: true,
-  rewriteQuery: 'off',
+  use_rewrite_query: 'off',
   rerankThreshold: 0.1,
   distanceThreshold: 0.3,
   topK: 10,
 });
 
-const rewriteQueryOptions = ref([
+const use_rewrite_queryOptions = ref([
   { value: 'off', payload: { title: 'off', subTitle: '不启用' } },
   { value: 'on', payload: { title: 'on', subTitle: '启用重写' } },
   { value: 'hyde', payload: { title: 'hyde', subTitle: '伪文档生成' } },
@@ -546,10 +546,7 @@ watch(() => meta, () => {
 
 // 添加示例查询
 const queryExamples = ref([
-  '食品添加剂的安全性如何?',
+  '贾宝玉的丫鬟有哪些？',
-  '如何识别和预防食物中毒?',
-  '转基因食品对人体健康有什么影响?',
-  '如何正确储存和处理生鲜食品?'
 ]);
 
 // 使用示例查询的方法

web/src/views/SettingView.vue

@@ -2,7 +2,7 @@
   <div class="">
     <HeaderComponent title="设置" class="setting-header">
       <template #description>
-        <p>配置文件也可以在 <code>saves/config/config.yaml</code> 中修改</p>
+        <p>配置文件也可以在 <code>src/static/config.yaml</code> 中修改</p>
       </template>
       <template #actions>
         <a-button type="primary" v-if="isNeedRestart" @click="sendRestart">
@@ -79,6 +79,21 @@
             />
           </div>
         </div>
+        <h3>检索配置</h3>
+        <div class="section">
+          <div class="card">
+            <span class="label">{{ items?.use_rewrite_query.des }}</span>
+            <a-select style="width: 200px"
+              :value="configStore.config?.use_rewrite_query"
+              @change="handleChange('use_rewrite_query', $event)"
+            >
+              <a-select-option
+                v-for="(name, idx) in items?.use_rewrite_query.choices" :key="idx"
+                :value="name">{{ name }}
+              </a-select-option>
+            </a-select>
+          </div>
+        </div>
       </div>
       <div class="setting" v-if="state.section === 'model'">
         <h3>模型配置</h3>
@@ -161,16 +176,21 @@
         </div>
         <div class="model-provider-card" v-for="(item, key) in notModelKeys" :key="key">
           <div class="card-header">
-            <h3>{{ modelNames[item].name }}</h3>
+            <h3 style="font-weight: 400">{{ modelNames[item].name }}</h3>
-            <a :href="modelNames[item].url" target="_blank">详情</a>
+            <a :href="modelNames[item].url" target="_blank"><InfoCircleOutlined /></a>
             <div class="missing-keys">
-              需配置 <span v-for="(key, idx) in modelNames[item].env" :key="idx">{{ key }}</span>
+              <small>需配置</small> <span v-for="(key, idx) in modelNames[item].env" :key="idx">{{ key }}</span>
             </div>
           </div>
         </div>
       </div>
       <div class="setting" v-if="state.section ==='path'">
-        <h3>暂无配置</h3>
+        <h3>本地模型配置</h3>
+        <p>如果是 Docker 启动，务必确保在环境变量中设置了 MODEL_DIR，或者设置了 volumes 映射</p>
+        <TableConfigComponent
+          :config="configStore.config?.model_local_paths"
+          @update:config="handleModelLocalPathsUpdate"
+        />
       </div>
     </div>
   </div>
@@ -191,6 +211,7 @@ import {
   InfoCircleOutlined,
 } from '@ant-design/icons-vue';
 import HeaderComponent from '@/components/HeaderComponent.vue';
+import TableConfigComponent from '@/components/TableConfigComponent.vue';
 import { notification, Button } from 'ant-design-vue';
 
 const configStore = useConfigStore()
@@ -231,6 +252,10 @@ const generateRandomHash = (length) => {
   return hash;
 }
 
+const handleModelLocalPathsUpdate = (config) => {
+  handleChange('model_local_paths', config)
+}
+
 const handleChange = (key, e) => {
   if (key == 'enable_knowledge_graph' && e && !configStore.config.enable_knowledge_base) {
     message.error('启动知识图谱必须请先启用知识库功能')
@@ -249,7 +274,8 @@ const handleChange = (key, e) => {
         || key == 'model_provider'
         || key == 'model_name'
         || key == 'embed_model'
-        || key == 'reranker') {
+        || key == 'reranker'
+        || key == 'model_local_paths') {
     if (!isNeedRestart.value) {
       isNeedRestart.value = true
       notification.info({