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

docs/latest/changelog/roadmap.md

@@ -15,12 +15,12 @@
 - 同名文件处理逻辑：遇到同名文件则在上传区域提示，是否删除旧文件
 - conversation 待修改为异步的版本
 - DBManager 需要将数据库修改为异步的aiosqlite或者异步mysql，缓存使用Redis存储
-- agent 状态中的文件区域，新增可以下载
 
 ### Bugs
 - 部分异常状态下，智能体的模型名称出现重叠[#279](https://github.com/xerrors/Yuxi-Know/issues/279)
 - DeepSeek 官方接口适配会出现问题
 - 目前的知识库的图片存在公开访问风险
+- 深度分析智能体需要考虑上下文超限的问题
 
 ### 新增
 - 优化知识库详情页面，更加简洁清晰
@@ -34,6 +34,8 @@
 - 新增自定义模型支持、新增 dashscope rerank/embeddings 模型的支持
 - 新增文档解析的图片支持，已支持 MinerU Officical、Docs、Markdown Zip格式
 - 新增暗色模式支持并调整整体 UI（[#343](https://github.com/xerrors/Yuxi-Know/pull/343)）
+- agent 状态中的文件区域，新增可以下载
+- 移除 Chroma 的支持，当前版本标记为移除
 
 ### 修复
 - 修复重排序模型实际未生效的问题

server/routers/knowledge_router.py

@@ -87,10 +87,12 @@ async def create_database(
     """创建知识库"""
     logger.debug(
         f"Create database {database_name} with kb_type {kb_type}, "
-        f"additional_params {additional_params}, llm_info {llm_info}"
+        f"additional_params {additional_params}, llm_info {llm_info}, "
+        f"embed_model_name {embed_model_name}"
     )
     try:
         additional_params = {**(additional_params or {})}
+        additional_params["auto_generate_questions"] = False  # 默认不生成问题
 
         def normalize_reranker_config(kb: str, params: dict) -> None:
             reranker_cfg = params.get("reranker_config")
@@ -112,12 +114,12 @@ async def create_database(
             if not isinstance(reranker_cfg, Mapping):
                 raise HTTPException(status_code=400, detail="reranker_config must be an object")
 
-            enabled = bool(reranker_cfg.get("enabled", False))
+            reranker_enabled = bool(reranker_cfg.get("enabled", False))
             model = (reranker_cfg.get("model") or "").strip()
             recall_top_k = max(1, int(reranker_cfg.get("recall_top_k", 50)))
             final_top_k = max(1, int(reranker_cfg.get("final_top_k", 10)))
 
-            if enabled:
+            if reranker_enabled:
                 if not model:
                     raise HTTPException(status_code=400, detail="reranker_config.model is required when enabled")
                 if model not in config.reranker_names:
@@ -132,7 +134,7 @@ async def create_database(
                 model = model if model in config.reranker_names else ""
 
             params["reranker_config"] = {
-                "enabled": enabled,
+                "enabled": reranker_enabled,
                 "model": model,
                 "recall_top_k": recall_top_k,
                 "final_top_k": final_top_k,

src/agents/common/mcp_repos/arxiv-mcp-server

@@ -0,0 +1 @@
+Subproject commit 057e2000be7b56823239815b0fe7c7fc0dbced96

src/agents/common/mcp_repos/mcp-server-mysql

@@ -0,0 +1 @@
+Subproject commit 6a0367834ea0fb5e5c94b9711e3e2756966789ea

src/config/static/models.py

@@ -29,7 +29,7 @@ class EmbedModelInfo(BaseModel):
     dimension: int = Field(..., description="向量维度")
     base_url: str = Field(..., description="API 基础 URL")
     api_key: str = Field(..., description="API Key 或环境变量名")
-
+    model_id: str | None = Field(None, description="可选的模型 ID")
 
 class RerankerInfo(BaseModel):
     """重排序模型配置"""
@@ -158,42 +158,49 @@ DEFAULT_CHAT_MODEL_PROVIDERS: dict[str, ChatModelProvider] = {
 
 DEFAULT_EMBED_MODELS: dict[str, EmbedModelInfo] = {
     "siliconflow/BAAI/bge-m3": EmbedModelInfo(
+        model_id="siliconflow/BAAI/bge-m3",
         name="BAAI/bge-m3",
         dimension=1024,
         base_url="https://api.siliconflow.cn/v1/embeddings",
         api_key="SILICONFLOW_API_KEY",
     ),
     "siliconflow/Pro/BAAI/bge-m3": EmbedModelInfo(
+        model_id="siliconflow/Pro/BAAI/bge-m3",
         name="Pro/BAAI/bge-m3",
         dimension=1024,
         base_url="https://api.siliconflow.cn/v1/embeddings",
         api_key="SILICONFLOW_API_KEY",
     ),
     "siliconflow/Qwen/Qwen3-Embedding-0.6B": EmbedModelInfo(
+        model_id="siliconflow/Qwen/Qwen3-Embedding-0.6B",
         name="Qwen/Qwen3-Embedding-0.6B",
         dimension=1024,
         base_url="https://api.siliconflow.cn/v1/embeddings",
         api_key="SILICONFLOW_API_KEY",
     ),
     "vllm/Qwen/Qwen3-Embedding-0.6B": EmbedModelInfo(
+        model_id="vllm/Qwen/Qwen3-Embedding-0.6B",
         name="Qwen3-Embedding-0.6B",
         dimension=1024,
         base_url="http://localhost:8000/v1/embeddings",
         api_key="no_api_key",
     ),
     "ollama/nomic-embed-text": EmbedModelInfo(
+        model_id="ollama/nomic-embed-text",
         name="nomic-embed-text",
         dimension=768,
         base_url="http://localhost:11434/api/embed",
         api_key="no_api_key",
     ),
     "ollama/bge-m3": EmbedModelInfo(
+        model_id="ollama/bge-m3",
         name="bge-m3",
         dimension=1024,
         base_url="http://localhost:11434/api/embed",
         api_key="no_api_key",
     ),
     "dashscope/text-embedding-v4": EmbedModelInfo(
+        model_id="dashscope/text-embedding-v4",
         name="text-embedding-v4",
         dimension=1024,
         base_url="https://dashscope.aliyuncs.com/compatible-mode/v1/embeddings",

src/knowledge/implementations/milvus.py

@@ -7,6 +7,7 @@ from typing import Any
 
 from pymilvus import Collection, CollectionSchema, DataType, FieldSchema, connections, db, utility
 
+from src import config
 from src.knowledge.base import KnowledgeBase
 from src.knowledge.indexing import process_file_to_markdown
 from src.knowledge.utils.kb_utils import (
@@ -91,10 +92,14 @@ class MilvusKB(KnowledgeBase):
         """创建 Milvus 集合"""
         logger.info(f"Creating Milvus collection for {db_id}")
 
-        if db_id not in self.databases_meta:
+        if not (metadata := self.databases_meta.get(db_id)):
             raise ValueError(f"Database {db_id} not found")
 
-        embed_info = self.databases_meta[db_id].get("embed_info", {})
+        # embed_info = metadata.get("embed_info", {})
+        if not (embed_info := metadata.get("embed_info")):
+            logger.error(f"Embedding info not found for database {db_id}, using default model")
+            embed_info = config.embed_model_names[config.embed_model]
+
         collection_name = db_id
 
         try:
@@ -117,8 +122,8 @@ class MilvusKB(KnowledgeBase):
 
         except Exception:
             # 创建新集合
-            embedding_dim = getattr(embed_info, "dimension", 1024) if embed_info else 1024
+            embedding_dim = embed_info.get("dimension", 1024)
-            model_name = getattr(embed_info, "name", "default") if embed_info else "default"
+            model_name = embed_info.get("name", "default")
 
             # 定义集合Schema
             fields = [
@@ -142,7 +147,7 @@ class MilvusKB(KnowledgeBase):
             index_params = {"metric_type": "COSINE", "index_type": "IVF_FLAT", "params": {"nlist": 1024}}
             collection.create_index("embedding", index_params)
 
-            logger.info(f"Created new Milvus collection: {collection_name}")
+            logger.info(f"Created new Milvus collection: {collection_name}: {model_name=}, {embedding_dim=}")
 
         return collection
 
@@ -154,25 +159,29 @@ class MilvusKB(KnowledgeBase):
         except Exception as e:
             logger.warning(f"Failed to load collection into memory: {e}")
 
-    def _get_async_embedding_function(self, embed_info: dict):
+    def _get_async_embedding(self, embed_info: dict):
         """获取 embedding 函数"""
+        # 检查是否有 model_id 字段，优先使用 select_embedding_model
+        if embed_info and "model_id" in embed_info:
+            from src.models.embed import select_embedding_model
+            return select_embedding_model(embed_info["model_id"])
+
+        # 使用原有的逻辑（兼容模式））
         config_dict = get_embedding_config(embed_info)
-        embedding_model = OtherEmbedding(
+        return OtherEmbedding(
             model=config_dict.get("model"),
             base_url=config_dict.get("base_url"),
             api_key=config_dict.get("api_key"),
         )
 
+    def _get_async_embedding_function(self, embed_info: dict):
+        """获取 embedding 函数"""
+        embedding_model = self._get_async_embedding(embed_info)
         return partial(embedding_model.abatch_encode, batch_size=40)
 
     def _get_embedding_function(self, embed_info: dict):
         """获取 embedding 函数"""
-        config_dict = get_embedding_config(embed_info)
+        embedding_model = self._get_async_embedding(embed_info)
-        embedding_model = OtherEmbedding(
-            model=config_dict.get("model"),
-            base_url=config_dict.get("base_url"),
-            api_key=config_dict.get("api_key"),
-        )
 
         return partial(embedding_model.batch_encode, batch_size=40)
 

src/knowledge/manager.py

@@ -246,16 +246,12 @@ class KnowledgeBaseManager:
         db_id = db_info["db_id"]
 
         async with self._metadata_lock:
-            # 准备 additional_params，包含 auto_generate_questions
-            saved_params = kwargs.copy()
-            saved_params["auto_generate_questions"] = False
-
             self.global_databases_meta[db_id] = {
                 "name": database_name,
                 "description": description,
                 "kb_type": kb_type,
                 "created_at": utc_isoformat(),
-                "additional_params": saved_params,
+                "additional_params": kwargs.copy(),
             }
             self._save_global_metadata()
 

src/knowledge/utils/kb_utils.py

@@ -247,15 +247,23 @@ def get_embedding_config(embed_info: dict) -> dict:
 
     try:
         if embed_info:
-            # 处理 embed_info 可能是字典或 EmbedModelInfo 对象的情况
+            # 优先检查是否有 model_id 字段
-            if hasattr(embed_info, "name"):
+            if "model_id" in embed_info:
+                from src.models.embed import select_embedding_model
+
+                model = select_embedding_model(embed_info["model_id"])
+                config_dict["model"] = model.model
+                config_dict["api_key"] = model.api_key
+                config_dict["base_url"] = model.base_url
+                config_dict["dimension"] = getattr(model, "dimension", 1024)
+            elif hasattr(embed_info, "name"):
                 # EmbedModelInfo 对象
                 config_dict["model"] = embed_info.name
                 config_dict["api_key"] = os.getenv(embed_info.api_key) or embed_info.api_key
                 config_dict["base_url"] = embed_info.base_url
                 config_dict["dimension"] = embed_info.dimension
             else:
-                # 字典形式
+                # 字典形式（保持向后兼容）
                 config_dict["model"] = embed_info["name"]
                 config_dict["api_key"] = os.getenv(embed_info["api_key"]) or embed_info["api_key"]
                 config_dict["base_url"] = embed_info["base_url"]

src/models/embed.py

@@ -11,7 +11,7 @@ from src.utils import get_docker_safe_url, hashstr, logger
 
 
 class BaseEmbeddingModel(ABC):
-    def __init__(self, model=None, name=None, dimension=None, url=None, base_url=None, api_key=None):
+    def __init__(self, model=None, name=None, dimension=None, url=None, base_url=None, api_key=None, model_id=None):
         """
         Args:
             model: 模型名称，冗余设计，同name
@@ -140,6 +140,7 @@ class OllamaEmbedding(BaseEmbeddingModel):
         payload = {"model": self.model, "input": message}
         async with httpx.AsyncClient() as client:
             try:
+                print(f"\n\n\nOllama Embedding request: {payload}\n\n\n")
                 response = await client.post(self.base_url, json=payload, timeout=60)
                 response.raise_for_status()
                 result = response.json()

web/src/views/DataBaseView.vue

@@ -14,15 +14,23 @@
       <h3>知识库类型<span style="color: var(--color-error-500)">*</span></h3>
       <div class="kb-type-cards">
         <div
-          v-for="(typeInfo, typeKey) in supportedKbTypes"
+          v-for="(typeInfo, typeKey) in orderedKbTypes"
           :key="typeKey"
           class="kb-type-card"
           :class="{ active: newDatabase.kb_type === typeKey }"
+          :data-type="typeKey"
           @click="handleKbTypeChange(typeKey)"
         >
           <div class="card-header">
             <component :is="getKbTypeIcon(typeKey)" class="type-icon" />
             <span class="type-title">{{ getKbTypeLabel(typeKey) }}</span>
+            <a-tooltip
+              v-if="typeKey === 'chroma'"
+              title="Chroma 已标记为弃用状态，建议使用 Milvus 替代。同时会在下个正式版本中移除。"
+              placement="top"
+            >
+              <span class="deprecated-badge">弃用</span>
+            </a-tooltip>
           </div>
           <div class="card-description">{{ typeInfo.description }}</div>
         </div>
@@ -71,7 +79,7 @@
       <a-textarea
         v-model:value="newDatabase.description"
         placeholder="新建知识库描述"
-        :auto-size="{ minRows: 5, maxRows: 10 }"
+        :auto-size="{ minRows: 3, maxRows: 10 }"
       />
 
       <h3 style="margin-top: 20px;">隐私设置</h3>
@@ -158,6 +166,18 @@
       <p>正在加载知识库...</p>
     </div>
 
+    <!-- 空状态显示 -->
+    <div v-else-if="!databases || databases.length === 0" class="empty-state">
+      <h3 class="empty-title">暂无知识库</h3>
+      <p class="empty-description">创建您的第一个知识库，开始管理文档和知识</p>
+      <a-button type="primary" size="large" @click="state.openNewDatabaseModel = true">
+        <template #icon>
+          <PlusOutlined />
+        </template>
+        创建知识库
+      </a-button>
+    </div>
+
     <!-- 数据库列表 -->
     <div v-else class="databases">
       <div
@@ -213,7 +233,7 @@ import { useRouter, useRoute } from 'vue-router';
 import { useConfigStore } from '@/stores/config';
 import { message } from 'ant-design-vue'
 import { Database, Zap, FileDigit,  Waypoints, Building2 } from 'lucide-vue-next';
-import { LockOutlined, InfoCircleOutlined, QuestionCircleOutlined } from '@ant-design/icons-vue';
+import { LockOutlined, InfoCircleOutlined, QuestionCircleOutlined, PlusOutlined } from '@ant-design/icons-vue';
 import { databaseApi, typeApi } from '@/apis/knowledge_api';
 import HeaderComponent from '@/components/HeaderComponent.vue';
 import ModelSelectorComponent from '@/components/ModelSelectorComponent.vue';
@@ -256,7 +276,7 @@ const createEmptyDatabaseForm = () => ({
   name: '',
   description: '',
   embed_model_name: configStore.config?.embed_model,
-  kb_type: 'chroma',
+  kb_type: 'milvus',
   is_private: false,
   storage: '',
   language: 'English',
@@ -295,6 +315,27 @@ const llmModelSpec = computed(() => {
 // 支持的知识库类型
 const supportedKbTypes = ref({})
 
+// 有序的知识库类型（Chroma 排在最后）
+const orderedKbTypes = computed(() => {
+  const types = { ...supportedKbTypes.value }
+  const ordered = {}
+  const chromaData = types.chroma
+
+  // 先添加除了 Chroma 之外的所有类型
+  Object.keys(types).forEach(key => {
+    if (key !== 'chroma') {
+      ordered[key] = types[key]
+    }
+  })
+
+  // 最后添加 Chroma（如果存在）
+  if (chromaData) {
+    ordered.chroma = chromaData
+  }
+
+  return ordered
+})
+
 // 加载支持的知识库类型
 const loadSupportedKbTypes = async () => {
   try {
@@ -368,24 +409,6 @@ const getKbTypeIcon = (type) => {
   return icons[type] || Database
 }
 
-// const getKbTypeDescription = (type) => {
-//   const descriptions = {
-//     lightrag: '🔥 图结构索引 • 智能查询 • 关系挖掘 • 复杂推理',
-//     chroma: '⚡ 轻量向量 • 快速开发 • 本地部署 • 简单易用',
-//     milvus: '🚀 生产级 • 高性能 • 分布式 • 企业级部署'
-//   }
-//   return descriptions[type] || ''
-// }
-
-const getKbTypeAlertType = (type) => {
-  const types = {
-    lightrag: 'info',
-    chroma: 'success',
-    milvus: 'warning'
-  }
-  return types[type] || 'info'
-}
-
 const getKbTypeColor = (type) => {
   const colors = {
     lightrag: 'purple',
@@ -395,7 +418,6 @@ const getKbTypeColor = (type) => {
   return colors[type] || 'blue'
 }
 
-
 // 格式化创建时间
 const formatCreatedTime = (createdAt) => {
   if (!createdAt) return ''
@@ -680,24 +702,12 @@ onMounted(() => {
         border-color: var(--main-color);
       }
 
-      // 为不同知识库类型设置不同的悬停颜色与主题色
+      &.active {
-      &:nth-child(1):hover,
+        border-color: var(--main-color);
-      &:nth-child(1).active {
+        background: var(--main-10);
-        border-color: var(--color-accent-100);
+        .type-icon { color: var(--main-color); }
-        .type-icon { color: var(--color-accent-500); }
       }
 
-      &:nth-child(2):hover,
-      &:nth-child(2).active {
-        border-color: var(--color-warning-100);
-        .type-icon { color: var(--color-warning-500); }
-      }
-
-      &:nth-child(3):hover,
-      &:nth-child(3).active {
-        border-color: var(--color-error-100);
-        .type-icon { color: var(--color-error-500); }
-      }
       .card-header {
         display: flex;
         align-items: center;
@@ -725,6 +735,26 @@ onMounted(() => {
         margin-bottom: 0;
         // min-height: 40px;
       }
+
+      .deprecated-badge {
+        background: var(--color-error-100);
+        color: var(--color-error-600);
+        font-size: 10px;
+        font-weight: 600;
+        padding: 2px 6px;
+        border-radius: 4px;
+        margin-left: auto;
+        text-transform: uppercase;
+        letter-spacing: 0.5px;
+        cursor: help;
+        transition: all 0.2s ease;
+
+        &:hover {
+          background: var(--color-error-200);
+          color: var(--color-error-700);
+        }
+      }
+
     }
   }
 
@@ -900,8 +930,6 @@ onMounted(() => {
     font-weight: 400;
     flex: 1;
   }
-
-
 }
 
 .database-empty {
@@ -913,6 +941,38 @@ onMounted(() => {
   color: var(--gray-900);
 }
 
+.empty-state {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  justify-content: center;
+  padding: 100px 20px;
+  text-align: center;
+
+  .empty-title {
+    font-size: 20px;
+    font-weight: 600;
+    color: var(--gray-900);
+    margin: 0 0 12px 0;
+    letter-spacing: -0.02em;
+  }
+
+  .empty-description {
+    font-size: 14px;
+    color: var(--gray-600);
+    margin: 0 0 32px 0;
+    line-height: 1.5;
+    max-width: 320px;
+  }
+
+  .ant-btn {
+    height: 44px;
+    padding: 0 24px;
+    font-size: 15px;
+    font-weight: 500;
+  }
+}
+
 .database-container {
   padding: 0;
 }