chore: update version to v1.3.1

api/routes/processors.py

@@ -3,6 +3,8 @@ from fastapi import APIRouter, Depends, Body, HTTPException
 from fastapi.concurrency import run_in_threadpool
 from typing import Annotated
 from services.processors.registry import (
+    get,
+    get_config_schema,
     get_config_schemas,
     get_module_path,
     reload_processors,
@@ -11,7 +13,8 @@ from services.task_queue import task_queue_service
 from services.auth import get_current_active_user, User
 from api.response import success
 from pydantic import BaseModel
-from services.virtual_fs import path_is_directory
+from services.virtual_fs import path_is_directory, resolve_adapter_and_rel
+from typing import List, Optional, Tuple
 
 router = APIRouter(prefix="/api/processors", tags=["processors"])
 
@@ -42,6 +45,15 @@ class ProcessRequest(BaseModel):
     overwrite: bool = False
 
 
+class ProcessDirectoryRequest(BaseModel):
+    path: str
+    processor_type: str
+    config: dict
+    overwrite: bool = True
+    max_depth: Optional[int] = None
+    suffix: Optional[str] = None
+
+
 class UpdateSourceRequest(BaseModel):
     source: str
 
@@ -69,6 +81,128 @@ async def process_file_with_processor(
     return success({"task_id": task.id})
 
 
+@router.post("/process-directory")
+async def process_directory_with_processor(
+    current_user: Annotated[User, Depends(get_current_active_user)],
+    req: ProcessDirectoryRequest = Body(...)
+):
+    if req.max_depth is not None and req.max_depth < 0:
+        raise HTTPException(400, detail="max_depth must be >= 0")
+
+    is_dir = await path_is_directory(req.path)
+    if not is_dir:
+        raise HTTPException(400, detail="Path must be a directory")
+
+    schema = get_config_schema(req.processor_type)
+    _processor = get(req.processor_type)
+    if not schema or not _processor:
+        raise HTTPException(404, detail="Processor not found")
+
+    produces_file = bool(schema.get("produces_file"))
+    raw_suffix = req.suffix if req.suffix is not None else None
+    if raw_suffix is not None and raw_suffix.strip() == "":
+        raw_suffix = None
+    suffix = raw_suffix
+    overwrite = req.overwrite
+
+    if produces_file:
+        if not overwrite and not suffix:
+            raise HTTPException(400, detail="Suffix is required when not overwriting files")
+    else:
+        overwrite = False
+        suffix = None
+
+    supported_exts = schema.get("supported_exts") or []
+    allowed_exts = {
+        ext.lower().lstrip('.')
+        for ext in supported_exts
+        if isinstance(ext, str)
+    }
+
+    def matches_extension(file_rel: str) -> bool:
+        if not allowed_exts:
+            return True
+        if '.' not in file_rel:
+            return '' in allowed_exts
+        ext = file_rel.rsplit('.', 1)[-1].lower()
+        return ext in allowed_exts or f'.{ext}' in allowed_exts
+
+    adapter_instance, adapter_model, root, rel = await resolve_adapter_and_rel(req.path)
+    rel = rel.rstrip('/')
+
+    list_dir = getattr(adapter_instance, "list_dir", None)
+    if not callable(list_dir):
+        raise HTTPException(501, detail="Adapter does not implement list_dir")
+
+    def build_absolute_path(mount_path: str, rel_path: str) -> str:
+        rel_norm = rel_path.lstrip('/')
+        mount_norm = mount_path.rstrip('/')
+        if not mount_norm:
+            return '/' + rel_norm if rel_norm else '/'
+        return f"{mount_norm}/{rel_norm}" if rel_norm else mount_norm
+
+    def apply_suffix(path_str: str, suffix_str: str) -> str:
+        path_obj = Path(path_str)
+        name = path_obj.name
+        if not name:
+            return path_str
+        if '.' in name:
+            base, ext = name.rsplit('.', 1)
+            new_name = f"{base}{suffix_str}.{ext}"
+        else:
+            new_name = f"{name}{suffix_str}"
+        return str(path_obj.with_name(new_name))
+
+    scheduled_tasks: List[str] = []
+    stack: List[Tuple[str, int]] = [(rel, 0)]
+    page_size = 200
+
+    while stack:
+        current_rel, depth = stack.pop()
+        page = 1
+        while True:
+            entries, total = await list_dir(root, current_rel, page, page_size, "name", "asc")
+            entries = entries or []
+            if not entries and (total or 0) == 0:
+                break
+
+            for entry in entries:
+                name = entry.get("name")
+                if not name:
+                    continue
+                child_rel = f"{current_rel}/{name}" if current_rel else name
+                if entry.get("is_dir"):
+                    if req.max_depth is None or depth < req.max_depth:
+                        stack.append((child_rel.rstrip('/'), depth + 1))
+                    continue
+                if not matches_extension(child_rel):
+                    continue
+                absolute_path = build_absolute_path(adapter_model.path, child_rel)
+                save_to = None
+                if produces_file and not overwrite and suffix:
+                    save_to = apply_suffix(absolute_path, suffix)
+                task = await task_queue_service.add_task(
+                    "process_file",
+                    {
+                        "path": absolute_path,
+                        "processor_type": req.processor_type,
+                        "config": req.config,
+                        "save_to": save_to,
+                        "overwrite": overwrite,
+                    },
+                )
+                scheduled_tasks.append(task.id)
+
+            if total is None or page * page_size >= total:
+                break
+            page += 1
+
+    return success({
+        "task_ids": scheduled_tasks,
+        "scheduled": len(scheduled_tasks),
+    })
+
+
 @router.get("/source/{processor_type}")
 async def get_processor_source(
     processor_type: str,

api/routes/search.py

@@ -1,4 +1,7 @@
+from typing import Any, Dict, List, Tuple
+
 from fastapi import APIRouter, Depends, Query
+
 from schemas.fs import SearchResultItem
 from services.auth import get_current_active_user, User
 from services.ai import get_text_embedding
@@ -6,24 +9,96 @@ from services.vector_db import VectorDBService
 
 router = APIRouter(prefix="/api/search", tags=["search"])
 
-async def search_files_by_vector(q: str, top_k: int):
-    embedding = await get_text_embedding(q)
-    vector_db = VectorDBService()
-    results = await vector_db.search_vectors("vector_collection", embedding, top_k)
-    items = [
-        SearchResultItem(id=res["id"], path=res["entity"]["path"], score=res["distance"])
-        for res in results[0]
-    ]
-    return {"items": items, "query": q}
 
-async def search_files_by_name(q: str, top_k: int):
+def _normalize_result(raw: Dict[str, Any], source: str, fallback_score: float = 0.0) -> SearchResultItem:
+    entity = dict(raw.get("entity") or {})
+    source_path = entity.get("source_path")
+    stored_path = entity.get("path")
+    path = source_path or stored_path or ""
+    chunk_id_value = entity.get("chunk_id")
+    chunk_id = str(chunk_id_value) if chunk_id_value is not None else None
+    snippet = entity.get("text") or entity.get("description") or entity.get("name")
+    mime = entity.get("mime")
+    start_offset = entity.get("start_offset")
+    end_offset = entity.get("end_offset")
+    raw_score = raw.get("distance")
+    score = float(raw_score) if raw_score is not None else fallback_score
+
+    metadata = {
+        "retrieval_source": source,
+        "raw_distance": raw_score,
+    }
+    if stored_path and stored_path != path:
+        metadata["stored_path"] = stored_path
+    vector_id = entity.get("vector_id")
+    if vector_id:
+        metadata["vector_id"] = vector_id
+
+    return SearchResultItem(
+        id=str(raw.get("id")),
+        path=path,
+        score=score,
+        chunk_id=chunk_id,
+        snippet=snippet,
+        mime=mime,
+        source_type=entity.get("type") or source,
+        start_offset=start_offset,
+        end_offset=end_offset,
+        metadata=metadata,
+    )
+
+
+async def _vector_search(query: str, top_k: int) -> List[SearchResultItem]:
     vector_db = VectorDBService()
-    results = await vector_db.search_by_path("vector_collection", q, top_k)
-    items = [
-        SearchResultItem(id=idx, path=res["entity"]["path"], score=res["distance"])
-        for idx, res in enumerate(results[0])
-    ]
-    return {"items": items, "query": q}
+    try:
+        embedding = await get_text_embedding(query)
+    except Exception:
+        embedding = None
+    if not embedding:
+        return []
+
+    try:
+        raw_results = await vector_db.search_vectors("vector_collection", embedding, max(top_k, 10))
+    except Exception:
+        return []
+
+    results: List[SearchResultItem] = []
+    for bucket in raw_results or []:
+        for record in bucket or []:
+            results.append(_normalize_result(record, "vector"))
+    return results
+
+
+async def _filename_search(query: str, page: int, page_size: int) -> Tuple[List[SearchResultItem], bool]:
+    vector_db = VectorDBService()
+    limit = max(page * page_size + 1, page_size * (page + 2))
+    limit = min(limit, 2000)
+    try:
+        raw_results = await vector_db.search_by_path("vector_collection", query, limit)
+    except Exception:
+        return [], False
+
+    records = raw_results[0] if raw_results else []
+    deduped: List[SearchResultItem] = []
+    seen_paths: set[str] = set()
+    for record in records or []:
+        item = _normalize_result(record, "filename", fallback_score=1.0)
+        stored_path = item.metadata.get("stored_path") if item.metadata else None
+        key = item.path or stored_path or ""
+        if key in seen_paths:
+            continue
+        seen_paths.add(key)
+        deduped.append(item)
+
+    start = max(page - 1, 0) * page_size
+    end = start + page_size
+    page_items = deduped[start:end]
+    for offset, item in enumerate(page_items):
+        if item.metadata is None:
+            item.metadata = {}
+        item.metadata.setdefault("retrieval_rank", start + offset)
+    has_more = len(deduped) > end
+    return page_items, has_more
 
 
 @router.get("")
@@ -31,11 +106,32 @@ async def search_files(
     q: str = Query(..., description="搜索查询"),
     top_k: int = Query(10, description="返回结果数量"),
     mode: str = Query("vector", description="搜索模式: 'vector' 或 'filename'"),
+    page: int = Query(1, description="分页页码，仅在文件名搜索模式下生效"),
+    page_size: int = Query(10, description="分页大小，仅在文件名搜索模式下生效"),
     user: User = Depends(get_current_active_user),
 ):
+    if not q.strip():
+        return {"items": [], "query": q}
+
+    top_k = max(top_k, 1)
+    page = max(page, 1)
+    page_size = max(min(page_size, 100), 1)
+
     if mode == "vector":
-        return await search_files_by_vector(q, top_k)
+        items = (await _vector_search(q, top_k))[:top_k]
     elif mode == "filename":
-        return await search_files_by_name(q, top_k)
+        items, has_more = await _filename_search(q, page, page_size)
+        return {
+            "items": items,
+            "query": q,
+            "mode": mode,
+            "pagination": {
+                "page": page,
+                "page_size": page_size,
+                "has_more": has_more,
+            },
+        }
     else:
-        return {"items": [], "query": q, "error": "Invalid search mode"}
+        items = (await _vector_search(q, top_k))[:top_k]
+
+    return {"items": items, "query": q, "mode": mode}

api/routes/vector_db.py

@@ -24,8 +24,6 @@ class VectorDBConfigPayload(BaseModel):
 
 @router.post("/clear-all", summary="清空向量数据库")
 async def clear_vector_db(user: UserAccount = Depends(get_current_active_user)):
-    if user.username != 'admin':
-        raise HTTPException(status_code=403, detail="仅管理员可操作")
     try:
         service = VectorDBService()
         await service.clear_all_data()
@@ -36,8 +34,6 @@ async def clear_vector_db(user: UserAccount = Depends(get_current_active_user)):
 
 @router.get("/stats", summary="获取向量数据库统计")
 async def get_vector_db_stats(user: UserAccount = Depends(get_current_active_user)):
-    if user.username != 'admin':
-        raise HTTPException(status_code=403, detail="仅管理员可操作")
     try:
         service = VectorDBService()
         data = await service.get_all_stats()
@@ -48,15 +44,11 @@ async def get_vector_db_stats(user: UserAccount = Depends(get_current_active_use
 
 @router.get("/providers", summary="列出可用向量数据库提供者")
 async def list_vector_providers(user: UserAccount = Depends(get_current_active_user)):
-    if user.username != 'admin':
-        raise HTTPException(status_code=403, detail="仅管理员可操作")
     return success(list_providers())
 
 
 @router.get("/config", summary="获取当前向量数据库配置")
 async def get_vector_db_config(user: UserAccount = Depends(get_current_active_user)):
-    if user.username != 'admin':
-        raise HTTPException(status_code=403, detail="仅管理员可操作")
     service = VectorDBService()
     data = await service.current_provider()
     return success(data)
@@ -64,18 +56,17 @@ async def get_vector_db_config(user: UserAccount = Depends(get_current_active_us
 
 @router.post("/config", summary="更新向量数据库配置")
 async def update_vector_db_config(payload: VectorDBConfigPayload, user: UserAccount = Depends(get_current_active_user)):
-    if user.username != 'admin':
-        raise HTTPException(status_code=403, detail="仅管理员可操作")
-
     entry = get_provider_entry(payload.type)
     if not entry:
-        raise HTTPException(status_code=400, detail=f"未知的向量数据库类型: {payload.type}")
+        raise HTTPException(
+            status_code=400, detail=f"未知的向量数据库类型: {payload.type}")
     if not entry.get("enabled", True):
         raise HTTPException(status_code=400, detail="该向量数据库类型暂不可用")
 
     provider_cls = get_provider_class(payload.type)
     if not provider_cls:
-        raise HTTPException(status_code=400, detail=f"未找到类型 {payload.type} 对应的实现")
+        raise HTTPException(
+            status_code=400, detail=f"未找到类型 {payload.type} 对应的实现")
 
     # 先尝试建立连接，确保配置有效
     test_provider = provider_cls(payload.config)

api/routes/virtual_fs.py

@@ -15,6 +15,7 @@ from services.virtual_fs import (
     stream_file,
     generate_temp_link_token,
     verify_temp_link_token,
+    maybe_redirect_download,
 )
 from services.thumbnail import is_image_filename, get_or_create_thumb, is_raw_filename
 from schemas import MkdirRequest, MoveRequest
@@ -50,6 +51,12 @@ async def get_file(
         except Exception as e:
             raise HTTPException(500, detail=f"RAW file processing failed: {e}")
 
+    adapter_instance, adapter_model, root, rel = await resolve_adapter_and_rel(full_path)
+
+    redirect_response = await maybe_redirect_download(adapter_instance, adapter_model, root, rel)
+    if redirect_response is not None:
+        return redirect_response
+
     try:
         content = await read_file(full_path)
     except FileNotFoundError:

entrypoint.sh

@@ -2,4 +2,4 @@
 set -e
 python migrate/run.py
 nginx -g 'daemon off;' &
-exec gunicorn -k uvicorn.workers.UvicornWorker -w 2 -b 0.0.0.0:8000 main:app
+exec gunicorn -k uvicorn.workers.UvicornWorker -w 1 -b 0.0.0.0:8000 main:app

schemas/fs.py

@@ -21,6 +21,13 @@ class SearchResultItem(BaseModel):
     id: int | str
     path: str
     score: float
+    chunk_id: Optional[str] = None
+    snippet: Optional[str] = None
+    mime: Optional[str] = None
+    source_type: Optional[str] = None
+    start_offset: Optional[int] = None
+    end_offset: Optional[int] = None
+    metadata: Optional[dict] = None
 
 
 class MkdirRequest(BaseModel):

services/adapters/onedrive.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 from datetime import datetime, timezone, timedelta
 from typing import List, Dict, Tuple, AsyncIterator
 import httpx
-from fastapi.responses import StreamingResponse
+from fastapi.responses import StreamingResponse, Response
 from fastapi import HTTPException
 from models import StorageAdapter
 
@@ -20,6 +20,7 @@ class OneDriveAdapter:
         self.client_secret = cfg.get("client_secret")
         self.refresh_token = cfg.get("refresh_token")
         self.root = cfg.get("root", "/").strip("/")
+        self.enable_redirect_307 = bool(cfg.get("enable_direct_download_307"))
 
         if not all([self.client_id, self.client_secret, self.refresh_token]):
             raise ValueError(
@@ -380,6 +381,26 @@ class OneDriveAdapter:
 
         return StreamingResponse(file_iterator(), status_code=status, headers=headers, media_type=content_type)
 
+    async def get_direct_download_response(self, root: str, rel: str):
+        if not self.enable_redirect_307:
+            return None
+
+        api_path = self._get_api_path(rel)
+        if not api_path:
+            raise IsADirectoryError("不能对目录进行直链重定向")
+
+        resp = await self._request("GET", api_path_segment=api_path)
+        if resp.status_code == 404:
+            raise FileNotFoundError(rel)
+        resp.raise_for_status()
+
+        item_data = resp.json()
+        download_url = item_data.get("@microsoft.graph.downloadUrl")
+        if not download_url:
+            return None
+
+        return Response(status_code=307, headers={"Location": download_url})
+
     async def get_thumbnail(self, root: str, rel: str, size: str = "medium"):
         """
         获取文件的缩略图。
@@ -434,6 +455,7 @@ CONFIG_SCHEMA = [
         "required": True, "help_text": "可以通过运行 'python -m services.adapters.onedrive' 获取"},
     {"key": "root", "label": "根目录 (Root Path)", "type": "string",
      "required": False, "placeholder": "默认为根目录 /"},
+    {"key": "enable_direct_download_307", "label": "Enable 307 redirect download", "type": "boolean", "default": False},
 ]
 
 

services/adapters/quark.py

@@ -34,8 +34,15 @@ class QuarkAdapter:
         cfg = record.config or {}
         self.cookie: str = cfg.get("cookie") or cfg.get("Cookie")
         self.root_fid: str = cfg.get("root_fid", "0")
-        self.use_transcoding_address: bool = bool(cfg.get("use_transcoding_address", False))
-        self.only_list_video_file: bool = bool(cfg.get("only_list_video_file", False))
+        def _as_bool(value: Any) -> bool:
+            if isinstance(value, bool):
+                return value
+            if isinstance(value, str):
+                return value.strip().lower() in {"1", "true", "yes", "on"}
+            return bool(value)
+
+        self.use_transcoding_address: bool = _as_bool(cfg.get("use_transcoding_address", False))
+        self.only_list_video_file: bool = _as_bool(cfg.get("only_list_video_file", False))
 
         if not self.cookie:
             raise ValueError("Quark 适配器需要 cookie 配置")
@@ -716,8 +723,8 @@ ADAPTER_TYPE = "Quark"
 CONFIG_SCHEMA = [
     {"key": "cookie", "label": "Cookie", "type": "password", "required": True, "placeholder": "从 pan.quark.cn 复制"},
     {"key": "root_fid", "label": "根 FID", "type": "string", "required": False, "default": "0"},
-    {"key": "use_transcoding_address", "label": "视频转码直链", "type": "checkbox", "required": False, "default": False},
-    {"key": "only_list_video_file", "label": "仅列出视频文件", "type": "checkbox", "required": False, "default": False},
+    {"key": "use_transcoding_address", "label": "视频转码直链", "type": "boolean", "required": False, "default": False},
+    {"key": "only_list_video_file", "label": "仅列出视频文件", "type": "boolean", "required": False, "default": False},
 ]
 
 def ADAPTER_FACTORY(rec: StorageAdapter) -> BaseAdapter:

services/adapters/telegram.py

@@ -74,33 +74,32 @@ class TelegramAdapter:
             for message in messages:
                 if not message:
                     continue
-                
+
                 media = message.document or message.video or message.photo
                 if not media:
                     continue
 
-                filename = None
-                size = 0
-                
-                if message.photo:
-                    photo_size = message.photo.sizes[-1]
-                    size = photo_size.size if hasattr(photo_size, 'size') else 0
-                    filename = f"photo_{message.id}.jpg"
+                file_meta = message.file
+                if not file_meta:
+                    continue
 
-                elif message.document or message.video:
-                    size = media.size
-                    if hasattr(media, 'attributes'):
-                        for attr in media.attributes:
-                            if hasattr(attr, 'file_name') and attr.file_name:
-                                filename = attr.file_name
-                                break
-                
+                filename = file_meta.name
                 if not filename:
                     if message.text and '.' in message.text and len(message.text) < 256 and '\n' not in message.text:
                         filename = message.text
-                
-                if not filename:
-                    filename = f"unknown_{message.id}"
+                    else:
+                        filename = f"unknown_{message.id}"
+
+                size = file_meta.size
+                if size is None:
+                    # 兼容缺失 size 的情况
+                    if hasattr(media, "size") and media.size is not None:
+                        size = media.size
+                    elif message.photo and getattr(message.photo, "sizes", None):
+                        photo_size = message.photo.sizes[-1]
+                        size = getattr(photo_size, "size", 0) or 0
+                    else:
+                        size = 0
 
                 entries.append({
                     "name": f"{message.id}_{filename}",
@@ -246,13 +245,27 @@ class TelegramAdapter:
             if not message or not media:
                 raise FileNotFoundError(f"在频道 {self.chat_id} 中未找到消息ID为 {message_id} 的文件")
 
-            if message.photo:
-                photo_size = media.sizes[-1]
-                file_size = photo_size.size if hasattr(photo_size, 'size') else 0
-                mime_type = "image/jpeg"
-            else:
-                file_size = media.size
-                mime_type = media.mime_type or "application/octet-stream"
+            file_meta = message.file
+            file_size = file_meta.size if file_meta and file_meta.size is not None else None
+            if file_size is None:
+                if hasattr(media, "size") and media.size is not None:
+                    file_size = media.size
+                elif message.photo and getattr(message.photo, "sizes", None):
+                    photo_size = message.photo.sizes[-1]
+                    file_size = getattr(photo_size, "size", 0) or 0
+                else:
+                    file_size = 0
+
+            mime_type = None
+            if file_meta and getattr(file_meta, "mime_type", None):
+                mime_type = file_meta.mime_type
+            if not mime_type:
+                if hasattr(media, "mime_type") and media.mime_type:
+                    mime_type = media.mime_type
+                elif message.photo:
+                    mime_type = "image/jpeg"
+                else:
+                    mime_type = "application/octet-stream"
 
             start = 0
             end = file_size - 1
@@ -321,11 +334,16 @@ class TelegramAdapter:
             if not message or not media:
                 raise FileNotFoundError(f"在频道 {self.chat_id} 中未找到消息ID为 {message_id} 的文件")
 
-            if message.photo:
-                photo_size = media.sizes[-1]
-                size = photo_size.size if hasattr(photo_size, 'size') else 0
-            else:
-                size = media.size
+            file_meta = message.file
+            size = file_meta.size if file_meta and file_meta.size is not None else None
+            if size is None:
+                if hasattr(media, "size") and media.size is not None:
+                    size = media.size
+                elif message.photo and getattr(message.photo, "sizes", None):
+                    photo_size = message.photo.sizes[-1]
+                    size = getattr(photo_size, "size", 0) or 0
+                else:
+                    size = 0
 
             return {
                 "name": rel,
@@ -339,4 +357,4 @@ class TelegramAdapter:
                 await client.disconnect()
 
 def ADAPTER_FACTORY(rec: StorageAdapter) -> TelegramAdapter:
-    return TelegramAdapter(rec)
+    return TelegramAdapter(rec)

services/ai.py

@@ -68,3 +68,46 @@ async def get_text_embedding(text: str) -> List[float]:
         resp.raise_for_status()
         result = resp.json()
         return result["data"][0]["embedding"]
+
+
+async def rerank_texts(query: str, documents: List[str]) -> List[float]:
+    """调用重排序模型，为一组文档返回得分。未配置时返回空列表。"""
+    if not documents:
+        return []
+
+    api_url = await ConfigCenter.get("AI_RERANK_API_URL")
+    model = await ConfigCenter.get("AI_RERANK_MODEL")
+    api_key = await ConfigCenter.get("AI_RERANK_API_KEY")
+
+    if not api_url or not model or not api_key:
+        return []
+
+    payload = {
+        "model": model,
+        "query": query,
+        "documents": documents,
+    }
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json",
+    }
+
+    async with httpx.AsyncClient() as client:
+        try:
+            resp = await client.post(api_url, headers=headers, json=payload)
+            resp.raise_for_status()
+        except httpx.HTTPStatusError:
+            return []
+        data = resp.json()
+        if isinstance(data, dict):
+            results = data.get("results")
+            if isinstance(results, list):
+                scores = []
+                for item in results:
+                    if isinstance(item, dict) and "score" in item:
+                        try:
+                            scores.append(float(item["score"]))
+                        except (TypeError, ValueError):
+                            scores.append(0.0)
+                return scores
+        return []

services/config.py

@@ -4,7 +4,7 @@ from typing import Any, Optional, Dict
 from dotenv import load_dotenv
 from models.database import Configuration
 load_dotenv(dotenv_path=".env")
-VERSION = "v1.2.10"
+VERSION = "v1.3.1"
 
 class ConfigCenter:
     _cache: Dict[str, Any] = {}

services/processors/vector_index.py

@@ -1,15 +1,99 @@
-from typing import Dict, Any
+from typing import Dict, Any, List, Tuple
 from fastapi.responses import Response
 import base64
+import mimetypes
+import os
+from io import BytesIO
+
 from services.ai import describe_image_base64, get_text_embedding
 from services.vector_db import VectorDBService, DEFAULT_VECTOR_DIMENSION
 from services.logging import LogService
 from services.config import ConfigCenter
 
+try:  # Pillow is optional but bundled with the project dependencies
+    from PIL import Image
+except ImportError:  # pragma: no cover - fallback when pillow missing
+    Image = None
+
+
+CHUNK_SIZE = 800
+CHUNK_OVERLAP = 200
+MAX_IMAGE_EDGE = 1600
+JPEG_QUALITY = 85
+
+
+def _chunk_text(content: str, chunk_size: int = CHUNK_SIZE, overlap: int = CHUNK_OVERLAP) -> List[Tuple[int, str, int, int]]:
+    """按固定窗口拆分文本，返回(chunk_id, chunk_text, start, end)。"""
+    if chunk_size <= 0:
+        chunk_size = CHUNK_SIZE
+    if overlap >= chunk_size:
+        overlap = max(chunk_size // 4, 1)
+
+    chunks: List[Tuple[int, str, int, int]] = []
+    step = chunk_size - overlap
+    idx = 0
+    start = 0
+    length = len(content)
+
+    while start < length:
+        end = min(length, start + chunk_size)
+        chunk = content[start:end].strip()
+        if chunk:
+            chunks.append((idx, chunk, start, end))
+            idx += 1
+        if end >= length:
+            break
+        start += step
+    return chunks
+
+
+def _guess_mime(path: str) -> str:
+    mime, _ = mimetypes.guess_type(path)
+    return mime or "application/octet-stream"
+
+
+def _chunk_key(path: str, chunk_id: str) -> str:
+    return f"{path}#chunk={chunk_id}"
+
+
+def _compress_image_for_embedding(input_bytes: bytes) -> Tuple[bytes, Dict[str, Any] | None]:
+    """压缩图片，降低发送到视觉模型的体积。"""
+    if Image is None:
+        return input_bytes, None
+
+    try:
+        with Image.open(BytesIO(input_bytes)) as img:
+            img = img.convert("RGB")
+            width, height = img.size
+            longest_edge = max(width, height)
+            scale = 1.0
+            if longest_edge > MAX_IMAGE_EDGE:
+                scale = MAX_IMAGE_EDGE / float(longest_edge)
+                new_size = (max(int(width * scale), 1), max(int(height * scale), 1))
+                resample_mode = getattr(getattr(Image, "Resampling", Image), "LANCZOS")
+                img = img.resize(new_size, resample=resample_mode)
+
+            buffer = BytesIO()
+            img.save(buffer, format="JPEG", quality=JPEG_QUALITY, optimize=True)
+            compressed = buffer.getvalue()
+
+            if len(compressed) < len(input_bytes):
+                return compressed, {
+                    "original_bytes": len(input_bytes),
+                    "compressed_bytes": len(compressed),
+                    "scaled": scale < 1.0,
+                    "width": img.width,
+                    "height": img.height,
+                }
+    except Exception:  # pragma: no cover - 任意图像处理异常时回退
+        return input_bytes, None
+
+    return input_bytes, None
+
 
 class VectorIndexProcessor:
     name = "向量索引"
-    supported_exts = ["jpg", "jpeg", "png", "bmp", "txt", "md"]
+    supported_exts: List[str] = []  # 留空表示不限扩展名
     config_schema = [
         {
             "key": "action", "label": "操作", "type": "select", "required": True, "default": "create",
@@ -33,6 +117,7 @@ class VectorIndexProcessor:
         index_type = config.get("index_type", "vector")
         vector_db = VectorDBService()
         collection_name = "vector_collection"
+
         if action == "destroy":
             await vector_db.delete_vector(collection_name, path)
             await LogService.info(
@@ -42,9 +127,19 @@ class VectorIndexProcessor:
             )
             return Response(content=f"文件 {path} 的 {index_type} 索引已销毁", media_type="text/plain")
 
-        if index_type == 'simple':
+        mime_type = _guess_mime(path)
+
+        if index_type == "simple":
             await vector_db.ensure_collection(collection_name, vector=False)
-            await vector_db.upsert_vector(collection_name, {'path': path})
+            await vector_db.delete_vector(collection_name, path)
+            await vector_db.upsert_vector(collection_name, {
+                "path": path,
+                "source_path": path,
+                "chunk_id": "filename",
+                "mime": mime_type,
+                "type": "filename",
+                "name": os.path.basename(path),
+            })
             await LogService.info(
                 "processor:vector_index",
                 f"Created simple index for {path}",
@@ -53,24 +148,7 @@ class VectorIndexProcessor:
             return Response(content=f"文件 {path} 的普通索引已创建", media_type="text/plain")
 
         file_ext = path.split('.')[-1].lower()
-        description = ""
-        embedding = None
-
-        if file_ext in ["jpg", "jpeg", "png", "bmp"]:
-            base64_image = base64.b64encode(input_bytes).decode("utf-8")
-            description = await describe_image_base64(base64_image)
-            embedding = await get_text_embedding(description)
-            log_message = f"Indexed image {path}"
-            response_message = f"图片已索引，描述：{description}"
-        elif file_ext in ["txt", "md"]:
-            text = input_bytes.decode("utf-8")
-            embedding = await get_text_embedding(text)
-            description = text[:100] + "..." if len(text) > 100 else text
-            log_message = f"Indexed text file {path}"
-            response_message = f"文本文件已索引"
-        
-        if embedding is None:
-            return Response(content="不支持的文件类型", status_code=400)
+        details: Dict[str, Any] = {"path": path, "action": "create", "index_type": "vector"}
 
         raw_dim = await ConfigCenter.get('AI_EMBED_DIM', DEFAULT_VECTOR_DIMENSION)
         try:
@@ -81,15 +159,103 @@ class VectorIndexProcessor:
             vector_dim = DEFAULT_VECTOR_DIMENSION
 
         await vector_db.ensure_collection(collection_name, vector=True, dim=vector_dim)
-        await vector_db.upsert_vector(
-            collection_name, {'path': path, 'embedding': embedding})
-        
+        await vector_db.delete_vector(collection_name, path)
+
+        if file_ext in ["jpg", "jpeg", "png", "bmp"]:
+            processed_bytes, compression = _compress_image_for_embedding(input_bytes)
+            base64_image = base64.b64encode(processed_bytes).decode("utf-8")
+            description = await describe_image_base64(base64_image)
+            embedding = await get_text_embedding(description)
+            image_mime = "image/jpeg" if compression else mime_type
+            await vector_db.upsert_vector(collection_name, {
+                "path": _chunk_key(path, "image"),
+                "source_path": path,
+                "chunk_id": "image",
+                "embedding": embedding,
+                "text": description,
+                "mime": image_mime,
+                "type": "image",
+            })
+            details["description"] = description
+            if compression:
+                details["image_compression"] = compression
+            await LogService.info(
+                "processor:vector_index",
+                f"Indexed image {path}",
+                details=details,
+            )
+            return Response(content=f"图片已索引，描述：{description}", media_type="text/plain")
+
+        if file_ext in ["txt", "md"]:
+            try:
+                text = input_bytes.decode("utf-8")
+            except UnicodeDecodeError:
+                return Response(content="文本文件解码失败", status_code=400)
+
+            chunks = _chunk_text(text)
+            if not chunks:
+                await vector_db.upsert_vector(collection_name, {
+                    "path": _chunk_key(path, "0"),
+                    "source_path": path,
+                    "chunk_id": "0",
+                    "embedding": await get_text_embedding(text or path),
+                    "text": text,
+                    "mime": mime_type,
+                    "type": "text",
+                    "start_offset": 0,
+                    "end_offset": len(text),
+                })
+                details["chunks"] = 1
+                await LogService.info(
+                    "processor:vector_index",
+                    f"Indexed text file {path}",
+                    details=details,
+                )
+                return Response(content="文本文件已索引", media_type="text/plain")
+
+            chunk_count = 0
+            for chunk_id, chunk_text, start, end in chunks:
+                embedding = await get_text_embedding(chunk_text)
+                await vector_db.upsert_vector(collection_name, {
+                    "path": _chunk_key(path, str(chunk_id)),
+                    "source_path": path,
+                    "chunk_id": str(chunk_id),
+                    "embedding": embedding,
+                    "text": chunk_text,
+                    "mime": mime_type,
+                    "type": "text",
+                    "start_offset": start,
+                    "end_offset": end,
+                })
+                chunk_count += 1
+
+            details["chunks"] = chunk_count
+            sample = chunks[0][1]
+            details["sample"] = sample[:120]
+            await LogService.info(
+                "processor:vector_index",
+                f"Indexed text file {path}",
+                details=details,
+            )
+            return Response(content="文本文件已索引", media_type="text/plain")
+
+        # 其他类型暂未支持向量索引，回退为文件名索引
+        await vector_db.delete_vector(collection_name, path)
+        await vector_db.upsert_vector(collection_name, {
+            "path": _chunk_key(path, "fallback"),
+            "source_path": path,
+            "chunk_id": "filename",
+            "mime": mime_type,
+            "type": "filename",
+            "name": os.path.basename(path),
+            "embedding": [0.0] * vector_dim,
+        })
         await LogService.info(
             "processor:vector_index",
-            log_message,
-            details={"path": path, "description": description, "action": "create", "index_type": "vector"},
+            f"File type fallback to simple index for {path}",
+            details={"path": path, "action": "create", "index_type": "simple", "original_type": file_ext},
         )
-        return Response(content=response_message, media_type="text/plain")
+        return Response(content="暂不支持该类型的向量索引，已创建文件名索引", media_type="text/plain")
 
 
 PROCESSOR_TYPE = "vector_index"

services/vector_db/providers/milvus_lite.py

@@ -39,6 +39,35 @@ class MilvusLiteProvider(BaseVectorProvider):
             raise RuntimeError("Milvus Lite client is not initialized")
         return self.client
 
+    @staticmethod
+    def _extract_hit_payload(hit: Any) -> tuple[Any, Any, Dict[str, Any]]:
+        hit_id = getattr(hit, "id", None)
+        distance = getattr(hit, "distance", None)
+        payload: Dict[str, Any] = {}
+
+        raw: Dict[str, Any] | None = None
+        if hasattr(hit, "entity"):
+            raw_entity = getattr(hit, "entity")
+            if hasattr(raw_entity, "to_dict"):
+                raw = dict(raw_entity.to_dict())
+            else:
+                raw = dict(raw_entity)
+        elif isinstance(hit, dict):
+            raw = dict(hit)
+
+        if raw:
+            hit_id = hit_id or raw.get("id")
+            distance = distance if distance is not None else raw.get("distance")
+            inner = raw.get("entity")
+            if isinstance(inner, dict):
+                payload = dict(inner)
+            else:
+                payload = {k: v for k, v in raw.items() if k not in {"id", "distance", "entity"}}
+
+        payload.setdefault("path", payload.get("source_path"))
+        payload.setdefault("source_path", payload.get("path"))
+        return hit_id, distance, payload
+
     @staticmethod
     def _to_int(value: Any) -> int:
         try:
@@ -50,15 +79,20 @@ class MilvusLiteProvider(BaseVectorProvider):
         client = self._get_client()
         if client.has_collection(collection_name):
             return
+        common_fields = [
+            FieldSchema(name="path", dtype=DataType.VARCHAR, max_length=512, is_primary=True, auto_id=False),
+            FieldSchema(name="source_path", dtype=DataType.VARCHAR, max_length=512, is_primary=False, auto_id=False),
+        ]
+
         if vector:
             vector_dim = dim if isinstance(dim, int) and dim > 0 else 0
             if vector_dim <= 0:
                 vector_dim = 4096
             fields = [
-                FieldSchema(name="path", dtype=DataType.VARCHAR, max_length=512, is_primary=True, auto_id=False),
+                *common_fields,
                 FieldSchema(name="embedding", dtype=DataType.FLOAT_VECTOR, dim=vector_dim),
             ]
-            schema = CollectionSchema(fields, description="Image vector collection")
+            schema = CollectionSchema(fields, description="Vector collection", enable_dynamic_field=True)
             client.create_collection(collection_name, schema=schema)
             index_params = MilvusClient.prepare_index_params()
             index_params.add_index(
@@ -70,38 +104,86 @@ class MilvusLiteProvider(BaseVectorProvider):
             )
             client.create_index(collection_name, index_params=index_params)
         else:
-            fields = [
-                FieldSchema(name="path", dtype=DataType.VARCHAR, max_length=512, is_primary=True, auto_id=False),
-            ]
-            schema = CollectionSchema(fields, description="Simple file index")
+            schema = CollectionSchema(common_fields, description="Simple file index", enable_dynamic_field=True)
             client.create_collection(collection_name, schema=schema)
 
     def upsert_vector(self, collection_name: str, data: Dict[str, Any]) -> None:
-        self._get_client().upsert(collection_name, data)
+        payload = dict(data)
+        payload.setdefault("source_path", payload.get("path"))
+        payload.setdefault("vector_id", payload.get("path"))
+        self._get_client().upsert(collection_name, data=[payload])
 
     def delete_vector(self, collection_name: str, path: str) -> None:
-        self._get_client().delete(collection_name, ids=[path])
+        client = self._get_client()
+        escaped = path.replace('"', '\\"')
+        client.delete(collection_name, filter=f'source_path == "{escaped}"')
 
     def search_vectors(self, collection_name: str, query_embedding, top_k: int):
         search_params = {"metric_type": "COSINE"}
-        return self._get_client().search(
+        output_fields = [
+            "path",
+            "source_path",
+            "chunk_id",
+            "mime",
+            "text",
+            "start_offset",
+            "end_offset",
+            "type",
+            "name",
+        ]
+        raw_results = self._get_client().search(
             collection_name,
             data=[query_embedding],
             anns_field="embedding",
             search_params=search_params,
             limit=top_k,
-            output_fields=["path"],
+            output_fields=output_fields,
         )
+        formatted: List[List[Dict[str, Any]]] = []
+        for hits in raw_results:
+            bucket: List[Dict[str, Any]] = []
+            for hit in hits:
+                hit_id, distance, entity = self._extract_hit_payload(hit)
+                bucket.append({
+                    "id": hit_id,
+                    "distance": distance,
+                    "entity": entity,
+                })
+            formatted.append(bucket)
+        return formatted
 
     def search_by_path(self, collection_name: str, query_path: str, top_k: int):
-        filter_expr = f"path like '%{query_path}%'" if query_path else "path like '%%'"
+        if query_path:
+            escaped = query_path.replace('"', '\\"')
+            filter_expr = f'source_path like "%{escaped}%"'
+        else:
+            filter_expr = "source_path like '%%'"
         results = self._get_client().query(
             collection_name,
             filter=filter_expr,
             limit=top_k,
-            output_fields=["path"],
+            output_fields=[
+                "path",
+                "source_path",
+                "chunk_id",
+                "mime",
+                "text",
+                "start_offset",
+                "end_offset",
+                "type",
+                "name",
+            ],
         )
-        return [[{"id": r["path"], "distance": 1.0, "entity": {"path": r["path"]}} for r in results]]
+        formatted = []
+        for row in results:
+            entity = dict(row)
+            entity.setdefault("path", entity.get("source_path"))
+            formatted.append({
+                "id": entity.get("path"),
+                "distance": 1.0,
+                "entity": entity,
+            })
+        return [formatted]
 
     def get_all_stats(self) -> Dict[str, Any]:
         client = self._get_client()

services/vector_db/providers/milvus_server.py

@@ -47,6 +47,35 @@ class MilvusServerProvider(BaseVectorProvider):
             raise RuntimeError("Milvus Server client is not initialized")
         return self.client
 
+    @staticmethod
+    def _extract_hit_payload(hit: Any) -> tuple[Any, Any, Dict[str, Any]]:
+        hit_id = getattr(hit, "id", None)
+        distance = getattr(hit, "distance", None)
+        payload: Dict[str, Any] = {}
+
+        raw: Dict[str, Any] | None = None
+        if hasattr(hit, "entity"):
+            raw_entity = getattr(hit, "entity")
+            if hasattr(raw_entity, "to_dict"):
+                raw = dict(raw_entity.to_dict())
+            else:
+                raw = dict(raw_entity)
+        elif isinstance(hit, dict):
+            raw = dict(hit)
+
+        if raw:
+            hit_id = hit_id or raw.get("id")
+            distance = distance if distance is not None else raw.get("distance")
+            inner = raw.get("entity")
+            if isinstance(inner, dict):
+                payload = dict(inner)
+            else:
+                payload = {k: v for k, v in raw.items() if k not in {"id", "distance", "entity"}}
+
+        payload.setdefault("path", payload.get("source_path"))
+        payload.setdefault("source_path", payload.get("path"))
+        return hit_id, distance, payload
+
     @staticmethod
     def _to_int(value: Any) -> int:
         try:
@@ -58,15 +87,19 @@ class MilvusServerProvider(BaseVectorProvider):
         client = self._get_client()
         if client.has_collection(collection_name):
             return
+        common_fields = [
+            FieldSchema(name="path", dtype=DataType.VARCHAR, max_length=512, is_primary=True, auto_id=False),
+            FieldSchema(name="source_path", dtype=DataType.VARCHAR, max_length=512, is_primary=False, auto_id=False),
+        ]
         if vector:
             vector_dim = dim if isinstance(dim, int) and dim > 0 else 0
             if vector_dim <= 0:
                 vector_dim = 4096
             fields = [
-                FieldSchema(name="path", dtype=DataType.VARCHAR, max_length=512, is_primary=True, auto_id=False),
+                *common_fields,
                 FieldSchema(name="embedding", dtype=DataType.FLOAT_VECTOR, dim=vector_dim),
             ]
-            schema = CollectionSchema(fields, description="Image vector collection")
+            schema = CollectionSchema(fields, description="Vector collection", enable_dynamic_field=True)
             client.create_collection(collection_name, schema=schema)
             index_params = MilvusClient.prepare_index_params()
             index_params.add_index(
@@ -78,38 +111,86 @@ class MilvusServerProvider(BaseVectorProvider):
             )
             client.create_index(collection_name, index_params=index_params)
         else:
-            fields = [
-                FieldSchema(name="path", dtype=DataType.VARCHAR, max_length=512, is_primary=True, auto_id=False),
-            ]
-            schema = CollectionSchema(fields, description="Simple file index")
+            schema = CollectionSchema(common_fields, description="Simple file index", enable_dynamic_field=True)
             client.create_collection(collection_name, schema=schema)
 
     def upsert_vector(self, collection_name: str, data: Dict[str, Any]) -> None:
-        self._get_client().upsert(collection_name, data)
+        payload = dict(data)
+        payload.setdefault("source_path", payload.get("path"))
+        payload.setdefault("vector_id", payload.get("path"))
+        self._get_client().upsert(collection_name, data=[payload])
 
     def delete_vector(self, collection_name: str, path: str) -> None:
-        self._get_client().delete(collection_name, ids=[path])
+        client = self._get_client()
+        escaped = path.replace('"', '\\"')
+        client.delete(collection_name, filter=f'source_path == "{escaped}"')
 
     def search_vectors(self, collection_name: str, query_embedding, top_k: int):
         search_params = {"metric_type": "COSINE"}
-        return self._get_client().search(
+        output_fields = [
+            "path",
+            "source_path",
+            "chunk_id",
+            "mime",
+            "text",
+            "start_offset",
+            "end_offset",
+            "type",
+            "name",
+        ]
+        raw_results = self._get_client().search(
             collection_name,
             data=[query_embedding],
             anns_field="embedding",
             search_params=search_params,
             limit=top_k,
-            output_fields=["path"],
+            output_fields=output_fields,
         )
+        formatted: List[List[Dict[str, Any]]] = []
+        for hits in raw_results:
+            bucket: List[Dict[str, Any]] = []
+            for hit in hits:
+                hit_id, distance, entity = self._extract_hit_payload(hit)
+                bucket.append({
+                    "id": hit_id,
+                    "distance": distance,
+                    "entity": entity,
+                })
+            formatted.append(bucket)
+        return formatted
 
     def search_by_path(self, collection_name: str, query_path: str, top_k: int):
-        filter_expr = f"path like '%{query_path}%'" if query_path else "path like '%%'"
+        if query_path:
+            escaped = query_path.replace('"', '\\"')
+            filter_expr = f'source_path like "%{escaped}%"'
+        else:
+            filter_expr = "source_path like '%%'"
         results = self._get_client().query(
             collection_name,
             filter=filter_expr,
             limit=top_k,
-            output_fields=["path"],
+            output_fields=[
+                "path",
+                "source_path",
+                "chunk_id",
+                "mime",
+                "text",
+                "start_offset",
+                "end_offset",
+                "type",
+                "name",
+            ],
         )
-        return [[{"id": r["path"], "distance": 1.0, "entity": {"path": r["path"]}} for r in results]]
+        formatted = []
+        for row in results:
+            entity = dict(row)
+            entity.setdefault("path", entity.get("source_path"))
+            formatted.append({
+                "id": entity.get("path"),
+                "distance": 1.0,
+                "entity": entity,
+            })
+        return [formatted]
 
     def get_all_stats(self) -> Dict[str, Any]:
         client = self._get_client()

services/vector_db/providers/qdrant.py

@@ -58,29 +58,59 @@ class QdrantProvider(BaseVectorProvider):
         size = dim if vector and isinstance(dim, int) and dim > 0 else 1
         return qmodels.VectorParams(size=size, distance=qmodels.Distance.COSINE)
 
+    def _ensure_payload_indexes(self, client: QdrantClient, collection_name: str) -> None:
+        for field in ("path", "source_path"):
+            try:
+                client.create_payload_index(
+                    collection_name=collection_name,
+                    field_name=field,
+                    field_schema="keyword",
+                )
+            except Exception as exc:  # pragma: no cover - 依赖外部服务
+                message = str(exc).lower()
+                if "already exists" in message or "index exists" in message:
+                    continue
+                # 旧版本 qdrant 可能返回带状态码的异常，这里容忍重复创建
+                raise
+
     def ensure_collection(self, collection_name: str, vector: bool, dim: int) -> None:
         client = self._get_client()
         try:
-            if client.collection_exists(collection_name):
-                return
+            exists = client.collection_exists(collection_name)
         except Exception as exc:  # pragma: no cover - 依赖外部服务
             raise RuntimeError(f"Failed to check Qdrant collection '{collection_name}': {exc}") from exc
 
+        if exists:
+            try:
+                self._ensure_payload_indexes(client, collection_name)
+            except Exception:
+                pass
+            return
+
         vectors_config = self._vector_params(vector, dim)
         try:
             client.create_collection(collection_name=collection_name, vectors_config=vectors_config)
         except Exception as exc:  # pragma: no cover
             if "already exists" in str(exc).lower():
+                try:
+                    self._ensure_payload_indexes(client, collection_name)
+                except Exception:
+                    pass
                 return
             raise RuntimeError(f"Failed to create Qdrant collection '{collection_name}': {exc}") from exc
 
+        try:
+            self._ensure_payload_indexes(client, collection_name)
+        except Exception:
+            pass
+
     @staticmethod
-    def _point_id(path: str) -> str:
-        return str(uuid5(NAMESPACE_URL, path))
+    def _point_id(uid: str) -> str:
+        return str(uuid5(NAMESPACE_URL, uid))
 
     def _prepare_point(self, data: Dict[str, Any]) -> qmodels.PointStruct:
-        path = data.get("path")
-        if not path:
+        uid = data.get("path")
+        if not uid:
             raise ValueError("Qdrant upsert requires 'path' in data")
 
         embedding = data.get("embedding")
@@ -89,8 +119,11 @@ class QdrantProvider(BaseVectorProvider):
         else:
             vector = [float(x) for x in embedding]
 
-        payload = {"path": path}
-        return qmodels.PointStruct(id=self._point_id(path), vector=vector, payload=payload)
+        payload = {k: v for k, v in data.items() if k != "embedding"}
+        payload.setdefault("vector_id", uid)
+        source_path = payload.get("source_path") or payload.get("path")
+        payload["path"] = source_path
+        return qmodels.PointStruct(id=self._point_id(str(uid)), vector=vector, payload=payload)
 
     def upsert_vector(self, collection_name: str, data: Dict[str, Any]) -> None:
         client = self._get_client()
@@ -99,7 +132,12 @@ class QdrantProvider(BaseVectorProvider):
 
     def delete_vector(self, collection_name: str, path: str) -> None:
         client = self._get_client()
-        selector = qmodels.PointIdsList(points=[self._point_id(path)])
+        condition = qmodels.FieldCondition(
+            key="path",
+            match=qmodels.MatchValue(value=path),
+        )
+        flt = qmodels.Filter(must=[condition])
+        selector = qmodels.FilterSelector(filter=flt)
         client.delete(collection_name=collection_name, points_selector=selector, wait=True)
 
     def _format_search_results(self, points: Sequence[qmodels.ScoredPoint]):
@@ -107,7 +145,7 @@ class QdrantProvider(BaseVectorProvider):
             {
                 "id": point.id,
                 "distance": point.score,
-                "entity": {"path": (point.payload or {}).get("path")},
+                "entity": point.payload or {},
             }
             for point in points
         ]
@@ -141,11 +179,11 @@ class QdrantProvider(BaseVectorProvider):
                 break
 
             for record in records:
-                path = (record.payload or {}).get("path")
-                if query_path and path:
-                    if query_path not in path:
-                        continue
-                results.append({"id": record.id, "distance": 1.0, "entity": {"path": path}})
+                payload = record.payload or {}
+                path = payload.get("path")
+                if query_path and path and query_path not in path:
+                    continue
+                results.append({"id": record.id, "distance": 1.0, "entity": payload})
                 if len(results) >= top_k:
                     break
 

services/virtual_fs.py

@@ -20,9 +20,11 @@ from services.processors.registry import get as get_processor
 from services.tasks import task_service
 from services.logging import LogService
 from services.config import ConfigCenter
+from services.vector_db import VectorDBService
 
 
 CROSS_TRANSFER_TEMP_ROOT = Path("data/tmp/cross_transfer")
+DIRECT_REDIRECT_CONFIG_KEY = "enable_direct_download_307"
 
 if TYPE_CHECKING:
     from services.task_queue import Task
@@ -87,6 +89,31 @@ async def resolve_adapter_and_rel(path: str):
     return adapter_instance, adapter_model, effective_root, rel
 
 
+async def maybe_redirect_download(adapter_instance, adapter_model, root: str, rel: str):
+    """若适配器启用了 307 直链，尝试构造重定向响应。"""
+    if not rel or rel.endswith('/'):
+        return None
+
+    config = getattr(adapter_model, "config", {}) or {}
+    if not config.get(DIRECT_REDIRECT_CONFIG_KEY):
+        return None
+
+    handler = getattr(adapter_instance, "get_direct_download_response", None)
+    if not callable(handler):
+        return None
+
+    try:
+        response = await handler(root, rel)
+    except FileNotFoundError:
+        raise
+    except Exception:
+        return None
+
+    if isinstance(response, Response):
+        return response
+    return None
+
+
 async def _ensure_method(adapter: Any, method: str):
     func = getattr(adapter, method, None)
     if not callable(func):
@@ -437,7 +464,7 @@ async def rename_path(src: str, dst: str, overwrite: bool = False, return_debug:
 
 
 async def stream_file(path: str, range_header: str | None):
-    adapter_instance, _, root, rel = await resolve_adapter_and_rel(path)
+    adapter_instance, adapter_model, root, rel = await resolve_adapter_and_rel(path)
     if not rel or rel.endswith('/'):
         raise HTTPException(400, detail="Path is a directory")
     if is_raw_filename(rel):
@@ -470,6 +497,10 @@ async def stream_file(path: str, range_header: str | None):
         except Exception as e:
             raise HTTPException(500, detail=f"RAW file processing failed: {e}")
 
+    redirect_response = await maybe_redirect_download(adapter_instance, adapter_model, root, rel)
+    if redirect_response is not None:
+        return redirect_response
+
     stream_impl = getattr(adapter_instance, "stream_file", None)
     if callable(stream_impl):
         return await stream_impl(root, rel, range_header)
@@ -478,12 +509,78 @@ async def stream_file(path: str, range_header: str | None):
     return Response(content=data, media_type=mime or "application/octet-stream")
 
 
+async def _gather_vector_index(full_path: str, limit: int = 20):
+    """查询与文件相关的索引信息。失败时返回 None。"""
+    vector_db = VectorDBService()
+    try:
+        raw_results = await vector_db.search_by_path("vector_collection", full_path, max(limit * 2, 20))
+    except Exception:
+        return None
+
+    matched = []
+    if raw_results:
+        buckets = raw_results if isinstance(raw_results, list) else [raw_results]
+        for bucket in buckets:
+            if not bucket:
+                continue
+            for record in bucket:
+                entity = dict((record or {}).get("entity") or {})
+                source_path = entity.get("source_path") or entity.get("path") or ""
+                if source_path != full_path:
+                    continue
+                entry = {
+                    "chunk_id": str(entity.get("chunk_id")) if entity.get("chunk_id") is not None else None,
+                    "type": entity.get("type"),
+                    "mime": entity.get("mime"),
+                    "name": entity.get("name"),
+                    "start_offset": entity.get("start_offset"),
+                    "end_offset": entity.get("end_offset"),
+                    "vector_id": entity.get("vector_id"),
+                }
+                text = entity.get("text") or entity.get("description")
+                if text:
+                    preview_limit = 400
+                    entry["preview"] = text[:preview_limit]
+                    entry["preview_truncated"] = len(text) > preview_limit
+                matched.append(entry)
+
+    if not matched:
+        return {"total": 0, "entries": [], "by_type": {}, "has_more": False}
+
+    type_counts: Dict[str, int] = {}
+    for item in matched:
+        key = item.get("type") or "unknown"
+        type_counts[key] = type_counts.get(key, 0) + 1
+
+    has_more = len(matched) > limit
+    return {
+        "total": len(matched),
+        "entries": matched[:limit],
+        "by_type": type_counts,
+        "has_more": has_more,
+        "limit": limit,
+    }
+
+
 async def stat_file(path: str):
     adapter_instance, _, root, rel = await resolve_adapter_and_rel(path)
     stat_func = getattr(adapter_instance, "stat_file", None)
     if not callable(stat_func):
         raise HTTPException(501, detail="Adapter does not implement stat_file")
-    return await stat_func(root, rel)
+    info = await stat_func(root, rel)
+
+    if isinstance(info, dict):
+        info.setdefault("path", path)
+        try:
+            is_dir = bool(info.get("is_dir"))
+        except Exception:
+            is_dir = False
+        if not is_dir:
+            vector_index = await _gather_vector_index(path)
+            if vector_index is not None:
+                info["vector_index"] = vector_index
+
+    return info
 
 
 async def copy_path(

web/src/api/adapters.ts

@@ -13,7 +13,7 @@ export interface AdapterItem {
 export interface AdapterTypeField {
   key: string;
   label: string;
-  type: 'string' | 'password' | 'number';
+  type: 'string' | 'password' | 'number' | 'boolean';
   required?: boolean;
   placeholder?: string;
   default?: any;

web/src/api/processors.ts

@@ -34,6 +34,18 @@ export const processorsApi = {
       method: 'POST',
       json: params,
     }),
+  processDirectory: (params: {
+    path: string;
+    processor_type: string;
+    config: any;
+    overwrite: boolean;
+    max_depth?: number | null;
+    suffix?: string | null;
+  }) =>
+    request<{ task_ids: string[]; scheduled: number }>('/processors/process-directory', {
+      method: 'POST',
+      json: params,
+    }),
   getSource: (type: string) =>
     request<{ source: string; module_path: string }>('/processors/source/' + encodeURIComponent(type), {
       method: 'GET',

web/src/api/vfs.ts

@@ -21,9 +21,29 @@ export interface DirListing {
 }
 
 export interface SearchResultItem {
-  id: number;
+  id: string;
   path: string;
   score: number;
+  chunk_id?: string;
+  snippet?: string;
+  mime?: string;
+  source_type?: string;
+  start_offset?: number;
+  end_offset?: number;
+  metadata?: Record<string, any>;
+}
+
+export interface SearchPagination {
+  page: number;
+  page_size: number;
+  has_more: boolean;
+}
+
+export interface SearchResponse {
+  items: SearchResultItem[];
+  query: string;
+  mode?: string;
+  pagination?: SearchPagination;
 }
 
 export const vfsApi = {
@@ -105,6 +125,20 @@ export const vfsApi = {
       xhr.send(fd);
     });
   },
-  searchFiles: (q: string, top_k: number = 10, mode: 'vector' | 'filename' = 'vector') =>
-    request<{ items: SearchResultItem[]; query: string }>(`/search?q=${encodeURIComponent(q)}&top_k=${top_k}&mode=${mode}`),
+  searchFiles: (
+    q: string,
+    top_k: number = 10,
+    mode: 'vector' | 'filename' = 'vector',
+    page?: number,
+    page_size?: number,
+  ) => {
+    const params = new URLSearchParams({
+      q,
+      top_k: String(top_k),
+      mode,
+    });
+    if (page !== undefined) params.set('page', String(page));
+    if (page_size !== undefined) params.set('page_size', String(page_size));
+    return request<SearchResponse>(`/search?${params.toString()}`);
+  },
 };

web/src/components/WeChatModal.tsx

@@ -0,0 +1,26 @@
+import { Modal, theme } from 'antd';
+import { useI18n } from '../i18n';
+
+export interface WeChatModalProps {
+  open: boolean;
+  onClose: () => void;
+}
+
+export default function WeChatModal({ open, onClose }: WeChatModalProps) {
+  const { token } = theme.useToken();
+  const { t } = useI18n();
+
+  return (
+    <Modal open={open} onCancel={onClose} title={t('Join Community')} footer={null} width={320}>
+      <div style={{ textAlign: 'center', padding: '12px 0' }}>
+        <img src="https://foxel.cc/image/wechat.png" width={200} alt="wechat" />
+        <div style={{ marginTop: 12, color: token.colorTextSecondary }}>
+          {t('Scan to join WeChat group')}
+        </div>
+        <div style={{ marginTop: 8, fontSize: 12, color: token.colorTextTertiary }}>
+          {t('If QR expires, add drizzle2001 to join')}
+        </div>
+      </div>
+    </Modal>
+  );
+}

web/src/i18n/locales/en.ts

@@ -220,6 +220,17 @@ export const en = {
   'Copy failed': 'Copy failed',
   'Permissions': 'Permissions',
   'EXIF Info': 'EXIF Info',
+  'Index Info': 'Index Info',
+  'Indexed Items': 'Indexed Items',
+  'Indexed Types': 'Indexed Types',
+  'No index data': 'No index data',
+  'Indexed Chunks': 'Indexed Chunks',
+  'More Indexed Chunks': 'More Indexed Chunks',
+  'Chunk ID': 'Chunk ID',
+  'Offset Range': 'Offset Range',
+  'Vector ID': 'Vector ID',
+  'Preview': 'Preview',
+  'Showing first {count} entries': 'Showing first {count} entries',
 
   // Search dialog
   'Smart Search': 'Smart Search',

web/src/i18n/locales/zh.ts

@@ -220,6 +220,17 @@ export const zh = {
   'Copy failed': '复制失败',
   'Permissions': '权限',
   'EXIF Info': 'EXIF信息',
+  'Index Info': '索引信息',
+  'Indexed Items': '索引条目数',
+  'Indexed Types': '索引类型统计',
+  'No index data': '暂无索引数据',
+  'Indexed Chunks': '索引条目',
+  'More Indexed Chunks': '更多索引条目',
+  'Chunk ID': '分片ID',
+  'Offset Range': '偏移范围',
+  'Vector ID': '向量ID',
+  'Preview': '内容预览',
+  'Showing first {count} entries': '仅展示前 {count} 条',
 
   // Search dialog
   'Smart Search': '智能搜索',
@@ -418,6 +429,17 @@ export const zh = {
   'Source Editor': '源码编辑',
   'Module Path': '模块路径',
   'Directory processing always overwrites original files': '选择目录时会强制覆盖原文件',
+  'Directory execution will enqueue one task per file': '目录模式会为每个文件单独创建任务',
+  'Directory scope': '目录范围',
+  'Current level only': '仅当前层级',
+  'Include subdirectories': '包含子目录',
+  'Max depth': '最大层级',
+  'Leave empty to traverse all subdirectories': '留空表示遍历所有子目录',
+  'Depth must be greater or equal to 0': '层级必须大于或等于 0',
+  'Output suffix': '输出后缀',
+  'Suffix will be inserted before the file extension, e.g. demo_processed.mp4': '后缀会插入到文件扩展名前，例如 demo_processed.mp4',
+  'Suffix such as _processed': '例如 _processed 的后缀',
+  'Suffix cannot be empty': '后缀不能为空',
   'No data': '暂无数据',
 
   // Path selector

web/src/layout/SearchDialog.tsx

@@ -1,128 +1,313 @@
-import { Modal, Input, List, Divider, Spin, Select, Space } from 'antd';
+import { Modal, Input, List, Divider, Spin, Space, Tag, Typography, Empty, Flex, Segmented, Pagination } from 'antd';
 import { SearchOutlined, FileTextOutlined } from '@ant-design/icons';
-import React, { useState } from 'react';
+import React, { useRef, useState } from 'react';
 import { vfsApi, type SearchResultItem } from '../api/vfs';
 import { useI18n } from '../i18n';
 import { useNavigate } from 'react-router';
 
-
 interface SearchDialogProps {
   open: boolean;
   onClose: () => void;
 }
 
-const SEARCH_MODES = (t: (k: string)=>string) => [
-  { label: t('Smart Search'), value: 'vector' },
-  { label: t('Name Search'), value: 'filename' },
-];
+type SearchMode = 'vector' | 'filename';
+const PAGE_SIZE = 10;
 
 const SearchDialog: React.FC<SearchDialogProps> = ({ open, onClose }) => {
   const [search, setSearch] = useState('');
   const [loading, setLoading] = useState(false);
   const [results, setResults] = useState<SearchResultItem[]>([]);
   const [searched, setSearched] = useState(false);
-  const [searchMode, setSearchMode] = useState<'vector' | 'filename'>('vector');
+  const [searchMode, setSearchMode] = useState<SearchMode>('vector');
+  const [page, setPage] = useState(1);
+  const [hasMore, setHasMore] = useState(false);
+  const requestIdRef = useRef(0);
   const { t } = useI18n();
   const navigate = useNavigate();
 
-  const handleSearch = async () => {
-    if (!search.trim()) return;
+  const renderSourceLabel = (value?: string) => {
+    switch ((value || '').toLowerCase()) {
+      case 'vector':
+        return t('Vector Search');
+      case 'filename':
+        return t('Name Search');
+      case 'text':
+        return t('Text Chunk');
+      case 'image':
+        return t('Image Description');
+      default:
+        return t('Vector Search');
+    }
+  };
+
+  const sourceColor = (value?: string) => {
+    switch ((value || '').toLowerCase()) {
+      case 'vector':
+        return 'blue';
+      case 'filename':
+        return 'green';
+      case 'image':
+        return 'volcano';
+      case 'text':
+        return 'geekblue';
+      default:
+        return 'purple';
+    }
+  };
+
+  const performSearch = async (options?: { page?: number; mode?: SearchMode }) => {
+    const query = search.trim();
+    if (!query) {
+      setSearched(false);
+      setResults([]);
+      setHasMore(false);
+      return;
+    }
+
+    const currentMode = options?.mode ?? searchMode;
+    const targetPage = currentMode === 'filename' ? (options?.page ?? (currentMode === searchMode ? page : 1)) : 1;
+
+    const requestId = requestIdRef.current + 1;
+    requestIdRef.current = requestId;
+
     setLoading(true);
     setSearched(true);
-    try {
-      const res = await vfsApi.searchFiles(search, 10, searchMode);
-      setResults(res.items);
-    } catch (e) {
-      setResults([]);
+    if (currentMode === 'filename') {
+      setPage(targetPage);
+    } else {
+      setPage(1);
+      setHasMore(false);
+    }
+
+    try {
+      const res = await vfsApi.searchFiles(
+        query,
+        currentMode === 'filename' ? PAGE_SIZE : 10,
+        currentMode,
+        currentMode === 'filename' ? targetPage : undefined,
+        currentMode === 'filename' ? PAGE_SIZE : undefined,
+      );
+      if (requestId !== requestIdRef.current) {
+        return;
+      }
+      setResults(res.items);
+      if (currentMode === 'filename') {
+        const pagination = res.pagination;
+        setHasMore(Boolean(pagination?.has_more));
+        if (pagination?.page) {
+          setPage(pagination.page);
+        }
+      } else {
+        setHasMore(false);
+      }
+    } catch (e) {
+      if (requestId !== requestIdRef.current) {
+        return;
+      }
+      setResults([]);
+      if (currentMode === 'filename') {
+        setHasMore(false);
+      }
+    } finally {
+      if (requestId === requestIdRef.current) {
+        setLoading(false);
+      }
     }
-    setLoading(false);
   };
 
+  const handleSearch = () => {
+    if (!search.trim()) {
+      setResults([]);
+      setSearched(false);
+      setHasMore(false);
+      setPage(1);
+      return;
+    }
+    void performSearch({ page: searchMode === 'filename' ? 1 : undefined });
+  };
+
+  const handleModeChange = (value: string | number) => {
+    const nextMode = value as SearchMode;
+    setHasMore(false);
+    setPage(1);
+    setSearchMode(nextMode);
+    if (search.trim()) {
+      void performSearch({ mode: nextMode, page: nextMode === 'filename' ? 1 : undefined });
+    } else {
+      setResults([]);
+      setSearched(false);
+    }
+  };
+
+  const handleClose = () => {
+    setSearch('');
+    setResults([]);
+    setSearched(false);
+    setSearchMode('vector');
+    setPage(1);
+    setHasMore(false);
+    requestIdRef.current = 0;
+    setLoading(false);
+    onClose();
+  };
+
+  const totalItems = searchMode === 'filename'
+    ? (hasMore ? page * PAGE_SIZE + 1 : (page - 1) * PAGE_SIZE + results.length)
+    : results.length;
+
   return (
     <Modal
       open={open}
-      onCancel={onClose}
+      onCancel={handleClose}
       footer={null}
-      width={600}
+      width={720}
       centered
       title={null}
       closable={false}
+      styles={{
+        body: {
+          padding: '12px 16px 16px',
+          maxHeight: '70vh',
+          overflow: 'hidden',
+          display: 'flex',
+          flexDirection: 'column',
+          gap: 12,
+        },
+      }}
     >
-      <Space.Compact style={{ marginBottom: 0, width: '100%' }}>
-        <Select
-          options={SEARCH_MODES(t)}
-          value={searchMode}
-          onChange={v => setSearchMode(v as 'vector' | 'filename')}
-          style={{
-            width: 120,
-            fontSize: 18,
-            height: 40,
-            lineHeight: '40px',
-            borderTopRightRadius: 0,
-            borderBottomRightRadius: 0,
-            borderRight: 0,
-            verticalAlign: 'top',
-          }}
-          styles={{ popup: { root: { fontSize: 18 } } }}
-          popupMatchSelectWidth={false}
-        />
-        <Input
-          allowClear
-          prefix={<SearchOutlined />}
-          placeholder={t('Search files / tags / types')}
-          value={search}
-          onChange={e => setSearch(e.target.value)}
-          style={{
-            fontSize: 18,
-            height: 40,
-            width: 'calc(100% - 120px)',
-            borderTopLeftRadius: 0,
-            borderBottomLeftRadius: 0,
-            verticalAlign: 'top',
-          }}
-          autoFocus
-          onPressEnter={handleSearch}
-        />
-      </Space.Compact>
-      {searched && (
-        <>
-          <Divider style={{ margin: '12px 0' }}>{t('Search Results')}</Divider>
-          {loading ? (
-            <Spin />
-          ) : (
-            <List
-              itemLayout="horizontal"
-              dataSource={results}
-              locale={{ emptyText: t('No files found') }}
-              renderItem={item => {
-                const fullPath = item.path || '';
-                const trimmed = fullPath.replace(/\/+$/, '');
-                const parts = trimmed.split('/');
-                const filename = parts.pop() || '';
-                const dir = parts.length ? '/' + parts.join('/') : '/';
-                return (
-                  <List.Item>
-                    <List.Item.Meta
-                      avatar={<FileTextOutlined />}
-                      title={
-                        <a
-                          onClick={() => {
-                            navigate(`/files${dir === '/' ? '' : dir}`, { state: { highlight: { name: filename } } });
-                            onClose();
-                          }}
-                        >
-                          {fullPath}
-                        </a>
-                      }
-                      description={`${t('Relevance')}: ${item.score.toFixed(2)}`}
-                    />
-                  </List.Item>
-                );
-              }}
-            />
-          )}
-        </>
-      )}
+      <Flex vertical style={{ gap: 12, flex: 1, minHeight: 0 }}>
+        <Flex align="center" style={{ width: '100%', gap: 12, flexWrap: 'wrap' }}>
+          <Segmented
+            options={[
+              { label: t('Smart Search'), value: 'vector' },
+              { label: t('Name Search'), value: 'filename' },
+            ]}
+            value={searchMode}
+            onChange={handleModeChange}
+            style={{
+              minWidth: 160,
+              height: 40,
+              borderRadius: 20,
+              display: 'flex',
+              alignItems: 'center',
+            }}
+            size="large"
+          />
+          <Input
+            allowClear
+            prefix={<SearchOutlined />}
+            placeholder={t('Search files / tags / types')}
+            value={search}
+            onChange={e => {
+              const value = e.target.value;
+              setSearch(value);
+              if (!value.trim()) {
+                setResults([]);
+                setSearched(false);
+                setHasMore(false);
+                setPage(1);
+                requestIdRef.current += 1;
+                setLoading(false);
+              }
+            }}
+            style={{ fontSize: 18, height: 40, flex: 1, minWidth: 240 }}
+            styles={{
+              input: {
+                borderRadius: 20,
+              },
+            }}
+            autoFocus
+            onPressEnter={handleSearch}
+          />
+        </Flex>
+
+        {!searched ? null : (
+          <Flex vertical style={{ flex: 1, minHeight: 0 }}>
+            <Divider style={{ margin: 0, padding: '0 0 12px' }}>{t('Search Results')}</Divider>
+            {loading ? (
+              <Flex align="center" justify="center" style={{ flex: 1 }}>
+                <Spin />
+              </Flex>
+            ) : results.length === 0 ? (
+              <Flex align="center" justify="center" style={{ flex: 1 }}>
+                <Empty description={t('No files found')} image={Empty.PRESENTED_IMAGE_SIMPLE} />
+              </Flex>
+            ) : (
+              <div style={{ flex: 1, minHeight: 0, display: 'flex', flexDirection: 'column' }}>
+                <div style={{ flex: 1, minHeight: 0, overflowY: 'auto', paddingRight: 6 }}>
+                  <List
+                    itemLayout="horizontal"
+                    dataSource={results}
+                    split={false}
+                    renderItem={item => {
+                      const fullPath = item.path || '';
+                      const trimmed = fullPath.replace(/\/+$/, '');
+                      const parts = trimmed.split('/');
+                      const filename = parts.pop() || '';
+                      const dir = parts.length ? '/' + parts.join('/') : '/';
+                    const snippet = item.snippet || '';
+                    const retrieval = item.metadata?.retrieval_source || item.source_type;
+                    const retrievalLabel = renderSourceLabel(retrieval);
+                    const scoreText = Number.isFinite(item.score) ? item.score.toFixed(2) : '-';
+
+                      return (
+                        <List.Item style={{ padding: '10px 12px', borderRadius: 6, background: '#fafafa', marginBottom: 8 }}>
+                          <List.Item.Meta
+                            avatar={<FileTextOutlined style={{ fontSize: 18, color: '#8c8c8c' }} />}
+                            title={
+                              <a
+                                onClick={() => {
+                                  navigate(`/files${dir === '/' ? '' : dir}`, { state: { highlight: { name: filename } } });
+                                  handleClose();
+                                }}
+                                style={{ fontSize: 16 }}
+                              >
+                                {fullPath}
+                              </a>
+                            }
+                            description={(
+                              <Space direction="vertical" size={6} style={{ width: '100%' }}>
+                                {snippet ? (
+                                  <Typography.Paragraph ellipsis={{ rows: 3 }} style={{ marginBottom: 0 }}>
+                                    {snippet}
+                                  </Typography.Paragraph>
+                                ) : null}
+                                <Space size={10} wrap>
+                                  {retrieval ? (
+                                    <Tag color={sourceColor(retrieval)} style={{ marginRight: 0 }}>
+                                      {retrievalLabel}
+                                    </Tag>
+                                  ) : null}
+                                  <Typography.Text type="secondary">
+                                    {t('Relevance')}: {scoreText}
+                                  </Typography.Text>
+                                </Space>
+                              </Space>
+                            )}
+                          />
+                        </List.Item>
+                      );
+                    }}
+                  />
+                </div>
+                {searchMode === 'filename' && results.length > 0 ? (
+                  <Pagination
+                    current={page}
+                    pageSize={PAGE_SIZE}
+                    total={Math.max(totalItems, 1)}
+                    showSizeChanger={false}
+                    size="small"
+                    style={{ marginTop: 12, textAlign: 'right' }}
+                    onChange={(nextPage) => {
+                      void performSearch({ page: nextPage });
+                    }}
+                  />
+                ) : null}
+              </div>
+            )}
+          </Flex>
+        )}
+      </Flex>
     </Modal>
   );
 };

web/src/layout/SideNav.tsx

@@ -18,6 +18,7 @@ import ReactMarkdown from 'react-markdown';
 import { useTheme } from '../contexts/ThemeContext';
 import { useI18n } from '../i18n';
 import { useAppWindows } from '../contexts/AppWindowsContext';
+import WeChatModal from '../components/WeChatModal';
 const { Sider } = Layout;
 
 export interface SideNavProps {
@@ -211,7 +212,7 @@ const SideNav = memo(function SideNav({ collapsed, activeKey, onChange, onToggle
                     <Tag icon={<WarningOutlined />} color="warning" style={{ marginInlineEnd: 0 }} />
                   ) : (
                     <Tag icon={<WarningOutlined />} color="warning">
-                      {status?.version} - {t('Update available')} [{latestVersion?.version}]
+                      {t('Update available')} [{latestVersion?.version}]
                     </Tag>
                   )}
                 </a>
@@ -260,23 +261,7 @@ const SideNav = memo(function SideNav({ collapsed, activeKey, onChange, onToggle
 
         </div>
       </Sider>
-      <Modal
-        open={isModalOpen}
-        onCancel={() => setIsModalOpen(false)}
-        title={t('Join Community')}
-        footer={null}
-        width={320}
-      >
-        <div style={{ textAlign: 'center', padding: '12px 0' }}>
-          <img src="https://foxel.cc/image/wechat.png" width={200} alt="wechat" />
-          <div style={{ marginTop: 12, color: token.colorTextSecondary }}>
-            {t('Scan to join WeChat group')}
-          </div>
-          <div style={{ marginTop: 8, fontSize: 12, color: token.colorTextTertiary }}>
-            {t('If QR expires, add drizzle2001 to join')}
-          </div>
-        </div>
-      </Modal>
+      <WeChatModal open={isModalOpen} onClose={() => setIsModalOpen(false)} />
       <Modal
         open={isVersionModalOpen}
         onCancel={() => setIsVersionModalOpen(false)}

web/src/pages/AdaptersPage.tsx

@@ -1,24 +1,9 @@
 import { memo, useState, useEffect, useCallback } from 'react';
 import { Table, Button, Space, Drawer, Form, Input, Switch, message, Typography, Popconfirm, Select } from 'antd';
 import PageCard from '../components/PageCard';
-import { adaptersApi, type AdapterItem } from '../api/client';
+import { adaptersApi, type AdapterItem, type AdapterTypeMeta } from '../api/client';
 import { useI18n } from '../i18n';
 
-
-interface AdapterTypeField {
-  key: string;
-  label: string;
-  type: 'string' | 'password' | 'number';
-  required?: boolean;
-  placeholder?: string;
-  default?: any;
-}
-interface AdapterTypeMeta {
-  type: string;
-  name: string;
-  config_schema: AdapterTypeField[];
-}
-
 const AdaptersPage = memo(function AdaptersPage() {
   const [loading, setLoading] = useState(false);
   const [data, setData] = useState<AdapterItem[]>([]);
@@ -185,14 +170,20 @@ const AdaptersPage = memo(function AdaptersPage() {
     return currentTypeMeta.config_schema.map(field => {
       const rules = field.required ? [{ required: true, message: t('Please input {label}', { label: field.label }) }] : [];
       let inputNode: any = <Input placeholder={field.placeholder} />;
+      let valuePropName: string | undefined;
       if (field.type === 'password') inputNode = <Input.Password placeholder={field.placeholder} />;
       if (field.type === 'number') inputNode = <Input type="number" placeholder={field.placeholder} />;
+      if (field.type === 'boolean') {
+        inputNode = <Switch />;
+        valuePropName = 'checked';
+      }
       return (
         <Form.Item
           key={field.key}
           name={['config', field.key]}
           label={t(field.label)}
           rules={rules}
+          valuePropName={valuePropName}
         >
           {inputNode}
         </Form.Item>

web/src/pages/FileExplorerPage/components/ContextMenu.tsx

@@ -61,7 +61,11 @@ export const ContextMenu: React.FC<ContextMenuProps> = (props) => {
     if (!entry.is_dir && processorTypes.length > 0) {
       const ext = entry.name.split('.').pop()?.toLowerCase() || '';
       processorSubMenu = processorTypes
-        .filter(pt => pt.supported_exts.includes(ext))
+        .filter(pt => {
+          const exts = pt.supported_exts;
+          if (!Array.isArray(exts) || exts.length === 0) return true;
+          return exts.includes(ext);
+        })
         .map(pt => ({
           key: 'processor-' + pt.type,
           label: pt.name,

web/src/pages/FileExplorerPage/components/FileDetailModal.tsx

@@ -1,6 +1,6 @@
 import React from 'react';
-import { Modal, Typography, Spin, theme, Card, Descriptions, Divider, Badge, Space, message } from 'antd';
-import { FileOutlined, FolderOutlined, CameraOutlined, InfoCircleOutlined } from '@ant-design/icons';
+import { Modal, Typography, Spin, theme, Card, Descriptions, Divider, Badge, Space, message, Collapse, Tag } from 'antd';
+import { FileOutlined, FolderOutlined, CameraOutlined, InfoCircleOutlined, DatabaseOutlined } from '@ant-design/icons';
 import { useI18n } from '../../../i18n';
 import type { VfsEntry } from '../../../api/client';
 
@@ -80,7 +80,63 @@ function formatFileSize(size: number | string, t: (k: string)=>string): string {
 export const FileDetailModal: React.FC<Props> = ({ entry, loading, data, onClose }) => {
   const { token } = theme.useToken();
   const { t } = useI18n();
-  
+  const vectorIndex = data?.vector_index;
+  const vectorEntries = Array.isArray(vectorIndex?.entries) ? vectorIndex.entries : [];
+  const primaryIndexEntries = vectorEntries.slice(0, 3);
+  const remainingIndexEntries = vectorEntries.slice(3);
+
+  const renderIndexEntry = (entry: any, idx: number, total: number) => {
+    const key = entry?.chunk_id ?? entry?.vector_id ?? idx;
+    const hasOffsets = entry?.start_offset !== undefined || entry?.end_offset !== undefined;
+    const previewText = entry?.preview;
+    const previewTruncated = Boolean(entry?.preview_truncated && previewText);
+
+    return (
+      <div
+        key={String(key)}
+        style={{
+          padding: '12px 0',
+          borderBottom: idx === total - 1 ? 'none' : `1px solid ${token.colorSplit}`,
+        }}
+      >
+        <Space direction="vertical" size={6} style={{ width: '100%' }}>
+          <Space size={[4, 4]} wrap>
+            {entry?.chunk_id && (
+              <Tag color="blue">{t('Chunk ID')}: {entry.chunk_id}</Tag>
+            )}
+            {entry?.type && (
+              <Tag>{entry.type}</Tag>
+            )}
+            {entry?.mime && (
+              <Tag color="geekblue">{entry.mime}</Tag>
+            )}
+            {entry?.name && !previewText && (
+              <Tag color="purple">{entry.name}</Tag>
+            )}
+          </Space>
+          {hasOffsets && (
+            <Typography.Text type="secondary" style={{ fontSize: 12 }}>
+              {t('Offset Range')}: {entry?.start_offset ?? '-'} ~ {entry?.end_offset ?? '-'}
+            </Typography.Text>
+          )}
+          {entry?.vector_id && (
+            <Typography.Text type="secondary" style={{ fontSize: 12 }}>
+              {t('Vector ID')}: {entry.vector_id}
+            </Typography.Text>
+          )}
+          {previewText && (
+            <Typography.Paragraph
+              style={{ marginBottom: 0 }}
+              ellipsis={{ rows: 3, expandable: previewTruncated }}
+            >
+              {previewText}
+            </Typography.Paragraph>
+          )}
+        </Space>
+      </div>
+    );
+  };
+
   return (
     <Modal
       title={
@@ -225,6 +281,82 @@ export const FileDetailModal: React.FC<Props> = ({ entry, loading, data, onClose
                   </>
                 )}
               </Card>
+
+              {!data.is_dir && vectorIndex && (
+                <Card
+                  size="small"
+                  style={{ borderRadius: 8, marginTop: 16 }}
+                  title={
+                    <Space>
+                      <DatabaseOutlined />
+                      {t('Index Info')}
+                    </Space>
+                  }
+                >
+                  <Descriptions
+                    column={1}
+                    size="small"
+                    items={[
+                      {
+                        key: 'total',
+                        label: t('Indexed Items'),
+                        children: vectorIndex.total ?? 0,
+                      },
+                      {
+                        key: 'types',
+                        label: t('Indexed Types'),
+                        children: Object.keys(vectorIndex.by_type || {}).length > 0 ? (
+                          <Space size={[4, 4]} wrap>
+                            {Object.entries(vectorIndex.by_type || {}).map(([type, count]) => (
+                              <Tag key={type}>{type} ({count as number})</Tag>
+                            ))}
+                          </Space>
+                        ) : (
+                          <Typography.Text type="secondary">{t('No index data')}</Typography.Text>
+                        ),
+                      },
+                    ]}
+                    contentStyle={{ fontSize: 14 }}
+                    labelStyle={{ fontWeight: 500, color: token.colorTextSecondary, width: '30%' }}
+                  />
+
+                  {vectorIndex.total ? (
+                    <div style={{ marginTop: 12 }}>
+                      <Typography.Text strong style={{ marginBottom: 8, display: 'block' }}>
+                        {t('Indexed Chunks')}
+                      </Typography.Text>
+                      <div style={{ maxHeight: '40vh', overflowY: 'auto', paddingRight: 8 }}>
+                        {primaryIndexEntries.map((entry: any, idx: number) => renderIndexEntry(entry, idx, primaryIndexEntries.length))}
+                        {remainingIndexEntries.length > 0 && (
+                          <Collapse
+                            bordered={false}
+                            size="small"
+                            items={[{
+                              key: 'more',
+                              label: t('More Indexed Chunks'),
+                              children: (
+                                <div>
+                                  {remainingIndexEntries.map((entry: any, idx: number) => renderIndexEntry(entry, idx, remainingIndexEntries.length))}
+                                </div>
+                              ),
+                            }]}
+                            style={{ background: 'transparent' }}
+                          />
+                        )}
+                      </div>
+                      {vectorIndex.has_more && (
+                        <Typography.Text type="secondary" style={{ fontSize: 12 }}>
+                          {t('Showing first {count} entries', { count: vectorEntries.length })}
+                        </Typography.Text>
+                      )}
+                    </div>
+                  ) : (
+                    <div style={{ marginTop: 12 }}>
+                      <Typography.Text type="secondary">{t('No index data')}</Typography.Text>
+                    </div>
+                  )}
+                </Card>
+              )}
             </div>
 
             {/* 右侧：EXIF 信息 */}

web/src/pages/LoginPage.tsx

@@ -6,6 +6,7 @@ import { useSystemStatus } from '../contexts/SystemContext';
 import { useNavigate } from 'react-router';
 import { useI18n } from '../i18n';
 import LanguageSwitcher from '../components/LanguageSwitcher';
+import WeChatModal from '../components/WeChatModal';
 
 const { Title, Text } = Typography;
 
@@ -16,6 +17,7 @@ export default function LoginPage() {
   const [password, setPassword] = useState('');
   const [err, setErr] = useState('');
   const [loading, setLoading] = useState(false);
+  const [wechatModalOpen, setWechatModalOpen] = useState(false);
   const navigate = useNavigate();
   const { t } = useI18n();
 
@@ -167,11 +169,12 @@ export default function LoginPage() {
               <Text type="secondary">{t('Join our community:')}</Text>
               <Button type="text" icon={<GithubOutlined />} href="https://github.com/DrizzleTime/Foxel" target="_blank">GitHub</Button>
               <Button type="text" icon={<SendOutlined />} href="https://t.me/+thDsBfyqJxZkNTU1" target="_blank">Telegram</Button>
-              <Button type="text" icon={<WechatOutlined />}>微信</Button>
+              <Button type="text" icon={<WechatOutlined />} onClick={() => setWechatModalOpen(true)}>微信</Button>
             </div>
           </div>
         </div>
       </div>
+      <WeChatModal open={wechatModalOpen} onClose={() => setWechatModalOpen(false)} />
     </div>
   );
 }

web/src/pages/ProcessorsPage.tsx

@@ -1,13 +1,16 @@
 import { memo, useCallback, useEffect, useMemo, useState } from 'react';
 import {
   Button,
+  Alert,
   Card,
   Empty,
   Flex,
   Form,
   Input,
+  InputNumber,
   message,
   Modal,
+  Segmented,
   Space,
   Spin,
   Switch,
@@ -134,23 +137,36 @@ const ProcessorsPage = memo(function ProcessorsPage() {
       overwrite: !!selectedProcessorMeta.produces_file,
       save_to: undefined,
       config: defaults,
+      directory_scope: 'current',
+      max_depth: undefined,
+      suffix: undefined,
     });
     setIsDirectory(false);
   }, [selectedProcessorMeta, form]);
 
-  const overwriteValue = Form.useWatch('overwrite', form) ?? false;
+  const producesFile = selectedProcessorMeta?.produces_file ?? false;
+  const overwriteWatch = Form.useWatch('overwrite', form);
+  const overwriteValue = producesFile ? !!overwriteWatch : false;
+  const directoryScope = Form.useWatch('directory_scope', form) ?? 'current';
 
   useEffect(() => {
     if (overwriteValue) {
-      form.setFieldsValue({ save_to: undefined });
+      form.setFieldsValue({ save_to: undefined, suffix: undefined });
     }
   }, [overwriteValue, form]);
 
   useEffect(() => {
     if (isDirectory) {
-      form.setFieldsValue({ overwrite: true, save_to: undefined });
+      form.setFieldsValue({
+        overwrite: producesFile ? true : false,
+        save_to: undefined,
+        directory_scope: 'current',
+        max_depth: undefined,
+      });
+    } else {
+      form.setFieldsValue({ suffix: undefined });
     }
-  }, [isDirectory, form]);
+  }, [isDirectory, form, producesFile]);
 
   const handleSelectProcessor = useCallback((type: string) => {
     if (type === selectedType) return;
@@ -232,17 +248,38 @@ const ProcessorsPage = memo(function ProcessorsPage() {
         }
       });
       setRunning(true);
-      const payload: any = {
-        path: values.path,
-        processor_type: selectedType,
-        config: finalConfig,
-        overwrite: !!values.overwrite,
-      };
-      if (values.save_to && !values.overwrite) {
-        payload.save_to = values.save_to;
+      const overwriteFlag = producesFile ? !!values.overwrite : false;
+      if (isDirectory) {
+        const scope: 'current' | 'recursive' = values.directory_scope || 'current';
+        let maxDepth: number | null = scope === 'current' ? 0 : null;
+        if (scope === 'recursive' && typeof values.max_depth === 'number') {
+          maxDepth = values.max_depth;
+        }
+        const suffixValue = producesFile && !overwriteFlag && typeof values.suffix === 'string'
+          ? values.suffix.trim() || null
+          : null;
+        const resp = await processorsApi.processDirectory({
+          path: values.path,
+          processor_type: selectedType,
+          config: finalConfig,
+          overwrite: overwriteFlag,
+          max_depth: maxDepth,
+          suffix: suffixValue,
+        });
+        messageApi.success(`${t('Task submitted')}: ${resp.scheduled}`);
+      } else {
+        const payload: any = {
+          path: values.path,
+          processor_type: selectedType,
+          config: finalConfig,
+          overwrite: overwriteFlag,
+        };
+        if (values.save_to && !overwriteFlag) {
+          payload.save_to = values.save_to;
+        }
+        const resp = await processorsApi.process(payload);
+        messageApi.success(`${t('Task submitted')}: ${resp.task_id}`);
       }
-      const resp = await processorsApi.process(payload);
-      messageApi.success(`${t('Task submitted')}: ${resp.task_id}`);
     } catch (err: any) {
       if (err?.errorFields) {
         return;
@@ -251,7 +288,7 @@ const ProcessorsPage = memo(function ProcessorsPage() {
     } finally {
       setRunning(false);
     }
-  }, [form, messageApi, selectedProcessorMeta, selectedType, t]);
+  }, [form, isDirectory, messageApi, producesFile, selectedProcessorMeta, selectedType, t]);
 
   const selectedConfigPath = pathModalField === 'path'
     ? (selectedType ? form.getFieldValue('path') : undefined) || '/'
@@ -379,11 +416,6 @@ const ProcessorsPage = memo(function ProcessorsPage() {
         <Form form={form} layout="vertical" disabled={!selectedType} style={{ padding: '12px 0' }}>
           {selectedType ? (
             <>
-              {isDirectory && (
-                <Text type="secondary" style={{ display: 'block', marginBottom: 12 }}>
-                  {t('Directory processing always overwrites original files')}
-                </Text>
-              )}
               <Form.Item
                 label={t('Target Path')}
                 required
@@ -402,16 +434,71 @@ const ProcessorsPage = memo(function ProcessorsPage() {
                   <Button onClick={() => openPathSelector('path', 'directory')}>{t('Select Directory')}</Button>
                 </Flex>
               </Form.Item>
+              {isDirectory && (
+                <Space direction="vertical" size={12} style={{ width: '100%', marginBottom: 12 }}>
+                  <Alert
+                    type="info"
+                    showIcon
+                    message={t('Directory execution will enqueue one task per file')}
+                  />
+                  <Form.Item name="directory_scope" label={t('Directory scope')} initialValue="current">
+                    <Segmented
+                      options={[
+                        { label: t('Current level only'), value: 'current' },
+                        { label: t('Include subdirectories'), value: 'recursive' },
+                      ]}
+                    />
+                  </Form.Item>
+                  {directoryScope === 'recursive' && (
+                    <Form.Item
+                      name="max_depth"
+                      label={t('Max depth')}
+                      extra={t('Leave empty to traverse all subdirectories')}
+                      rules={[{
+                        validator: async (_: any, value: number | null) => {
+                          if (value === undefined || value === null) return;
+                          if (value < 0) throw new Error(t('Depth must be greater or equal to 0'));
+                        },
+                      }]}
+                    >
+                      <InputNumber min={0} placeholder={t('Unlimited')} style={{ width: '100%' }} />
+                    </Form.Item>
+                  )}
+                </Space>
+              )}
 
-              <Form.Item
-                name="overwrite"
-                label={t('Overwrite original')}
-                valuePropName="checked"
-              >
-                <Switch disabled={isDirectory} />
-              </Form.Item>
+              {producesFile && (
+                <Form.Item
+                  name="overwrite"
+                  label={t('Overwrite original')}
+                  valuePropName="checked"
+                >
+                  <Switch />
+                </Form.Item>
+              )}
 
-              {selectedProcessorMeta?.produces_file && !overwriteValue && (
+              {isDirectory && producesFile && !overwriteValue && (
+                <Form.Item
+                  name="suffix"
+                  label={t('Output suffix')}
+                  rules={[
+                    { required: true, message: t('Please input a suffix') },
+                    {
+                      validator: async (_: any, value: string) => {
+                        if (typeof value !== 'string') return;
+                        if (!value.trim()) {
+                          throw new Error(t('Suffix cannot be empty'));
+                        }
+                      },
+                    },
+                  ]}
+                  extra={t('Suffix will be inserted before the file extension, e.g. demo_processed.mp4')}
+                >
+                  <Input placeholder={t('Suffix such as _processed')} />
+                </Form.Item>
+              )}
+
+              {!isDirectory && producesFile && !overwriteValue && (
                 <Form.Item label={t('Save To')}>
                   <Flex gap={8} align="center">
                     <div style={{ flex: 1 }}>

web/src/pages/SystemSettingsPage/SystemSettingsPage.tsx

@@ -8,14 +8,23 @@ import { useTheme } from '../../contexts/ThemeContext';
 import '../../styles/settings-tabs.css';
 import { useI18n } from '../../i18n';
 
-const APP_CONFIG_KEYS: {key: string, label: string, default?: string}[] = [
+const APP_CONFIG_KEYS: { key: string, label: string, default?: string }[] = [
   { key: 'APP_NAME', label: 'App Name' },
   { key: 'APP_LOGO', label: 'Logo URL' },
   { key: 'APP_DOMAIN', label: 'App Domain' },
   { key: 'FILE_DOMAIN', label: 'File Domain' },
 ];
 
-const VISION_CONFIG_KEYS = [
+interface AiConfigKeyBase {
+  key: string;
+  default?: string | number;
+}
+
+interface AiConfigKeyWithLabel extends AiConfigKeyBase {
+  label: string;
+}
+
+const VISION_CONFIG_KEYS: AiConfigKeyWithLabel[] = [
   { key: 'AI_VISION_API_URL', label: 'Vision API URL' },
   { key: 'AI_VISION_MODEL', label: 'Vision Model', default: 'Qwen/Qwen2.5-VL-32B-Instruct' },
   { key: 'AI_VISION_API_KEY', label: 'Vision API Key' },
@@ -24,13 +33,24 @@ const VISION_CONFIG_KEYS = [
 const DEFAULT_EMBED_DIMENSION = 4096;
 const EMBED_DIM_KEY = 'AI_EMBED_DIM';
 
-const EMBED_CONFIG_KEYS = [
+const EMBED_CONFIG_KEYS: AiConfigKeyWithLabel[] = [
   { key: 'AI_EMBED_API_URL', label: 'Embedding API URL' },
   { key: 'AI_EMBED_MODEL', label: 'Embedding Model', default: 'Qwen/Qwen3-Embedding-8B' },
   { key: 'AI_EMBED_API_KEY', label: 'Embedding API Key' },
 ];
 
-const ALL_AI_KEYS = [...VISION_CONFIG_KEYS, ...EMBED_CONFIG_KEYS, { key: EMBED_DIM_KEY, default: DEFAULT_EMBED_DIMENSION }];
+const RERANK_CONFIG_KEYS: AiConfigKeyWithLabel[] = [
+  { key: 'AI_RERANK_API_URL', label: 'Rerank API URL' },
+  { key: 'AI_RERANK_MODEL', label: 'Rerank Model' },
+  { key: 'AI_RERANK_API_KEY', label: 'Rerank API Key' },
+];
+
+const ALL_AI_KEYS: AiConfigKeyBase[] = [
+  ...VISION_CONFIG_KEYS,
+  ...EMBED_CONFIG_KEYS,
+  ...RERANK_CONFIG_KEYS,
+  { key: EMBED_DIM_KEY, default: DEFAULT_EMBED_DIMENSION },
+];
 
 const formatBytes = (bytes?: number | null) => {
   if (bytes === null || bytes === undefined) return '-';
@@ -194,6 +214,8 @@ export default function SystemSettingsPage() {
     }
   }, [buildProviderConfigValues, message, t, vectorConfigForm, vectorProviders]);
 
+  const vectorSectionLoading = vectorStatsLoading || vectorConfigLoading;
+
   // 离开“外观设置”时，恢复后端持久化配置（取消未保存的预览）
   useEffect(() => {
     if (activeTab !== 'appearance') {
@@ -303,7 +325,7 @@ export default function SystemSettingsPage() {
                     </Form.Item>
                   </Card>
                   <Card title={t('Advanced')} style={{ marginTop: 24 }}>
-                    <Form.Item name={THEME_KEYS.TOKENS} label={t('Override AntD Tokens (JSON)')} tooltip={t('e.g. {"colorText": "#222"}') }>
+                    <Form.Item name={THEME_KEYS.TOKENS} label={t('Override AntD Tokens (JSON)')} tooltip={t('e.g. {"colorText": "#222"}')}>
                       <Input.TextArea autoSize={{ minRows: 4 }} placeholder='{ "colorText": "#222" }' />
                     </Form.Item>
                     <Form.Item name={THEME_KEYS.CSS} label={t('Custom CSS')}>
@@ -402,6 +424,13 @@ export default function SystemSettingsPage() {
                       <InputNumber min={1} max={32768} style={{ width: '100%' }} />
                     </Form.Item>
                   </Card>
+                  <Card title={t('Rerank Model')} style={{ marginTop: 24 }}>
+                    {RERANK_CONFIG_KEYS.map(({ key, label }) => (
+                      <Form.Item key={key} name={key} label={t(label)}>
+                        <Input size="large" />
+                      </Form.Item>
+                    ))}
+                  </Card>
                   <Form.Item style={{ marginTop: 24 }}>
                     <Button type="primary" htmlType="submit" loading={loading} block>
                       {t('Save')}
@@ -428,178 +457,180 @@ export default function SystemSettingsPage() {
                           {t('Refresh')}
                         </Button>
                       </div>
-                      {vectorMetaError ? (
-                        <Alert type="error" showIcon message={vectorMetaError} />
-                      ) : null}
-                      {vectorStatsLoading && !vectorStats ? (
-                        <Spin />
-                      ) : vectorStats ? (
-                        <Space direction="vertical" size={16} style={{ width: '100%' }}>
-                          <div style={{ display: 'flex', flexWrap: 'wrap', gap: 24 }}>
-                            <div>
-                              <div style={{ color: '#888' }}>{t('Collections')}</div>
-                              <div style={{ fontSize: 20, fontWeight: 600 }}>{vectorStats.collection_count}</div>
-                            </div>
-                            <div>
-                              <div style={{ color: '#888' }}>{t('Vectors')}</div>
-                              <div style={{ fontSize: 20, fontWeight: 600 }}>{vectorStats.total_vectors}</div>
-                            </div>
-                            <div>
-                              <div style={{ color: '#888' }}>{t('Database Size')}</div>
-                              <div style={{ fontSize: 20, fontWeight: 600 }}>{formatBytes(vectorStats.db_file_size_bytes)}</div>
-                            </div>
-                            <div>
-                              <div style={{ color: '#888' }}>{t('Estimated Memory')}</div>
-                              <div style={{ fontSize: 20, fontWeight: 600 }}>{formatBytes(vectorStats.estimated_total_memory_bytes)}</div>
-                            </div>
-                          </div>
-                          {vectorStats.collections.length ? (
-                            <Space direction="vertical" style={{ width: '100%' }} size={16}>
-                              {vectorStats.collections.map((collection) => (
-                                <div key={collection.name} style={{ border: '1px solid #f0f0f0', borderRadius: 8, padding: 16 }}>
-                                  <Space direction="vertical" size={12} style={{ width: '100%' }}>
-                                    <div style={{ display: 'flex', justifyContent: 'space-between', alignItems: 'center', flexWrap: 'wrap', gap: 12 }}>
-                                      <strong>{collection.name}</strong>
-                                      <span style={{ color: '#888' }}>
-                                        {collection.is_vector_collection && collection.dimension
-                                          ? `${t('Dimension')}: ${collection.dimension}`
-                                          : t('Non-vector collection')}
-                                      </span>
-                                    </div>
-                                    <div>{t('Vectors')}: {collection.row_count}</div>
-                                    {collection.is_vector_collection ? (
-                                      <div>{t('Estimated memory')}: {formatBytes(collection.estimated_memory_bytes)}</div>
-                                    ) : null}
-                                    {collection.indexes.length ? (
-                                      <Space direction="vertical" size={4} style={{ width: '100%' }}>
-                                        <span>{t('Indexes')}:</span>
-                                        <ul style={{ paddingLeft: 20, margin: 0 }}>
-                                          {collection.indexes.map((index) => (
-                                            <li key={`${collection.name}-${index.index_name || 'default'}`}>
-                                              <span>{index.index_name || t('Unnamed index')}</span>
-                                              <span>{' · '}{index.index_type || '-'}</span>
-                                              <span>{' · '}{index.metric_type || '-'}</span>
-                                              <span>{' · '}{t('Indexed rows')}: {index.indexed_rows}</span>
-                                              <span>{' · '}{t('Pending rows')}: {index.pending_index_rows}</span>
-                                              <span>{' · '}{t('Status')}: {index.state || '-'}</span>
-                                            </li>
-                                          ))}
-                                        </ul>
-                                      </Space>
-                                    ) : null}
-                                  </Space>
+                      {vectorSectionLoading ? (
+                        <div style={{ display: 'flex', justifyContent: 'center', padding: '24px 0' }}>
+                          <Spin />
+                        </div>
+                      ) : (
+                        <>
+                          {vectorMetaError ? (
+                            <Alert type="error" showIcon message={vectorMetaError} />
+                          ) : null}
+                          {vectorStats ? (
+                            <Space direction="vertical" size={16} style={{ width: '100%' }}>
+                              <div style={{ display: 'flex', flexWrap: 'wrap', gap: 24 }}>
+                                <div>
+                                  <div style={{ color: '#888' }}>{t('Collections')}</div>
+                                  <div style={{ fontSize: 20, fontWeight: 600 }}>{vectorStats.collection_count}</div>
                                 </div>
-                              ))}
+                                <div>
+                                  <div style={{ color: '#888' }}>{t('Vectors')}</div>
+                                  <div style={{ fontSize: 20, fontWeight: 600 }}>{vectorStats.total_vectors}</div>
+                                </div>
+                                <div>
+                                  <div style={{ color: '#888' }}>{t('Database Size')}</div>
+                                  <div style={{ fontSize: 20, fontWeight: 600 }}>{formatBytes(vectorStats.db_file_size_bytes)}</div>
+                                </div>
+                                <div>
+                                  <div style={{ color: '#888' }}>{t('Estimated Memory')}</div>
+                                  <div style={{ fontSize: 20, fontWeight: 600 }}>{formatBytes(vectorStats.estimated_total_memory_bytes)}</div>
+                                </div>
+                              </div>
+                              {vectorStats.collections.length ? (
+                                <Space direction="vertical" style={{ width: '100%' }} size={16}>
+                                  {vectorStats.collections.map((collection) => (
+                                    <div key={collection.name} style={{ border: '1px solid #f0f0f0', borderRadius: 8, padding: 16 }}>
+                                      <Space direction="vertical" size={12} style={{ width: '100%' }}>
+                                        <div style={{ display: 'flex', justifyContent: 'space-between', alignItems: 'center', flexWrap: 'wrap', gap: 12 }}>
+                                          <strong>{collection.name}</strong>
+                                          <span style={{ color: '#888' }}>
+                                            {collection.is_vector_collection && collection.dimension
+                                              ? `${t('Dimension')}: ${collection.dimension}`
+                                              : t('Non-vector collection')}
+                                          </span>
+                                        </div>
+                                        <div>{t('Vectors')}: {collection.row_count}</div>
+                                        {collection.is_vector_collection ? (
+                                          <div>{t('Estimated memory')}: {formatBytes(collection.estimated_memory_bytes)}</div>
+                                        ) : null}
+                                        {collection.indexes.length ? (
+                                          <Space direction="vertical" size={4} style={{ width: '100%' }}>
+                                            <span>{t('Indexes')}:</span>
+                                            <ul style={{ paddingLeft: 20, margin: 0 }}>
+                                              {collection.indexes.map((index) => (
+                                                <li key={`${collection.name}-${index.index_name || 'default'}`}>
+                                                  <span>{index.index_name || t('Unnamed index')}</span>
+                                                  <span>{' · '}{index.index_type || '-'}</span>
+                                                  <span>{' · '}{index.metric_type || '-'}</span>
+                                                  <span>{' · '}{t('Indexed rows')}: {index.indexed_rows}</span>
+                                                  <span>{' · '}{t('Pending rows')}: {index.pending_index_rows}</span>
+                                                  <span>{' · '}{t('Status')}: {index.state || '-'}</span>
+                                                </li>
+                                              ))}
+                                            </ul>
+                                          </Space>
+                                        ) : null}
+                                      </Space>
+                                    </div>
+                                  ))}
+                                </Space>
+                              ) : (
+                                <Empty description={t('No collections')} />
+                              )}
+                              <div style={{ color: '#888' }}>
+                                {t('Estimated memory is calculated as vectors x dimension x 4 bytes (float32).')}
+                              </div>
                             </Space>
+                          ) : vectorStatsError ? (
+                            <div style={{ color: '#ff4d4f' }}>{vectorStatsError}</div>
                           ) : (
                             <Empty description={t('No collections')} />
                           )}
-                          <div style={{ color: '#888' }}>
-                            {t('Estimated memory is calculated as vectors x dimension x 4 bytes (float32).')}
-                          </div>
-                        </Space>
-                      ) : vectorStatsError ? (
-                        <div style={{ color: '#ff4d4f' }}>{vectorStatsError}</div>
-                      ) : (
-                        <Empty description={t('No collections')} />
+                          <Form
+                            layout="vertical"
+                            form={vectorConfigForm}
+                            onFinish={handleVectorConfigSave}
+                            initialValues={{ type: selectedProviderType || undefined, config: {} }}
+                          >
+                            <Form.Item
+                              name="type"
+                              label={t('Database Provider')}
+                              rules={[{ required: true, message: t('Please select a provider') }]}
+                            >
+                              <Select
+                                size="large"
+                                options={vectorProviders.map((provider) => ({
+                                  value: provider.type,
+                                  label: provider.enabled ? provider.label : `${provider.label} (${t('Coming soon')})`,
+                                  disabled: !provider.enabled,
+                                }))}
+                                onChange={handleProviderChange}
+                                loading={vectorConfigLoading && !vectorProviders.length}
+                              />
+                            </Form.Item>
+                            {selectedProvider?.description ? (
+                              <Alert
+                                type="info"
+                                showIcon
+                                message={t(selectedProvider.description)}
+                                style={{ marginBottom: 16 }}
+                              />
+                            ) : null}
+                            {selectedProvider?.config_schema?.map((field) => (
+                              <Form.Item
+                                key={field.key}
+                                name={['config', field.key]}
+                                label={t(field.label)}
+                                rules={field.required ? [{ required: true, message: t('Please input {label}', { label: t(field.label) }) }] : []}
+                              >
+                                {field.type === 'password' ? (
+                                  <Input.Password size="large" placeholder={field.placeholder ? t(field.placeholder) : undefined} />
+                                ) : (
+                                  <Input size="large" placeholder={field.placeholder ? t(field.placeholder) : undefined} />
+                                )}
+                              </Form.Item>
+                            ))}
+                            {selectedProvider && !selectedProvider.enabled ? (
+                              <Alert
+                                type="warning"
+                                showIcon
+                                message={t('This provider is not available yet')}
+                                style={{ marginBottom: 16 }}
+                              />
+                            ) : null}
+                            <Form.Item>
+                              <Space direction="vertical" style={{ width: '100%' }}>
+                                <Button
+                                  type="primary"
+                                  htmlType="submit"
+                                  loading={vectorConfigSaving}
+                                  block
+                                  disabled={!selectedProvider?.enabled}
+                                >
+                                  {t('Save')}
+                                </Button>
+                                <Button
+                                  danger
+                                  htmlType="button"
+                                  block
+                                  onClick={() => {
+                                    Modal.confirm({
+                                      title: t('Confirm clear vector database?'),
+                                      content: t('This will delete all collections irreversibly.'),
+                                      okText: t('Confirm Clear'),
+                                      okType: 'danger',
+                                      cancelText: t('Cancel'),
+                                      onOk: async () => {
+                                        try {
+                                          await vectorDBApi.clearAll();
+                                          message.success(t('Vector database cleared'));
+                                          await fetchVectorStats();
+                                          await fetchVectorMeta();
+                                        } catch (e: any) {
+                                          message.error(e.message || t('Clear failed'));
+                                        }
+                                      },
+                                    });
+                                  }}
+                                >
+                                  {t('Clear Vector DB')}
+                                </Button>
+                              </Space>
+                            </Form.Item>
+                          </Form>
+                        </>
                       )}
                     </Space>
-                    {vectorConfigLoading && !vectorProviders.length ? (
-                      <Spin />
-                    ) : (
-                      <Form
-                        layout="vertical"
-                        form={vectorConfigForm}
-                        onFinish={handleVectorConfigSave}
-                        initialValues={{ type: selectedProviderType || undefined, config: {} }}
-                      >
-                        <Form.Item
-                          name="type"
-                          label={t('Database Provider')}
-                          rules={[{ required: true, message: t('Please select a provider') }]}
-                        >
-                          <Select
-                            size="large"
-                            options={vectorProviders.map((provider) => ({
-                              value: provider.type,
-                              label: provider.enabled ? provider.label : `${provider.label} (${t('Coming soon')})`,
-                              disabled: !provider.enabled,
-                            }))}
-                            onChange={handleProviderChange}
-                            loading={vectorConfigLoading && !vectorProviders.length}
-                          />
-                        </Form.Item>
-                        {selectedProvider?.description ? (
-                          <Alert
-                            type="info"
-                            showIcon
-                            message={t(selectedProvider.description)}
-                            style={{ marginBottom: 16 }}
-                          />
-                        ) : null}
-                        {selectedProvider?.config_schema?.map((field) => (
-                          <Form.Item
-                            key={field.key}
-                            name={['config', field.key]}
-                            label={t(field.label)}
-                            rules={field.required ? [{ required: true, message: t('Please input {label}', { label: t(field.label) }) }] : []}
-                          >
-                            {field.type === 'password' ? (
-                              <Input.Password size="large" placeholder={field.placeholder ? t(field.placeholder) : undefined} />
-                            ) : (
-                              <Input size="large" placeholder={field.placeholder ? t(field.placeholder) : undefined} />
-                            )}
-                          </Form.Item>
-                        ))}
-                        {selectedProvider && !selectedProvider.enabled ? (
-                          <Alert
-                            type="warning"
-                            showIcon
-                            message={t('This provider is not available yet')}
-                            style={{ marginBottom: 16 }}
-                          />
-                        ) : null}
-                        <Form.Item>
-                          <Space direction="vertical" style={{ width: '100%' }}>
-                            <Button
-                              type="primary"
-                              htmlType="submit"
-                              loading={vectorConfigSaving}
-                              block
-                              disabled={!selectedProvider?.enabled}
-                            >
-                              {t('Save')}
-                            </Button>
-                            <Button
-                              danger
-                              htmlType="button"
-                              block
-                              onClick={() => {
-                                Modal.confirm({
-                                  title: t('Confirm clear vector database?'),
-                                  content: t('This will delete all collections irreversibly.'),
-                                  okText: t('Confirm Clear'),
-                                  okType: 'danger',
-                                  cancelText: t('Cancel'),
-                                  onOk: async () => {
-                                    try {
-                                      await vectorDBApi.clearAll();
-                                      message.success(t('Vector database cleared'));
-                                      await fetchVectorStats();
-                                      await fetchVectorMeta();
-                                    } catch (e: any) {
-                                      message.error(e.message || t('Clear failed'));
-                                    }
-                                  },
-                                });
-                              }}
-                            >
-                              {t('Clear Vector DB')}
-                            </Button>
-                          </Space>
-                        </Form.Item>
-                      </Form>
-                    )}
                   </Space>
                 </Card>
               ),