chore: update version to v1.2.8

CONTRIBUTING.md

@@ -1,76 +1,76 @@
+<div align="right">
+  <b>English</b> | <a href="./CONTRIBUTING_zh.md">简体中文</a>
+</div>
+
 # Contributing to Foxel
 
-🎉 首先，非常感谢您愿意花时间为 Foxel 做出贡献！
+We appreciate every minute you spend helping Foxel improve. This guide explains the contribution workflow so you can get started quickly.
 
-我们热烈欢迎各种形式的贡献。无论是报告 Bug、提出新功能建议、完善文档，还是直接提交代码，都将对项目产生积极的影响。
+## Table of Contents
 
-本指南将帮助您顺利地参与到项目中来。
-
-## 目录
-
-- [如何贡献](#如何贡献)
-  - [🐛 报告 Bug](#-报告-bug)
-  - [✨ 提交功能建议](#-提交功能建议)
-  - [🛠️ 贡献代码](#️-贡献代码)
-- [开发环境搭建](#开发环境搭建)
-  - [依赖准备](#依赖准备)
-  - [后端 (FastAPI)](#后端-fastapi)
-  - [前端 (React + Vite)](#前端-react--vite)
-- [代码贡献指南](#代码贡献指南)
-  - [贡献存储适配器 (Adapter)](#贡献存储适配器-adapter)
-  - [贡献前端应用 (App)](#贡献前端应用-app)
-- [提交规范](#提交规范)
-  - [Git 分支管理](#git-分支管理)
-  - [Commit Message 格式](#commit-message-格式)
-  - [Pull Request 流程](#pull-request-流程)
+- [How to Contribute](#how-to-contribute)
+  - [🐛 Report Bugs](#-report-bugs)
+  - [✨ Suggest Features](#-suggest-features)
+  - [🛠️ Contribute Code](#️-contribute-code)
+- [Development Environment](#development-environment)
+  - [Prerequisites](#prerequisites)
+  - [Backend (FastAPI)](#backend-fastapi)
+  - [Frontend (React + Vite)](#frontend-react--vite)
+- [Contribution Guidelines](#contribution-guidelines)
+  - [Storage Adapters](#storage-adapters)
+  - [Frontend Apps](#frontend-apps)
+- [Submission Rules](#submission-rules)
+  - [Git Branching](#git-branching)
+  - [Commit Message Format](#commit-message-format)
+  - [Pull Request Flow](#pull-request-flow)
 
 ---
 
-## 如何贡献
+## How to Contribute
 
-### 🐛 报告 Bug
+### 🐛 Report Bugs
 
-如果您在使用的过程中发现了 Bug，请通过 [GitHub Issues](https://github.com/DrizzleTime/Foxel/issues) 来报告。请在报告中提供以下信息：
+If you discover a bug, open a ticket via [GitHub Issues](https://github.com/DrizzleTime/Foxel/issues) and include:
 
-- **清晰的标题**：简明扼要地描述问题。
-- **复现步骤**：详细说明如何一步步重现该 Bug。
-- **期望行为** vs **实际行为**：描述您预期的结果和实际发生的情况。
-- **环境信息**：例如操作系统、浏览器版本、Foxel 版本等。
+- **A clear title** that summarises the problem.
+- **Reproduction steps** with enough detail to trigger the bug.
+- **Expected vs actual behaviour** to highlight the gap.
+- **Environment details** such as operating system, browser version, and the Foxel build you used.
 
-### ✨ 提交功能建议
+### ✨ Suggest Features
 
-我们欢迎任何关于新功能或改进的建议。请通过 [GitHub Issues](https://github.com/DrizzleTime/Foxel/issues) 创建一个 "Feature Request"，并详细阐述您的想法：
+To propose a new capability or an improvement, create an Issue and choose the "Feature Request" template. Document:
 
-- **问题描述**：说明该功能要解决什么问题。
-- **方案设想**：描述您希望该功能如何工作。
-- **相关信息**：提供任何有助于理解您想法的截图、链接或参考。
+- **Problem statement** – what pain point will the feature solve?
+- **Proposed solution** – how you expect it to work.
+- **Supporting material** – screenshots, references, or related links if helpful.
 
-### 🛠️ 贡献代码
+### 🛠️ Contribute Code
 
-如果您希望直接贡献代码，请参考下面的开发和提交流程。
+Follow the development setup below before opening a pull request. Keep changes focused and small so they are easier to review.
 
-## 开发环境搭建
+## Development Environment
 
-### 依赖准备
+### Prerequisites
 
-- **Git**: 用于版本控制。
-- **Python**: >= 3.13
-- **Bun**: 用于前端包管理和脚本运行。
+Install the following tooling first:
 
-### 后端 (FastAPI)
+- **Git** for version control
+- **Python** 3.13 or newer
+- **Bun** for frontend package management and scripts
 
-后端 API 服务基于 Python 和 FastAPI 构建。
+### Backend (FastAPI)
 
-1. **克隆仓库**
+1. **Clone the repository**
 
     ```bash
     git clone https://github.com/DrizzleTime/foxel.git
     cd Foxel
     ```
 
-2. **创建并激活 Python 虚拟环境**
+2. **Create and activate a virtual environment**
 
-    我们推荐使用 `uv` 来管理虚拟环境，以获得最佳性能。
+    `uv` is recommended for performance and reproducibility:
 
     ```bash
     uv venv
@@ -78,91 +78,85 @@
     # On Windows: .venv\Scripts\activate
     ```
 
-3. **安装依赖**
+3. **Install dependencies**
 
     ```bash
     uv sync
     ```
 
-4. **初始化环境**
+4. **Prepare local resources**
 
-    在启动服务前，请进行以下准备：
+    - Create the data directory:
 
-    - **创建数据目录**:
-      在项目根目录执行 `mkdir -p data/db`。这将创建用于存放数据库等文件的目录。
-      > [!IMPORTANT]
-      > 请确保应用拥有对 `data/db` 目录的读写权限。
+      ```bash
+      mkdir -p data/db
+      ```
 
-    - **创建 `.env` 配置文件**:
-      在项目根目录创建名为 `.env` 的文件，并填入以下内容。这些密钥用于保障应用安全，您可以按需修改。
+      Ensure the application user can read and write to `data/db`.
+
+    - Create an `.env` file in the project root and provide the required secrets. Replace the sample values with your own random strings:
 
       ```dotenv
       SECRET_KEY=EnsRhL9NFPxgFVc+7t96/y70DIOR+9SpntcIqQa90TU=
       TEMP_LINK_SECRET_KEY=EnsRhL9NFPxgFVc+7t96/y70DIOR+9SpntcIqQa90TU=
       ```
 
-5. **启动开发服务器**
+5. **Start the development server**
 
     ```bash
     uvicorn main:app --reload --host 0.0.0.0 --port 8000
     ```
 
-    API 服务将在 `http://localhost:8000` 上运行，您可以通过 `http://localhost:8000/docs` 访问自动生成的 API 文档。
+    The API is available at `http://localhost:8000`, and the interactive docs live at `http://localhost:8000/docs`.
 
-### 前端 (React + Vite)
+### Frontend (React + Vite)
 
-前端应用使用 React, Vite, 和 TypeScript 构建。
-
-1. **进入前端目录**
+1. **Enter the frontend directory**
 
     ```bash
     cd web
     ```
 
-2. **安装依赖**
+2. **Install dependencies**
 
     ```bash
     bun install
     ```
 
-3. **启动开发服务器**
+3. **Run the dev server**
 
     ```bash
     bun run dev
     ```
 
-    前端开发服务器将在 `http://localhost:5173` 运行。它已经配置了代理，会自动将 `/api` 请求转发到后端服务。
+    The Vite dev server runs at `http://localhost:5173` and proxies `/api` requests to the backend.
 
-## 代码贡献指南
+## Contribution Guidelines
 
-### 贡献存储适配器 (Adapter)
+### Storage Adapters
 
-存储适配器是 Foxel 的核心扩展点，用于接入不同的存储后端 (如 S3, FTP, Alist 等)。
+Storage adapters integrate new storage providers (for example S3, FTP, or Alist).
 
-1. **创建适配器文件**: 在 [`services/adapters/`](services/adapters/) 目录下，创建一个新文件，例如 `my_new_adapter.py`。
-2. **实现适配器类**:
-    - 创建一个类，继承自 [`services.adapters.base.BaseAdapter`](services/adapters/base.py)。
-    - 实现 `BaseAdapter` 中定义的所有抽象方法，如 `list_dir`, `get_meta`, `upload`, `download` 等。请仔细阅读基类中的文档注释以理解每个方法的作用和参数。
+1. Create a new module under [`services/adapters/`](services/adapters/) (for example `my_new_adapter.py`).
+2. Implement a class that inherits from [`services.adapters.base.BaseAdapter`](services/adapters/base.py) and provide concrete implementations for the abstract methods such as `list_dir`, `get_meta`, `upload`, and `download`.
 
-### 贡献前端应用 (App)
+### Frontend Apps
 
-前端应用允许用户在浏览器中直接预览或编辑特定类型的文件。
+Frontend apps enable in-browser previews or editors for specific file types.
 
-1. **创建应用组件**: 在 [`web/src/apps/`](web/src/apps/) 目录下，为您的应用创建一个新的文件夹，并在其中创建 React 组件。
-2. **定义应用类型**: 您的应用需要实现 [`web/src/apps/types.ts`](web/src/apps/types.ts) 中定义的 `FoxelApp` 接口。
-3. **注册应用**: 在 [`web/src/apps/registry.ts`](web/src/apps/registry.ts) 中，导入您的应用组件，并将其添加到 `APP_REGISTRY`。在注册时，您需要指定该应用可以处理的文件类型（通过 MIME Type 或文件扩展名）。
+1. Add a new folder in [`web/src/apps/`](web/src/apps/) for your app and expose a React component.
+2. Implement the `FoxelApp` interface defined in [`web/src/apps/types.ts`](web/src/apps/types.ts).
+3. Register the app in [`web/src/apps/registry.ts`](web/src/apps/registry.ts) and declare the MIME types or extensions it supports.
 
-## 提交规范
+## Submission Rules
 
-### Git 分支管理
+### Git Branching
 
-- 从最新的 `main` 分支创建您的特性分支。
+Start your work from the latest `main` branch and push feature changes on a dedicated branch.
 
-### Commit Message 格式
+### Commit Message Format
 
-我们遵循 [Conventional Commits](https://www.conventionalcommits.org/) 规范。这有助于自动化生成更新日志和版本管理。
-
-Commit Message 格式如下:
+We follow the [Conventional Commits](https://www.conventionalcommits.org/) specification to drive release tooling.
 
 ```
 <type>(<scope>): <subject>
@@ -172,27 +166,27 @@ Commit Message 格式如下:
 <footer>
 ```
 
-- **type**: `feat`, `fix`, `docs`, `style`, `refactor`, `test`, `chore` 等。
-- **scope**: (可选) 本次提交影响的范围，例如 `adapter`, `ui`, `api`。
-- **subject**: 简明扼要的描述。
+- **type**: e.g. `feat`, `fix`, `docs`, `style`, `refactor`, `test`, `chore`.
+- **scope** (optional): the area impacted by the change, such as `adapter`, `ui`, or `api`.
+- **subject**: a concise summary written in the imperative mood.
 
-**示例:**
+**Examples:**
 
 ```
-feat(adapter): Add support for Alist storage
+feat(adapter): add support for Alist storage
 ```
 
 ```
-fix(ui): Correct display issue in file list view
+fix(ui): correct display issue in file list view
 ```
 
-### Pull Request 流程
+### Pull Request Flow
 
-1. Fork 仓库并克隆到本地。
-2. 创建并切换到您的特性分支。
-3. 完成代码编写和测试。
-4. 将您的分支推送到您的 Fork 仓库。
-5. 在 Foxel 主仓库创建一个 Pull Request，目标分支为 `main`。
-6. 在 PR 描述中清晰地说明您的更改内容、目的和任何相关的 Issue 编号。
+1. Fork the repository and clone it locally.
+2. Create and switch to your feature branch.
+3. Implement the change and run relevant checks.
+4. Push the branch to your fork.
+5. Open a pull request against `main` in the Foxel repository.
+6. Explain the change set, its motivation, and reference related Issues in the PR description.
 
-项目维护者会尽快审查您的 PR。感谢您的耐心和贡献！
+Maintainers will review your pull request as soon as possible.

CONTRIBUTING_zh.md

@@ -0,0 +1,202 @@
+<div align="right">
+  <a href="./CONTRIBUTING.md">English</a> | <b>简体中文</b>
+</div>
+
+# Contributing to Foxel
+
+🎉 首先，非常感谢您愿意花时间为 Foxel 做出贡献！
+
+我们热烈欢迎各种形式的贡献。无论是报告 Bug、提出新功能建议、完善文档，还是直接提交代码，都将对项目产生积极的影响。
+
+本指南将帮助您顺利地参与到项目中来。
+
+## 目录
+
+- [如何贡献](#如何贡献)
+  - [🐛 报告 Bug](#-报告-bug)
+  - [✨ 提交功能建议](#-提交功能建议)
+  - [🛠️ 贡献代码](#️-贡献代码)
+- [开发环境搭建](#开发环境搭建)
+  - [依赖准备](#依赖准备)
+  - [后端 (FastAPI)](#后端-fastapi)
+  - [前端 (React + Vite)](#前端-react--vite)
+- [代码贡献指南](#代码贡献指南)
+  - [贡献存储适配器 (Adapter)](#贡献存储适配器-adapter)
+  - [贡献前端应用 (App)](#贡献前端应用-app)
+- [提交规范](#提交规范)
+  - [Git 分支管理](#git-分支管理)
+  - [Commit Message 格式](#commit-message-格式)
+  - [Pull Request 流程](#pull-request-流程)
+
+---
+
+## 如何贡献
+
+### 🐛 报告 Bug
+
+如果您在使用的过程中发现了 Bug，请通过 [GitHub Issues](https://github.com/DrizzleTime/Foxel/issues) 来报告。请在报告中提供以下信息：
+
+- **清晰的标题**：简明扼要地描述问题。
+- **复现步骤**：详细说明如何一步步重现该 Bug。
+- **期望行为** vs **实际行为**：描述您预期的结果和实际发生的情况。
+- **环境信息**：例如操作系统、浏览器版本、Foxel 版本等。
+
+### ✨ 提交功能建议
+
+我们欢迎任何关于新功能或改进的建议。请通过 [GitHub Issues](https://github.com/DrizzleTime/Foxel/issues) 创建一个 "Feature Request"，并详细阐述您的想法：
+
+- **问题描述**：说明该功能要解决什么问题。
+- **方案设想**：描述您希望该功能如何工作。
+- **相关信息**：提供任何有助于理解您想法的截图、链接或参考。
+
+### 🛠️ 贡献代码
+
+如果您希望直接贡献代码，请参考下面的开发和提交流程。
+
+## 开发环境搭建
+
+### 依赖准备
+
+- **Git**: 用于版本控制。
+- **Python**: >= 3.13
+- **Bun**: 用于前端包管理和脚本运行。
+
+### 后端 (FastAPI)
+
+后端 API 服务基于 Python 和 FastAPI 构建。
+
+1. **克隆仓库**
+
+    ```bash
+    git clone https://github.com/DrizzleTime/foxel.git
+    cd Foxel
+    ```
+
+2. **创建并激活 Python 虚拟环境**
+
+    我们推荐使用 `uv` 来管理虚拟环境，以获得最佳性能。
+
+    ```bash
+    uv venv
+    source .venv/bin/activate
+    # On Windows: .venv\Scripts\activate
+    ```
+
+3. **安装依赖**
+
+    ```bash
+    uv sync
+    ```
+
+4. **初始化环境**
+
+    在启动服务前，请进行以下准备：
+
+    - **创建数据目录**:
+      在项目根目录执行 `mkdir -p data/db`。这将创建用于存放数据库等文件的目录。
+      > [!IMPORTANT]
+      > 请确保应用拥有对 `data/db` 目录的读写权限。
+
+    - **创建 `.env` 配置文件**:
+      在项目根目录创建名为 `.env` 的文件，并填入以下内容。这些密钥用于保障应用安全，您可以按需修改。
+
+      ```dotenv
+      SECRET_KEY=EnsRhL9NFPxgFVc+7t96/y70DIOR+9SpntcIqQa90TU=
+      TEMP_LINK_SECRET_KEY=EnsRhL9NFPxgFVc+7t96/y70DIOR+9SpntcIqQa90TU=
+      ```
+
+5. **启动开发服务器**
+
+    ```bash
+    uvicorn main:app --reload --host 0.0.0.0 --port 8000
+    ```
+
+    API 服务将在 `http://localhost:8000` 上运行，您可以通过 `http://localhost:8000/docs` 访问自动生成的 API 文档。
+
+### 前端 (React + Vite)
+
+前端应用使用 React, Vite, 和 TypeScript 构建。
+
+1. **进入前端目录**
+
+    ```bash
+    cd web
+    ```
+
+2. **安装依赖**
+
+    ```bash
+    bun install
+    ```
+
+3. **启动开发服务器**
+
+    ```bash
+    bun run dev
+    ```
+
+    前端开发服务器将在 `http://localhost:5173` 运行。它已经配置了代理，会自动将 `/api` 请求转发到后端服务。
+
+## 代码贡献指南
+
+### 贡献存储适配器 (Adapter)
+
+存储适配器是 Foxel 的核心扩展点，用于接入不同的存储后端 (如 S3, FTP, Alist 等)。
+
+1. **创建适配器文件**: 在 [`services/adapters/`](services/adapters/) 目录下，创建一个新文件，例如 `my_new_adapter.py`。
+2. **实现适配器类**:
+    - 创建一个类，继承自 [`services.adapters.base.BaseAdapter`](services/adapters/base.py)。
+    - 实现 `BaseAdapter` 中定义的所有抽象方法，如 `list_dir`, `get_meta`, `upload`, `download` 等。请仔细阅读基类中的文档注释以理解每个方法的作用和参数。
+
+### 贡献前端应用 (App)
+
+前端应用允许用户在浏览器中直接预览或编辑特定类型的文件。
+
+1. **创建应用组件**: 在 [`web/src/apps/`](web/src/apps/) 目录下，为您的应用创建一个新的文件夹，并在其中创建 React 组件。
+2. **定义应用类型**: 您的应用需要实现 [`web/src/apps/types.ts`](web/src/apps/types.ts) 中定义的 `FoxelApp` 接口。
+3. **注册应用**: 在 [`web/src/apps/registry.ts`](web/src/apps/registry.ts) 中，导入您的应用组件，并将其添加到 `APP_REGISTRY`。在注册时，您需要指定该应用可以处理的文件类型（通过 MIME Type 或文件扩展名）。
+
+## 提交规范
+
+### Git 分支管理
+
+- 从最新的 `main` 分支创建您的特性分支。
+
+### Commit Message 格式
+
+我们遵循 [Conventional Commits](https://www.conventionalcommits.org/) 规范。这有助于自动化生成更新日志和版本管理。
+
+Commit Message 格式如下:
+
+```
+<type>(<scope>): <subject>
+<BLANK LINE>
+<body>
+<BLANK LINE>
+<footer>
+```
+
+- **type**: `feat`, `fix`, `docs`, `style`, `refactor`, `test`, `chore` 等。
+- **scope**: (可选) 本次提交影响的范围，例如 `adapter`, `ui`, `api`。
+- **subject**: 简明扼要的描述。
+
+**示例:**
+
+```
+feat(adapter): Add support for Alist storage
+```
+
+```
+fix(ui): Correct display issue in file list view
+```
+
+### Pull Request 流程
+
+1. Fork 仓库并克隆到本地。
+2. 创建并切换到您的特性分支。
+3. 完成代码编写和测试。
+4. 将您的分支推送到您的 Fork 仓库。
+5. 在 Foxel 主仓库创建一个 Pull Request，目标分支为 `main`。
+6. 在 PR 描述中清晰地说明您的更改内容、目的和任何相关的 Issue 编号。
+
+项目维护者会尽快审查您的 PR。感谢您的耐心和贡献！

Dockerfile

@@ -27,6 +27,9 @@ COPY . .
 
 COPY nginx.conf /etc/nginx/nginx.conf
 
+RUN mkdir -p data/db data/mount && \
+    chmod 777 data/db data/mount
+    
 EXPOSE 80
 
 COPY entrypoint.sh /entrypoint.sh

README.md

@@ -73,7 +73,7 @@ chmod 777 data/db data/mount
 
 We welcome contributions from the community! Whether it's submitting bugs, suggesting new features, or contributing code directly.
 
-Before you start, please read our [`CONTRIBUTING.md`](CONTRIBUTING.md) file, which will guide you on how to set up your development environment and the submission process.
+Before you start, please read our [`CONTRIBUTING.md`](CONTRIBUTING.md) file, which explains the development environment and submission process. A Simplified Chinese translation is available in [`CONTRIBUTING_zh.md`](CONTRIBUTING_zh.md).
 
 ## 🌐 Community
 

README_zh.md

@@ -74,7 +74,7 @@ chmod 777 data/db data/mount
 
 我们非常欢迎来自社区的贡献！无论是提交 Bug、建议新功能还是直接贡献代码。
 
-在开始之前，请先阅读我们的 [`CONTRIBUTING.md`](CONTRIBUTING.md) 文件，它会指导你如何设置开发环境以及提交流程。
+在开始之前，请先阅读我们的 [`CONTRIBUTING_zh.md`](CONTRIBUTING_zh.md) 文件，它会指导你如何设置开发环境以及提交流程。
 
 ## 🌐 社区
 

api/routes/config.py

@@ -1,10 +1,11 @@
 import httpx
 import time
-from fastapi import APIRouter, Depends, Form
+from fastapi import APIRouter, Depends, Form, HTTPException
 from typing import Annotated
 from services.config import ConfigCenter, VERSION
 from services.auth import get_current_active_user, User, has_users
 from api.response import success
+from services.vector_db import VectorDBService
 router = APIRouter(prefix="/api/config", tags=["config"])
 
 
@@ -23,8 +24,27 @@ async def set_config(
     key: str = Form(...),
     value: str = Form(...)
 ):
-    await ConfigCenter.set(key, value)
-    return success({"key": key, "value": value})
+    original_value = await ConfigCenter.get(key)
+    value_to_save = value
+    if key == "AI_EMBED_DIM":
+        try:
+            parsed_value = int(value)
+        except (TypeError, ValueError):
+            raise HTTPException(status_code=400, detail="AI_EMBED_DIM must be an integer")
+        if parsed_value <= 0:
+            raise HTTPException(status_code=400, detail="AI_EMBED_DIM must be greater than zero")
+        value_to_save = str(parsed_value)
+
+    await ConfigCenter.set(key, value_to_save)
+
+    if key == "AI_EMBED_DIM" and str(original_value) != value_to_save:
+        try:
+            service = VectorDBService()
+            await service.clear_all_data()
+        except Exception as exc:
+            raise HTTPException(status_code=500, detail=f"Failed to clear vector database: {exc}")
+
+    return success({"key": key, "value": value_to_save})
 
 
 @router.get("/all")

api/routes/processors.py

@@ -1,10 +1,17 @@
-from fastapi import APIRouter, Depends, Body
+from pathlib import Path
+from fastapi import APIRouter, Depends, Body, HTTPException
+from fastapi.concurrency import run_in_threadpool
 from typing import Annotated
-from services.processors.registry import get_config_schemas
+from services.processors.registry import (
+    get_config_schemas,
+    get_module_path,
+    reload_processors,
+)
 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
 
 router = APIRouter(prefix="/api/processors", tags=["processors"])
 
@@ -22,6 +29,7 @@ async def list_processors(
             "supported_exts": meta.get("supported_exts", []),
             "config_schema": meta["config_schema"],
             "produces_file": meta.get("produces_file", False),
+            "module_path": meta.get("module_path"),
         })
     return success(out)
 
@@ -34,12 +42,20 @@ class ProcessRequest(BaseModel):
     overwrite: bool = False
 
 
+class UpdateSourceRequest(BaseModel):
+    source: str
+
+
 @router.post("/process")
 async def process_file_with_processor(
     current_user: Annotated[User, Depends(get_current_active_user)],
     req: ProcessRequest = Body(...)
 ):
-    save_to = req.path if req.overwrite else req.save_to
+    is_dir = await path_is_directory(req.path)
+    if is_dir and not req.overwrite:
+        raise HTTPException(400, detail="Directory processing requires overwrite")
+
+    save_to = None if is_dir else (req.path if req.overwrite else req.save_to)
     task = await task_queue_service.add_task(
         "process_file",
         {
@@ -47,6 +63,54 @@ async def process_file_with_processor(
             "processor_type": req.processor_type,
             "config": req.config,
             "save_to": save_to,
+            "overwrite": req.overwrite,
         },
     )
     return success({"task_id": task.id})
+
+
+@router.get("/source/{processor_type}")
+async def get_processor_source(
+    processor_type: str,
+    current_user: Annotated[User, Depends(get_current_active_user)],
+):
+    module_path = get_module_path(processor_type)
+    if not module_path:
+        raise HTTPException(404, detail="Processor not found")
+    path_obj = Path(module_path)
+    if not path_obj.exists():
+        raise HTTPException(404, detail="Processor source not found")
+    try:
+        content = await run_in_threadpool(path_obj.read_text, encoding='utf-8')
+    except Exception as exc:
+        raise HTTPException(500, detail=f"Failed to read source: {exc}")
+    return success({"source": content, "module_path": str(path_obj)})
+
+
+@router.put("/source/{processor_type}")
+async def update_processor_source(
+    processor_type: str,
+    req: UpdateSourceRequest,
+    current_user: Annotated[User, Depends(get_current_active_user)],
+):
+    module_path = get_module_path(processor_type)
+    if not module_path:
+        raise HTTPException(404, detail="Processor not found")
+    path_obj = Path(module_path)
+    if not path_obj.exists():
+        raise HTTPException(404, detail="Processor source not found")
+    try:
+        await run_in_threadpool(path_obj.write_text, req.source, encoding='utf-8')
+    except Exception as exc:
+        raise HTTPException(500, detail=f"Failed to write source: {exc}")
+    return success(True)
+
+
+@router.post("/reload")
+async def reload_processor_modules(
+    current_user: Annotated[User, Depends(get_current_active_user)],
+):
+    errors = reload_processors()
+    if errors:
+        raise HTTPException(500, detail="; ".join(errors))
+    return success(True)

api/routes/search.py

@@ -9,7 +9,7 @@ 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 = vector_db.search_vectors("vector_collection", embedding, top_k)
+    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]
@@ -18,7 +18,7 @@ async def search_files_by_vector(q: str, top_k: int):
 
 async def search_files_by_name(q: str, top_k: int):
     vector_db = VectorDBService()
-    results = vector_db.search_by_path("vector_collection", q, top_k)
+    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])
@@ -38,4 +38,4 @@ async def search_files(
     elif mode == "filename":
         return await search_files_by_name(q, top_k)
     else:
-        return {"items": [], "query": q, "error": "Invalid search mode"}
+        return {"items": [], "query": q, "error": "Invalid search mode"}

api/routes/share.py

@@ -83,6 +83,18 @@ async def get_my_shares(current_user: User = Depends(get_current_active_user)):
     return [ShareInfo.from_orm(s) for s in shares]
 
 
+@router.delete("/expired")
+async def delete_expired_shares(
+    current_user: User = Depends(get_current_active_user),
+):
+    """
+    删除当前用户的所有已过期分享。
+    """
+    user_account = await UserAccount.get(id=current_user.id)
+    deleted_count = await share_service.delete_expired_shares(user=user_account)
+    return success({"deleted_count": deleted_count})
+
+
 @router.delete("/{share_id}")
 async def delete_share(
     share_id: int,

api/routes/vector_db.py

@@ -1,19 +1,100 @@
+from typing import Any, Dict
+
 from fastapi import APIRouter, Depends, HTTPException
+from pydantic import BaseModel, Field
+
 from services.auth import get_current_active_user
 from models.database import UserAccount
-from services.vector_db import VectorDBService
+from services.vector_db import (
+    VectorDBService,
+    VectorDBConfigManager,
+    list_providers,
+    get_provider_entry,
+)
+from services.vector_db.providers import get_provider_class
 from api.response import success
 
 router = APIRouter(prefix="/api/vector-db", tags=["vector-db"])
 
 
+class VectorDBConfigPayload(BaseModel):
+    type: str = Field(..., description="向量数据库提供者类型")
+    config: Dict[str, Any] = Field(default_factory=dict, description="提供者配置参数")
+
+
 @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()
-        service.clear_all_data()
+        await service.clear_all_data()
         return success(msg="向量数据库已清空")
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@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()
+        return success(data=data)
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@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)
+
+
+@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}")
+    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")
+
+    # 先尝试建立连接，确保配置有效
+    test_provider = provider_cls(payload.config)
+    try:
+        await test_provider.initialize()
+    except Exception as exc:
+        raise HTTPException(status_code=400, detail=str(exc))
+    finally:
+        client = getattr(test_provider, "client", None)
+        close_fn = getattr(client, "close", None)
+        if callable(close_fn):
+            try:
+                close_fn()
+            except Exception:
+                pass
+
+    await VectorDBConfigManager.save_config(payload.type, payload.config)
+    service = VectorDBService()
+    await service.reload()
+    config_data = await service.current_provider()
+    stats = await service.get_all_stats()
+    return success({"config": config_data, "stats": stats})

nginx.conf

@@ -28,7 +28,7 @@ http {
         listen 80;
         server_name _;
 
-        location ~ ^/(api|docs|openapi\.json$) {
+        location ~ ^/(api|webdav|docs|openapi\.json$) {
             proxy_pass http://127.0.0.1:8000;
             proxy_set_header Host $host;
             proxy_set_header X-Real-IP $remote_addr;

pyproject.toml

@@ -64,6 +64,7 @@ dependencies = [
     "python-multipart==0.0.20",
     "pytz==2025.2",
     "pyyaml==6.0.2",
+    "qdrant-client==1.15.1",
     "rawpy==0.25.1",
     "rich==14.1.0",
     "rich-toolkit==0.15.0",

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 = "v1.2.4"
+VERSION = "v1.2.8"
 
 class ConfigCenter:
     _cache: Dict[str, Any] = {}

services/processors/registry.py

@@ -1,33 +1,53 @@
-import pkgutil
 import inspect
-from importlib import import_module
-from typing import Dict, Callable
+import pkgutil
+from importlib import import_module, reload
+from pathlib import Path
+from types import ModuleType
+from typing import Callable, Dict, Optional
+
 from .base import BaseProcessor
 
 ProcessorFactory = Callable[[], BaseProcessor]
 TYPE_MAP: Dict[str, ProcessorFactory] = {}
 CONFIG_SCHEMAS: Dict[str, dict] = {}
+MODULE_MAP: Dict[str, ModuleType] = {}
+LAST_DISCOVERY_ERRORS: list[str] = []
+
+
+def discover_processors(force_reload: bool = False) -> list[str]:
+    """Discover available processor modules and cache their metadata."""
+    import services.processors  # 延迟导入以避免循环
 
-def discover_processors():
-    import services.processors
     processors_pkg = services.processors
     TYPE_MAP.clear()
     CONFIG_SCHEMAS.clear()
+    MODULE_MAP.clear()
+
+    global LAST_DISCOVERY_ERRORS
+    LAST_DISCOVERY_ERRORS = []
+
     for modinfo in pkgutil.iter_modules(processors_pkg.__path__):
         if modinfo.name.startswith("_"):
             continue
+
         full_name = f"{processors_pkg.__name__}.{modinfo.name}"
         try:
             module = import_module(full_name)
-        except Exception:
+            if force_reload:
+                module = reload(module)
+        except Exception as exc:
+            LAST_DISCOVERY_ERRORS.append(f"Failed to import {full_name}: {exc}")
             continue
+
         processor_type = getattr(module, "PROCESSOR_TYPE", None)
         processor_name = getattr(module, "PROCESSOR_NAME", None)
         supported_exts = getattr(module, "SUPPORTED_EXTS", None)
         schema = getattr(module, "CONFIG_SCHEMA", None)
         factory = getattr(module, "PROCESSOR_FACTORY", None)
+
         if not processor_type:
             continue
+
         if factory is None:
             for attr in module.__dict__.values():
                 if inspect.isclass(attr) and attr.__name__.endswith("Processor"):
@@ -35,31 +55,85 @@ def discover_processors():
                         return lambda: cls()
                     factory = _mk()
                     break
+
         if not callable(factory):
+            LAST_DISCOVERY_ERRORS.append(f"Processor {full_name} missing factory")
             continue
+
+        try:
+            sample = factory()
+        except Exception as exc:
+            LAST_DISCOVERY_ERRORS.append(f"Failed to instantiate processor {processor_type}: {exc}")
+            continue
+
         TYPE_MAP[processor_type] = factory
+        MODULE_MAP[processor_type] = module
+
         produces_file = getattr(module, "produces_file", None)
-        if produces_file is None and hasattr(factory(), "produces_file"):
-            produces_file = getattr(factory(), "produces_file")
+        if produces_file is None and hasattr(sample, "produces_file"):
+            produces_file = getattr(sample, "produces_file")
+
+        module_file = getattr(module, "__file__", None)
+        module_path: Optional[str] = None
+        if module_file:
+            try:
+                module_path = str(Path(module_file).resolve())
+            except Exception:
+                module_path = module_file
+
+        if isinstance(supported_exts, list):
+            normalized_exts = [str(ext) for ext in supported_exts]
+        elif supported_exts:
+            normalized_exts = [str(supported_exts)]
+        else:
+            normalized_exts = []
+
+        if not normalized_exts and hasattr(sample, "supported_exts"):
+            sample_exts = getattr(sample, "supported_exts") or []
+            if isinstance(sample_exts, list):
+                normalized_exts = [str(ext) for ext in sample_exts]
+
         if isinstance(schema, list):
             CONFIG_SCHEMAS[processor_type] = {
                 "type": processor_type,
                 "name": processor_name or processor_type,
-                "supported_exts": supported_exts or [],
+                "supported_exts": normalized_exts,
                 "config_schema": schema,
-                "produces_file": produces_file if produces_file is not None else False
+                "produces_file": produces_file if produces_file is not None else False,
+                "module_path": module_path,
             }
 
+    return LAST_DISCOVERY_ERRORS
+
+
 def get_config_schemas() -> Dict[str, dict]:
     return CONFIG_SCHEMAS
 
+
 def get_config_schema(processor_type: str):
     return CONFIG_SCHEMAS.get(processor_type)
 
+
 def get(processor_type: str) -> BaseProcessor:
     factory = TYPE_MAP.get(processor_type)
     if factory:
         return factory()
     return None
 
+
+def get_module_path(processor_type: str) -> Optional[str]:
+    meta = CONFIG_SCHEMAS.get(processor_type)
+    if not meta:
+        return None
+    return meta.get("module_path")
+
+
+def get_last_discovery_errors() -> list[str]:
+    return LAST_DISCOVERY_ERRORS
+
+
+def reload_processors() -> list[str]:
+    return discover_processors(force_reload=True)
+
+
 discover_processors()

services/processors/vector_index.py

@@ -2,8 +2,9 @@ from typing import Dict, Any
 from fastapi.responses import Response
 import base64
 from services.ai import describe_image_base64, get_text_embedding
-from services.vector_db import VectorDBService
+from services.vector_db import VectorDBService, DEFAULT_VECTOR_DIMENSION
 from services.logging import LogService
+from services.config import ConfigCenter
 
 
 class VectorIndexProcessor:
@@ -33,7 +34,7 @@ class VectorIndexProcessor:
         vector_db = VectorDBService()
         collection_name = "vector_collection"
         if action == "destroy":
-            vector_db.delete_vector(collection_name, path)
+            await vector_db.delete_vector(collection_name, path)
             await LogService.info(
                 "processor:vector_index",
                 f"Destroyed {index_type} index for {path}",
@@ -42,8 +43,8 @@ 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':
-            vector_db.ensure_collection(collection_name, vector=False)
-            vector_db.upsert_vector(collection_name, {'path': path})
+            await vector_db.ensure_collection(collection_name, vector=False)
+            await vector_db.upsert_vector(collection_name, {'path': path})
             await LogService.info(
                 "processor:vector_index",
                 f"Created simple index for {path}",
@@ -71,8 +72,16 @@ class VectorIndexProcessor:
         if embedding is None:
             return Response(content="不支持的文件类型", status_code=400)
 
-        vector_db.ensure_collection(collection_name, vector=True)
-        vector_db.upsert_vector(
+        raw_dim = await ConfigCenter.get('AI_EMBED_DIM', DEFAULT_VECTOR_DIMENSION)
+        try:
+            vector_dim = int(raw_dim)
+        except (TypeError, ValueError):
+            vector_dim = DEFAULT_VECTOR_DIMENSION
+        if vector_dim <= 0:
+            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 LogService.info(

services/share.py

@@ -90,6 +90,16 @@ class ShareService:
             raise HTTPException(status_code=404, detail="分享链接不存在")
         await share.delete()
 
+    @staticmethod
+    async def delete_expired_shares(user: UserAccount) -> int:
+        """
+        删除当前用户所有已过期的分享链接，返回删除数量。
+        条件：expires_at 非空 且 小于等于当前时间（UTC）。
+        """
+        now = datetime.now(timezone.utc)
+        deleted_count = await ShareLink.filter(user=user, expires_at__lte=now).delete()
+        return deleted_count
+
     @staticmethod
     async def get_shared_item_details(share: ShareLink, sub_path: str = ""):
         """
@@ -122,4 +132,4 @@ class ShareService:
             raise e
 
 
-share_service = ShareService()
+share_service = ShareService()

services/task_queue.py

@@ -54,7 +54,8 @@ class TaskQueueService:
                     path=params["path"],
                     processor_type=params["processor_type"],
                     config=params["config"],
-                    save_to=params["save_to"]
+                    save_to=params.get("save_to"),
+                    overwrite=params.get("overwrite", False),
                 )
                 task.result = result
             elif task.name == "automation_task":
@@ -119,4 +120,4 @@ class TaskQueueService:
                 await LogService.info("task_queue", "Task worker has been stopped.")
 
 
-task_queue_service = TaskQueueService()
+task_queue_service = TaskQueueService()

services/vector_db.py

@@ -1,83 +0,0 @@
-from pymilvus import CollectionSchema, DataType, FieldSchema, MilvusClient
-
-
-class VectorDBService:
-    _instance = None
-
-    def __new__(cls, *args, **kwargs):
-        if not cls._instance:
-            cls._instance = super(VectorDBService, cls).__new__(cls)
-        return cls._instance
-
-    def __init__(self):
-        if not hasattr(self, 'client'):
-            self.client = MilvusClient("data/db/milvus.db")
-
-    def ensure_collection(self, collection_name, vector: bool = True):
-        if self.client.has_collection(collection_name):
-            return
-        if vector:
-            fields = [
-                FieldSchema(name="path", dtype=DataType.VARCHAR,
-                            max_length=512, is_primary=True, auto_id=False),
-                FieldSchema(name="embedding",
-                            dtype=DataType.FLOAT_VECTOR, dim=4096)
-            ]
-            schema = CollectionSchema(
-                fields, description="Image vector collection")
-            self.client.create_collection(collection_name, schema=schema)
-            index_params = MilvusClient.prepare_index_params()
-            index_params.add_index(
-                field_name="embedding",
-                index_type="IVF_FLAT",
-                index_name="vector_index",
-                metric_type="COSINE",
-                params={
-                    "nlist": 64,
-                }
-            )
-            self.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")
-            self.client.create_collection(collection_name, schema=schema)
-
-    def upsert_vector(self, collection_name, data):
-        self.client.upsert(collection_name, data)
-
-    def delete_vector(self, collection_name, path: str):
-        self.client.delete(collection_name, ids=[path])
-
-    def search_vectors(self, collection_name, query_embedding, top_k=5):
-        search_params = {"metric_type": "COSINE"}
-        results = self.client.search(
-            collection_name,
-            data=[query_embedding],
-            anns_field="embedding",
-            search_params=search_params,
-            limit=top_k,
-            output_fields=["path"]
-        )
-        print(results)
-        return results
-
-    def search_by_path(self, collection_name, query_path, top_k=20):
-        results = self.client.query(
-            collection_name,
-            filter=f"path like '%{query_path}%'",
-            limit=top_k,
-            output_fields=["path"]
-        )
-        return [[{'id': r['path'], 'distance': 1.0, 'entity': {'path': r['path']}} for r in results]]
-
-    def clear_all_data(self):
-        """清空所有集合的内容"""
-        collections = self.client.list_collections()
-        for collection_name in collections:
-            self.client.drop_collection(collection_name)

services/vector_db/__init__.py

@@ -0,0 +1,11 @@
+from .service import VectorDBService, DEFAULT_VECTOR_DIMENSION
+from .providers import list_providers, get_provider_entry
+from .config_manager import VectorDBConfigManager
+
+__all__ = [
+    "VectorDBService",
+    "DEFAULT_VECTOR_DIMENSION",
+    "list_providers",
+    "get_provider_entry",
+    "VectorDBConfigManager",
+]

services/vector_db/config_manager.py

@@ -0,0 +1,43 @@
+from __future__ import annotations
+
+import json
+from typing import Any, Dict, Tuple
+
+from services.config import ConfigCenter
+
+
+class VectorDBConfigManager:
+    TYPE_KEY = "VECTOR_DB_TYPE"
+    CONFIG_KEY = "VECTOR_DB_CONFIG"
+    DEFAULT_TYPE = "milvus_lite"
+
+    @classmethod
+    async def load_config(cls) -> Tuple[str, Dict[str, Any]]:
+        raw_type = await ConfigCenter.get(cls.TYPE_KEY, cls.DEFAULT_TYPE)
+        provider_type = str(raw_type or cls.DEFAULT_TYPE)
+
+        raw_config = await ConfigCenter.get(cls.CONFIG_KEY)
+        config_dict: Dict[str, Any] = {}
+        if isinstance(raw_config, str) and raw_config:
+            try:
+                config_dict = json.loads(raw_config)
+            except json.JSONDecodeError:
+                config_dict = {}
+        elif isinstance(raw_config, dict):
+            config_dict = raw_config
+        return provider_type, config_dict
+
+    @classmethod
+    async def save_config(cls, provider_type: str, config: Dict[str, Any]) -> None:
+        await ConfigCenter.set(cls.TYPE_KEY, provider_type)
+        await ConfigCenter.set(cls.CONFIG_KEY, json.dumps(config or {}))
+
+    @classmethod
+    async def get_type(cls) -> str:
+        provider_type, _ = await cls.load_config()
+        return provider_type
+
+    @classmethod
+    async def get_config(cls) -> Dict[str, Any]:
+        _, config = await cls.load_config()
+        return config

services/vector_db/providers/__init__.py

@@ -0,0 +1,56 @@
+from __future__ import annotations
+
+from typing import Dict, List, Type
+
+from .base import BaseVectorProvider
+from .milvus_lite import MilvusLiteProvider
+from .milvus_server import MilvusServerProvider
+from .qdrant import QdrantProvider
+
+_PROVIDER_REGISTRY: Dict[str, Dict[str, object]] = {
+    MilvusLiteProvider.type: {
+        "class": MilvusLiteProvider,
+        "label": MilvusLiteProvider.label,
+        "description": MilvusLiteProvider.description,
+        "enabled": MilvusLiteProvider.enabled,
+        "config_schema": MilvusLiteProvider.config_schema,
+    },
+    MilvusServerProvider.type: {
+        "class": MilvusServerProvider,
+        "label": MilvusServerProvider.label,
+        "description": MilvusServerProvider.description,
+        "enabled": MilvusServerProvider.enabled,
+        "config_schema": MilvusServerProvider.config_schema,
+    },
+    QdrantProvider.type: {
+        "class": QdrantProvider,
+        "label": QdrantProvider.label,
+        "description": QdrantProvider.description,
+        "enabled": QdrantProvider.enabled,
+        "config_schema": QdrantProvider.config_schema,
+    },
+}
+
+
+def list_providers() -> List[Dict[str, object]]:
+    return [
+        {
+            "type": type_key,
+            "label": meta["label"],
+            "description": meta.get("description"),
+            "enabled": meta.get("enabled", True),
+            "config_schema": meta.get("config_schema", []),
+        }
+        for type_key, meta in _PROVIDER_REGISTRY.items()
+    ]
+
+
+def get_provider_entry(provider_type: str) -> Dict[str, object] | None:
+    return _PROVIDER_REGISTRY.get(provider_type)
+
+
+def get_provider_class(provider_type: str) -> Type[BaseVectorProvider] | None:
+    entry = get_provider_entry(provider_type)
+    if not entry:
+        return None
+    return entry.get("class")  # type: ignore[return-value]

services/vector_db/providers/base.py

@@ -0,0 +1,41 @@
+from __future__ import annotations
+
+from typing import Any, Dict, List
+
+
+class BaseVectorProvider:
+    """向量数据库提供者基础类，所有实际实现需继承该类"""
+
+    type: str = ""
+    label: str = ""
+    description: str | None = None
+    enabled: bool = True
+    config_schema: List[Dict[str, Any]] = []
+
+    def __init__(self, config: Dict[str, Any] | None = None):
+        self.config = config or {}
+
+    async def initialize(self) -> None:
+        """执行初始化逻辑，例如建立连接"""
+        raise NotImplementedError
+
+    def ensure_collection(self, collection_name: str, vector: bool, dim: int) -> None:
+        raise NotImplementedError
+
+    def upsert_vector(self, collection_name: str, data: Dict[str, Any]) -> None:
+        raise NotImplementedError
+
+    def delete_vector(self, collection_name: str, path: str) -> None:
+        raise NotImplementedError
+
+    def search_vectors(self, collection_name: str, query_embedding, top_k: int):
+        raise NotImplementedError
+
+    def search_by_path(self, collection_name: str, query_path: str, top_k: int):
+        raise NotImplementedError
+
+    def get_all_stats(self) -> Dict[str, Any]:
+        raise NotImplementedError
+
+    def clear_all_data(self) -> None:
+        raise NotImplementedError

services/vector_db/providers/milvus_lite.py

@@ -0,0 +1,196 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from pymilvus import CollectionSchema, DataType, FieldSchema, MilvusClient
+
+from .base import BaseVectorProvider
+
+
+class MilvusLiteProvider(BaseVectorProvider):
+    type = "milvus_lite"
+    label = "Milvus Lite"
+    description = "Embedded Milvus Lite (local file storage)."
+    enabled = True
+    config_schema: List[Dict[str, Any]] = [
+        {
+            "key": "db_path",
+            "label": "Database file path",
+            "type": "text",
+            "default": "data/db/milvus.db",
+            "required": False,
+        }
+    ]
+
+    def __init__(self, config: Dict[str, Any] | None = None):
+        super().__init__(config)
+        self.db_path = Path(self.config.get("db_path") or "data/db/milvus.db")
+        self.client: MilvusClient | None = None
+
+    async def initialize(self) -> None:
+        try:
+            self.client = MilvusClient(str(self.db_path))
+        except Exception as exc:  # pragma: no cover - depends on local environment
+            raise RuntimeError(f"Failed to open Milvus Lite at {self.db_path}: {exc}") from exc
+
+    def _get_client(self) -> MilvusClient:
+        if not self.client:
+            raise RuntimeError("Milvus Lite client is not initialized")
+        return self.client
+
+    @staticmethod
+    def _to_int(value: Any) -> int:
+        try:
+            return int(value)
+        except (TypeError, ValueError):
+            return 0
+
+    def ensure_collection(self, collection_name: str, vector: bool, dim: int) -> None:
+        client = self._get_client()
+        if client.has_collection(collection_name):
+            return
+        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),
+                FieldSchema(name="embedding", dtype=DataType.FLOAT_VECTOR, dim=vector_dim),
+            ]
+            schema = CollectionSchema(fields, description="Image vector collection")
+            client.create_collection(collection_name, schema=schema)
+            index_params = MilvusClient.prepare_index_params()
+            index_params.add_index(
+                field_name="embedding",
+                index_type="IVF_FLAT",
+                index_name="vector_index",
+                metric_type="COSINE",
+                params={"nlist": 64},
+            )
+            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")
+            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)
+
+    def delete_vector(self, collection_name: str, path: str) -> None:
+        self._get_client().delete(collection_name, ids=[path])
+
+    def search_vectors(self, collection_name: str, query_embedding, top_k: int):
+        search_params = {"metric_type": "COSINE"}
+        return self._get_client().search(
+            collection_name,
+            data=[query_embedding],
+            anns_field="embedding",
+            search_params=search_params,
+            limit=top_k,
+            output_fields=["path"],
+        )
+
+    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 '%%'"
+        results = self._get_client().query(
+            collection_name,
+            filter=filter_expr,
+            limit=top_k,
+            output_fields=["path"],
+        )
+        return [[{"id": r["path"], "distance": 1.0, "entity": {"path": r["path"]}} for r in results]]
+
+    def get_all_stats(self) -> Dict[str, Any]:
+        client = self._get_client()
+        try:
+            collection_names = client.list_collections()
+        except Exception as exc:
+            raise RuntimeError(f"Failed to list collections: {exc}") from exc
+
+        collections: List[Dict[str, Any]] = []
+        total_vectors = 0
+        total_estimated_memory = 0
+
+        for name in collection_names:
+            try:
+                stats = client.get_collection_stats(name) or {}
+            except Exception:
+                stats = {}
+            row_count = self._to_int(stats.get("row_count"))
+            total_vectors += row_count
+
+            dimension: Optional[int] = None
+            is_vector_collection = False
+            try:
+                description = client.describe_collection(name)
+            except Exception:
+                description = None
+
+            if description:
+                for field in description.get("fields", []):
+                    if field.get("type") == DataType.FLOAT_VECTOR:
+                        params = field.get("params") or {}
+                        dimension = self._to_int(params.get("dim")) or 4096
+                        is_vector_collection = True
+                        break
+
+            estimated_memory = 0
+            if is_vector_collection and dimension:
+                estimated_memory = row_count * dimension * 4
+                total_estimated_memory += estimated_memory
+
+            indexes: List[Dict[str, Any]] = []
+            try:
+                index_names = client.list_indexes(name) or []
+            except Exception:
+                index_names = []
+
+            for index_name in index_names:
+                try:
+                    detail = client.describe_index(name, index_name) or {}
+                except Exception:
+                    detail = {}
+                indexes.append(
+                    {
+                        "index_name": index_name,
+                        "index_type": detail.get("index_type"),
+                        "metric_type": detail.get("metric_type"),
+                        "indexed_rows": self._to_int(detail.get("indexed_rows")),
+                        "pending_index_rows": self._to_int(detail.get("pending_index_rows")),
+                        "state": detail.get("state"),
+                    }
+                )
+
+            collections.append(
+                {
+                    "name": name,
+                    "row_count": row_count,
+                    "dimension": dimension if is_vector_collection else None,
+                    "estimated_memory_bytes": estimated_memory,
+                    "is_vector_collection": is_vector_collection,
+                    "indexes": indexes,
+                }
+            )
+
+        db_file_size = None
+        try:
+            if self.db_path.exists():
+                db_file_size = self.db_path.stat().st_size
+        except OSError:
+            db_file_size = None
+
+        return {
+            "collections": collections,
+            "collection_count": len(collections),
+            "total_vectors": total_vectors,
+            "estimated_total_memory_bytes": total_estimated_memory,
+            "db_file_size_bytes": db_file_size,
+        }
+
+    def clear_all_data(self) -> None:
+        client = self._get_client()
+        for collection_name in client.list_collections():
+            client.drop_collection(collection_name)

services/vector_db/providers/milvus_server.py

@@ -0,0 +1,197 @@
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional
+
+from pymilvus import CollectionSchema, DataType, FieldSchema, MilvusClient
+
+from .base import BaseVectorProvider
+
+
+class MilvusServerProvider(BaseVectorProvider):
+    type = "milvus_server"
+    label = "Milvus Server"
+    description = "Remote Milvus instance accessed via URI."
+    enabled = True
+    config_schema: List[Dict[str, Any]] = [
+        {
+            "key": "uri",
+            "label": "Server URI",
+            "type": "text",
+            "required": True,
+            "placeholder": "http://localhost:19530",
+        },
+        {
+            "key": "token",
+            "label": "Token",
+            "type": "password",
+            "required": False,
+            "placeholder": "user:password",
+        },
+    ]
+
+    def __init__(self, config: Dict[str, Any] | None = None):
+        super().__init__(config)
+        self.client: MilvusClient | None = None
+
+    async def initialize(self) -> None:
+        uri = self.config.get("uri")
+        if not uri:
+            raise RuntimeError("Milvus Server URI is required")
+        try:
+            self.client = MilvusClient(uri=uri, token=self.config.get("token"))
+        except Exception as exc:  # pragma: no cover - depends on remote availability
+            raise RuntimeError(f"Failed to connect to Milvus Server {uri}: {exc}") from exc
+
+    def _get_client(self) -> MilvusClient:
+        if not self.client:
+            raise RuntimeError("Milvus Server client is not initialized")
+        return self.client
+
+    @staticmethod
+    def _to_int(value: Any) -> int:
+        try:
+            return int(value)
+        except (TypeError, ValueError):
+            return 0
+
+    def ensure_collection(self, collection_name: str, vector: bool, dim: int) -> None:
+        client = self._get_client()
+        if client.has_collection(collection_name):
+            return
+        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),
+                FieldSchema(name="embedding", dtype=DataType.FLOAT_VECTOR, dim=vector_dim),
+            ]
+            schema = CollectionSchema(fields, description="Image vector collection")
+            client.create_collection(collection_name, schema=schema)
+            index_params = MilvusClient.prepare_index_params()
+            index_params.add_index(
+                field_name="embedding",
+                index_type="IVF_FLAT",
+                index_name="vector_index",
+                metric_type="COSINE",
+                params={"nlist": 64},
+            )
+            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")
+            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)
+
+    def delete_vector(self, collection_name: str, path: str) -> None:
+        self._get_client().delete(collection_name, ids=[path])
+
+    def search_vectors(self, collection_name: str, query_embedding, top_k: int):
+        search_params = {"metric_type": "COSINE"}
+        return self._get_client().search(
+            collection_name,
+            data=[query_embedding],
+            anns_field="embedding",
+            search_params=search_params,
+            limit=top_k,
+            output_fields=["path"],
+        )
+
+    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 '%%'"
+        results = self._get_client().query(
+            collection_name,
+            filter=filter_expr,
+            limit=top_k,
+            output_fields=["path"],
+        )
+        return [[{"id": r["path"], "distance": 1.0, "entity": {"path": r["path"]}} for r in results]]
+
+    def get_all_stats(self) -> Dict[str, Any]:
+        client = self._get_client()
+        try:
+            collection_names = client.list_collections()
+        except Exception as exc:
+            raise RuntimeError(f"Failed to list collections: {exc}") from exc
+
+        collections: List[Dict[str, Any]] = []
+        total_vectors = 0
+        total_estimated_memory = 0
+
+        for name in collection_names:
+            try:
+                stats = client.get_collection_stats(name) or {}
+            except Exception:
+                stats = {}
+            row_count = self._to_int(stats.get("row_count"))
+            total_vectors += row_count
+
+            dimension: Optional[int] = None
+            is_vector_collection = False
+            try:
+                description = client.describe_collection(name)
+            except Exception:
+                description = None
+
+            if description:
+                for field in description.get("fields", []):
+                    if field.get("type") == DataType.FLOAT_VECTOR:
+                        params = field.get("params") or {}
+                        dimension = self._to_int(params.get("dim")) or 4096
+                        is_vector_collection = True
+                        break
+
+            estimated_memory = 0
+            if is_vector_collection and dimension:
+                estimated_memory = row_count * dimension * 4
+                total_estimated_memory += estimated_memory
+
+            indexes: List[Dict[str, Any]] = []
+            try:
+                index_names = client.list_indexes(name) or []
+            except Exception:
+                index_names = []
+
+            for index_name in index_names:
+                try:
+                    detail = client.describe_index(name, index_name) or {}
+                except Exception:
+                    detail = {}
+                indexes.append(
+                    {
+                        "index_name": index_name,
+                        "index_type": detail.get("index_type"),
+                        "metric_type": detail.get("metric_type"),
+                        "indexed_rows": self._to_int(detail.get("indexed_rows")),
+                        "pending_index_rows": self._to_int(detail.get("pending_index_rows")),
+                        "state": detail.get("state"),
+                    }
+                )
+
+            collections.append(
+                {
+                    "name": name,
+                    "row_count": row_count,
+                    "dimension": dimension if is_vector_collection else None,
+                    "estimated_memory_bytes": estimated_memory,
+                    "is_vector_collection": is_vector_collection,
+                    "indexes": indexes,
+                }
+            )
+
+        return {
+            "collections": collections,
+            "collection_count": len(collections),
+            "total_vectors": total_vectors,
+            "estimated_total_memory_bytes": total_estimated_memory,
+            "db_file_size_bytes": None,
+        }
+
+    def clear_all_data(self) -> None:
+        client = self._get_client()
+        for collection_name in client.list_collections():
+            client.drop_collection(collection_name)

services/vector_db/providers/qdrant.py

@@ -0,0 +1,237 @@
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional, Sequence
+from uuid import NAMESPACE_URL, uuid5
+
+from qdrant_client import QdrantClient
+from qdrant_client.http import models as qmodels
+
+from .base import BaseVectorProvider
+
+
+class QdrantProvider(BaseVectorProvider):
+    type = "qdrant"
+    label = "Qdrant"
+    description = "Qdrant vector database (HTTP API)."
+    enabled = True
+    config_schema: List[Dict[str, Any]] = [
+        {
+            "key": "url",
+            "label": "Server URL",
+            "type": "text",
+            "required": True,
+            "placeholder": "http://localhost:6333",
+        },
+        {
+            "key": "api_key",
+            "label": "API Key",
+            "type": "password",
+            "required": False,
+        },
+    ]
+
+    def __init__(self, config: Dict[str, Any] | None = None):
+        super().__init__(config)
+        self.client: Optional[QdrantClient] = None
+
+    async def initialize(self) -> None:
+        url = (self.config.get("url") or "").strip()
+        if not url:
+            raise RuntimeError("Qdrant URL is required")
+
+        api_key = (self.config.get("api_key") or None) or None
+        try:
+            client = QdrantClient(url=url, api_key=api_key)
+            # 简单连通性校验
+            client.get_collections()
+            self.client = client
+        except Exception as exc:  # pragma: no cover - 依赖外部服务
+            raise RuntimeError(f"Failed to connect to Qdrant at {url}: {exc}") from exc
+
+    def _get_client(self) -> QdrantClient:
+        if not self.client:
+            raise RuntimeError("Qdrant client is not initialized")
+        return self.client
+
+    @staticmethod
+    def _vector_params(vector: bool, dim: int) -> qmodels.VectorParams:
+        size = dim if vector and isinstance(dim, int) and dim > 0 else 1
+        return qmodels.VectorParams(size=size, distance=qmodels.Distance.COSINE)
+
+    def ensure_collection(self, collection_name: str, vector: bool, dim: int) -> None:
+        client = self._get_client()
+        try:
+            if client.collection_exists(collection_name):
+                return
+        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
+
+        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():
+                return
+            raise RuntimeError(f"Failed to create Qdrant collection '{collection_name}': {exc}") from exc
+
+    @staticmethod
+    def _point_id(path: str) -> str:
+        return str(uuid5(NAMESPACE_URL, path))
+
+    def _prepare_point(self, data: Dict[str, Any]) -> qmodels.PointStruct:
+        path = data.get("path")
+        if not path:
+            raise ValueError("Qdrant upsert requires 'path' in data")
+
+        embedding = data.get("embedding")
+        if embedding is None:
+            vector = [0.0]
+        else:
+            vector = [float(x) for x in embedding]
+
+        payload = {"path": path}
+        return qmodels.PointStruct(id=self._point_id(path), vector=vector, payload=payload)
+
+    def upsert_vector(self, collection_name: str, data: Dict[str, Any]) -> None:
+        client = self._get_client()
+        point = self._prepare_point(data)
+        client.upsert(collection_name=collection_name, wait=True, points=[point])
+
+    def delete_vector(self, collection_name: str, path: str) -> None:
+        client = self._get_client()
+        selector = qmodels.PointIdsList(points=[self._point_id(path)])
+        client.delete(collection_name=collection_name, points_selector=selector, wait=True)
+
+    def _format_search_results(self, points: Sequence[qmodels.ScoredPoint]):
+        return [
+            {
+                "id": point.id,
+                "distance": point.score,
+                "entity": {"path": (point.payload or {}).get("path")},
+            }
+            for point in points
+        ]
+
+    def search_vectors(self, collection_name: str, query_embedding, top_k: int):
+        client = self._get_client()
+        vector = [float(x) for x in query_embedding]
+        points = client.search(
+            collection_name=collection_name,
+            query_vector=vector,
+            limit=top_k,
+            with_payload=True,
+        )
+        return [self._format_search_results(points)]
+
+    def search_by_path(self, collection_name: str, query_path: str, top_k: int):
+        client = self._get_client()
+        results: List[Dict[str, Any]] = []
+        offset: Optional[str | int] = None
+        remaining = max(top_k, 1)
+
+        while len(results) < top_k:
+            batch_size = min(max(remaining * 2, 10), 200)
+            records, next_offset = client.scroll(
+                collection_name=collection_name,
+                limit=batch_size,
+                offset=offset,
+                with_payload=True,
+            )
+            if not records:
+                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}})
+                if len(results) >= top_k:
+                    break
+
+            if next_offset is None or len(results) >= top_k:
+                break
+            offset = next_offset
+            remaining = top_k - len(results)
+
+        return [results]
+
+    def _extract_vector_config(self, vectors) -> Optional[qmodels.VectorParams]:
+        if isinstance(vectors, qmodels.VectorParams):
+            return vectors
+        if isinstance(vectors, dict):
+            for value in vectors.values():
+                if isinstance(value, qmodels.VectorParams):
+                    return value
+        return None
+
+    def get_all_stats(self) -> Dict[str, Any]:
+        client = self._get_client()
+        try:
+            response = client.get_collections()
+        except Exception as exc:  # pragma: no cover
+            raise RuntimeError(f"Failed to list Qdrant collections: {exc}") from exc
+
+        collections: List[Dict[str, Any]] = []
+        total_vectors = 0
+        total_estimated_memory = 0
+
+        for description in response.collections or []:
+            name = description.name
+            try:
+                info = client.get_collection(name)
+            except Exception:
+                continue
+
+            row_count = int(info.points_count or 0)
+            total_vectors += row_count
+
+            vector_params = self._extract_vector_config(info.config.params.vectors if info.config and info.config.params else None)
+            dimension = int(vector_params.size) if vector_params and vector_params.size else None
+            estimated_memory = row_count * dimension * 4 if dimension else 0
+            total_estimated_memory += estimated_memory
+            distance = str(vector_params.distance) if vector_params and vector_params.distance else None
+
+            indexed_rows = int(info.indexed_vectors_count or 0)
+            pending_rows = max(row_count - indexed_rows, 0)
+
+            collections.append(
+                {
+                    "name": name,
+                    "row_count": row_count,
+                    "dimension": dimension,
+                    "estimated_memory_bytes": estimated_memory,
+                    "is_vector_collection": dimension is not None and dimension > 1,
+                    "indexes": [
+                        {
+                            "index_name": "hnsw",
+                            "index_type": "HNSW",
+                            "metric_type": distance,
+                            "indexed_rows": indexed_rows,
+                            "pending_index_rows": pending_rows,
+                            "state": info.status,
+                        }
+                    ],
+                }
+            )
+
+        return {
+            "collections": collections,
+            "collection_count": len(collections),
+            "total_vectors": total_vectors,
+            "estimated_total_memory_bytes": total_estimated_memory,
+            "db_file_size_bytes": None,
+        }
+
+    def clear_all_data(self) -> None:
+        client = self._get_client()
+        try:
+            response = client.get_collections()
+        except Exception as exc:  # pragma: no cover
+            raise RuntimeError(f"Failed to list Qdrant collections: {exc}") from exc
+
+        for description in response.collections or []:
+            try:
+                client.delete_collection(description.name)
+            except Exception:
+                continue

services/vector_db/service.py

@@ -0,0 +1,99 @@
+from __future__ import annotations
+
+import asyncio
+from typing import Any, Dict, Optional
+
+from .config_manager import VectorDBConfigManager
+from .providers import get_provider_class, get_provider_entry
+from .providers.base import BaseVectorProvider
+
+DEFAULT_VECTOR_DIMENSION = 4096
+
+
+class VectorDBService:
+    _instance: "VectorDBService" | None = None
+
+    def __new__(cls, *args, **kwargs):
+        if cls._instance is None:
+            cls._instance = super().__new__(cls)
+        return cls._instance
+
+    def __init__(self):
+        if not hasattr(self, "_provider"):
+            self._provider: Optional[BaseVectorProvider] = None
+            self._provider_type: Optional[str] = None
+            self._provider_config: Dict[str, Any] | None = None
+            self._lock = asyncio.Lock()
+
+    async def _ensure_provider(self) -> BaseVectorProvider:
+        if self._provider is None:
+            await self.reload()
+        assert self._provider is not None  # for type checker
+        return self._provider
+
+    async def reload(self) -> BaseVectorProvider:
+        async with self._lock:
+            provider_type, provider_config = await VectorDBConfigManager.load_config()
+            normalized_config = dict(provider_config or {})
+            if (
+                self._provider
+                and self._provider_type == provider_type
+                and self._provider_config == normalized_config
+            ):
+                return self._provider
+
+            entry = get_provider_entry(provider_type)
+            if not entry:
+                raise RuntimeError(f"Unknown vector database provider: {provider_type}")
+            if not entry.get("enabled", True):
+                raise RuntimeError(f"Vector database provider '{provider_type}' is disabled")
+
+            provider_cls = get_provider_class(provider_type)
+            if not provider_cls:
+                raise RuntimeError(f"Provider class not found for '{provider_type}'")
+
+            provider = provider_cls(provider_config)
+            await provider.initialize()
+
+            self._provider = provider
+            self._provider_type = provider_type
+            self._provider_config = normalized_config
+            return provider
+
+    async def ensure_collection(self, collection_name: str, vector: bool = True, dim: int = DEFAULT_VECTOR_DIMENSION) -> None:
+        provider = await self._ensure_provider()
+        provider.ensure_collection(collection_name, vector, dim)
+
+    async def upsert_vector(self, collection_name: str, data: Dict[str, Any]) -> None:
+        provider = await self._ensure_provider()
+        provider.upsert_vector(collection_name, data)
+
+    async def delete_vector(self, collection_name: str, path: str) -> None:
+        provider = await self._ensure_provider()
+        provider.delete_vector(collection_name, path)
+
+    async def search_vectors(self, collection_name: str, query_embedding, top_k: int = 5):
+        provider = await self._ensure_provider()
+        return provider.search_vectors(collection_name, query_embedding, top_k)
+
+    async def search_by_path(self, collection_name: str, query_path: str, top_k: int = 20):
+        provider = await self._ensure_provider()
+        return provider.search_by_path(collection_name, query_path, top_k)
+
+    async def get_all_stats(self) -> Dict[str, Any]:
+        provider = await self._ensure_provider()
+        return provider.get_all_stats()
+
+    async def clear_all_data(self) -> None:
+        provider = await self._ensure_provider()
+        provider.clear_all_data()
+
+    async def current_provider(self) -> Dict[str, Any]:
+        provider_type, provider_config = await VectorDBConfigManager.load_config()
+        entry = get_provider_entry(provider_type) or {}
+        return {
+            "type": provider_type,
+            "config": provider_config,
+            "label": entry.get("label"),
+            "enabled": entry.get("enabled", True),
+        }

services/virtual_fs.py

@@ -1,4 +1,4 @@
-from typing import Dict, Tuple, Any, Union, AsyncIterator
+from typing import Dict, Tuple, Any, Union, AsyncIterator, List
 from fastapi import HTTPException
 import mimetypes
 from fastapi.responses import Response
@@ -59,6 +59,24 @@ async def _ensure_method(adapter: Any, method: str):
     return func
 
 
+async def path_is_directory(path: str) -> bool:
+    """判断给定路径是否为目录。"""
+    adapter_instance, _, root, rel = await resolve_adapter_and_rel(path)
+    rel = rel.rstrip('/')
+    if rel == '':
+        return True
+    stat_func = getattr(adapter_instance, "stat_file", None)
+    if not callable(stat_func):
+        raise HTTPException(501, detail="Adapter does not implement stat_file")
+    try:
+        info = await stat_func(root, rel)
+    except FileNotFoundError:
+        raise HTTPException(404, detail="Path not found")
+    if isinstance(info, dict):
+        return bool(info.get("is_dir"))
+    return False
+
+
 async def list_virtual_dir(path: str, page_num: int = 1, page_size: int = 50, sort_by: str = "name", sort_order: str = "asc") -> Dict:
     norm = (path if path.startswith('/') else '/' + path).rstrip('/') or '/'
     adapters = await StorageAdapter.filter(enabled=True)
@@ -476,28 +494,110 @@ async def copy_path(src: str, dst: str, overwrite: bool = False, return_debug: b
     return debug_info if return_debug else None
 
 
-async def process_file(path: str, processor_type: str, config: dict, save_to: str = None):
-    """
-    使用指定处理器处理文件，并可选择保存到新路径
-    :param path: 源文件路径
-    :param processor_type: 处理器类型
-    :param config: 处理器配置
-    :param save_to: 保存路径（可选），不指定则只返回处理结果
-    :return: 处理后的文件内容或保存结果
-    """
-    data = await read_file(path)
+async def process_file(
+    path: str,
+    processor_type: str,
+    config: dict,
+    save_to: str | None = None,
+    overwrite: bool = False,
+) -> Any:
+    """处理指定路径（文件或目录）。目录会递归处理其下所有文件。"""
+
     processor = get_processor(processor_type)
     if not processor:
-        raise HTTPException(
-            400, detail=f"Processor {processor_type} not found")
-    result = await processor.process(data, path, config)
-    if save_to and getattr(processor, "produces_file", False):
+        raise HTTPException(400, detail=f"Processor {processor_type} not found")
+
+    actual_is_dir = await path_is_directory(path)
+
+    supported_exts = getattr(processor, "supported_exts", None) or []
+    allowed_exts = {
+        str(ext).lower().lstrip('.')
+        for ext in supported_exts
+        if isinstance(ext, str)
+    }
+
+    def matches_extension(rel_path: str) -> bool:
+        if not allowed_exts:
+            return True
+        if '.' not in rel_path:
+            return '' in allowed_exts
+        ext = rel_path.rsplit('.', 1)[-1].lower()
+        return ext in allowed_exts or f'.{ext}' in allowed_exts
+
+    def coerce_result_bytes(result: Any) -> bytes:
         if isinstance(result, Response):
-            result_bytes = result.body
-        else:
-            result_bytes = result
-        await write_file(save_to, result_bytes)
-        return {"saved_to": save_to}
+            return result.body
+        if isinstance(result, (bytes, bytearray)):
+            return bytes(result)
+        if isinstance(result, str):
+            return result.encode('utf-8')
+        raise HTTPException(500, detail="Processor must return bytes/Response when produces_file=True")
+
+    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
+
+    if actual_is_dir:
+        if save_to:
+            raise HTTPException(400, detail="Directory processing does not support custom save_to path")
+        if not overwrite:
+            raise HTTPException(400, detail="Directory processing requires overwrite")
+
+        adapter_instance, adapter_model, root, rel = await resolve_adapter_and_rel(path)
+        rel = rel.rstrip('/')
+        list_dir = await _ensure_method(adapter_instance, "list_dir")
+        processed_count = 0
+        stack: List[str] = [rel]
+        page_size = 200
+
+        while stack:
+            current = stack.pop()
+            page = 1
+            while True:
+                entries, total = await list_dir(root, current, page, page_size, "name", "asc")
+                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}/{name}" if current else name
+                    if entry.get("is_dir"):
+                        stack.append(child_rel)
+                        continue
+                    if not matches_extension(child_rel):
+                        continue
+                    absolute_path = build_absolute_path(adapter_model.path, child_rel)
+                    data = await read_file(absolute_path)
+                    result = await processor.process(data, absolute_path, config)
+                    if getattr(processor, "produces_file", False):
+                        result_bytes = coerce_result_bytes(result)
+                        await write_file(absolute_path, result_bytes)
+                    processed_count += 1
+
+                if total is None or page * page_size >= total:
+                    break
+                page += 1
+
+        return {"processed_files": processed_count}
+
+    # 单文件处理
+    data = await read_file(path)
+    result = await processor.process(data, path, config)
+
+    target_path = save_to
+    if overwrite and not target_path:
+        target_path = path
+
+    if target_path and getattr(processor, "produces_file", False):
+        result_bytes = coerce_result_bytes(result)
+        await write_file(target_path, result_bytes)
+        return {"saved_to": target_path}
+
     return result
 
 

uv.lock

@@ -415,6 +415,7 @@ dependencies = [
     { name = "python-multipart" },
     { name = "pytz" },
     { name = "pyyaml" },
+    { name = "qdrant-client" },
     { name = "rawpy" },
     { name = "rich" },
     { name = "rich-toolkit" },
@@ -505,6 +506,7 @@ requires-dist = [
     { name = "python-multipart", specifier = "==0.0.20" },
     { name = "pytz", specifier = "==2025.2" },
     { name = "pyyaml", specifier = "==6.0.2" },
+    { name = "qdrant-client", specifier = "==1.15.1" },
     { name = "rawpy", specifier = "==0.25.1" },
     { name = "rich", specifier = "==14.1.0" },
     { name = "rich-toolkit", specifier = "==0.15.0" },
@@ -604,6 +606,28 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86", size = 37515, upload-time = "2025-04-24T03:35:24.344Z" },
 ]
 
+[[package]]
+name = "h2"
+version = "4.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "hpack" },
+    { name = "hyperframe" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/1d/17/afa56379f94ad0fe8defd37d6eb3f89a25404ffc71d4d848893d270325fc/h2-4.3.0.tar.gz", hash = "sha256:6c59efe4323fa18b47a632221a1888bd7fde6249819beda254aeca909f221bf1", size = 2152026, upload-time = "2025-08-23T18:12:19.778Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/69/b2/119f6e6dcbd96f9069ce9a2665e0146588dc9f88f29549711853645e736a/h2-4.3.0-py3-none-any.whl", hash = "sha256:c438f029a25f7945c69e0ccf0fb951dc3f73a5f6412981daee861431b70e2bdd", size = 61779, upload-time = "2025-08-23T18:12:17.779Z" },
+]
+
+[[package]]
+name = "hpack"
+version = "4.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/2c/48/71de9ed269fdae9c8057e5a4c0aa7402e8bb16f2c6e90b3aa53327b113f8/hpack-4.1.0.tar.gz", hash = "sha256:ec5eca154f7056aa06f196a557655c5b009b382873ac8d1e66e79e87535f1dca", size = 51276, upload-time = "2025-01-22T21:44:58.347Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/c6/80c95b1b2b94682a72cbdbfb85b81ae2daffa4291fbfa1b1464502ede10d/hpack-4.1.0-py3-none-any.whl", hash = "sha256:157ac792668d995c657d93111f46b4535ed114f0c9c8d672271bbec7eae1b496", size = 34357, upload-time = "2025-01-22T21:44:56.92Z" },
+]
+
 [[package]]
 name = "httpcore"
 version = "1.0.9"
@@ -647,6 +671,20 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517, upload-time = "2024-12-06T15:37:21.509Z" },
 ]
 
+[package.optional-dependencies]
+http2 = [
+    { name = "h2" },
+]
+
+[[package]]
+name = "hyperframe"
+version = "6.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/02/e7/94f8232d4a74cc99514c13a9f995811485a6903d48e5d952771ef6322e30/hyperframe-6.1.0.tar.gz", hash = "sha256:f630908a00854a7adeabd6382b43923a4c4cd4b821fcb527e6ab9e15382a3b08", size = 26566, upload-time = "2025-01-22T21:41:49.302Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/48/30/47d0bf6072f7252e6521f3447ccfa40b421b6824517f82854703d0f5a98b/hyperframe-6.1.0-py3-none-any.whl", hash = "sha256:b03380493a519fce58ea5af42e4a42317bf9bd425596f7a0835ffce80f1a42e5", size = 13007, upload-time = "2025-01-22T21:41:47.295Z" },
+]
+
 [[package]]
 name = "idna"
 version = "3.10"
@@ -950,6 +988,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/89/c7/5572fa4a3f45740eaab6ae86fcdf7195b55beac1371ac8c619d880cfe948/pillow-11.3.0-cp314-cp314t-win_arm64.whl", hash = "sha256:79ea0d14d3ebad43ec77ad5272e6ff9bba5b679ef73375ea760261207fa8e0aa", size = 2512835, upload-time = "2025-07-01T09:15:50.399Z" },
 ]
 
+[[package]]
+name = "portalocker"
+version = "3.2.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pywin32", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/5e/77/65b857a69ed876e1951e88aaba60f5ce6120c33703f7cb61a3c894b8c1b6/portalocker-3.2.0.tar.gz", hash = "sha256:1f3002956a54a8c3730586c5c77bf18fae4149e07eaf1c29fc3faf4d5a3f89ac", size = 95644, upload-time = "2025-06-14T13:20:40.03Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4b/a6/38c8e2f318bf67d338f4d629e93b0b4b9af331f455f0390ea8ce4a099b26/portalocker-3.2.0-py3-none-any.whl", hash = "sha256:3cdc5f565312224bc570c49337bd21428bba0ef363bbcf58b9ef4a9f11779968", size = 22424, upload-time = "2025-06-14T13:20:38.083Z" },
+]
+
 [[package]]
 name = "propcache"
 version = "0.3.2"
@@ -1161,6 +1211,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/81/c4/34e93fe5f5429d7570ec1fa436f1986fb1f00c3e0f43a589fe2bbcd22c3f/pytz-2025.2-py2.py3-none-any.whl", hash = "sha256:5ddf76296dd8c44c26eb8f4b6f35488f3ccbf6fbbd7adee0b7262d43f0ec2f00", size = 509225, upload-time = "2025-03-25T02:24:58.468Z" },
 ]
 
+[[package]]
+name = "pywin32"
+version = "311"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a5/be/3fd5de0979fcb3994bfee0d65ed8ca9506a8a1260651b86174f6a86f52b3/pywin32-311-cp313-cp313-win32.whl", hash = "sha256:f95ba5a847cba10dd8c4d8fefa9f2a6cf283b8b88ed6178fa8a6c1ab16054d0d", size = 8705700, upload-time = "2025-07-14T20:13:26.471Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/28/e0a1909523c6890208295a29e05c2adb2126364e289826c0a8bc7297bd5c/pywin32-311-cp313-cp313-win_amd64.whl", hash = "sha256:718a38f7e5b058e76aee1c56ddd06908116d35147e133427e59a3983f703a20d", size = 9494700, upload-time = "2025-07-14T20:13:28.243Z" },
+    { url = "https://files.pythonhosted.org/packages/04/bf/90339ac0f55726dce7d794e6d79a18a91265bdf3aa70b6b9ca52f35e022a/pywin32-311-cp313-cp313-win_arm64.whl", hash = "sha256:7b4075d959648406202d92a2310cb990fea19b535c7f4a78d3f5e10b926eeb8a", size = 8709318, upload-time = "2025-07-14T20:13:30.348Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/31/097f2e132c4f16d99a22bfb777e0fd88bd8e1c634304e102f313af69ace5/pywin32-311-cp314-cp314-win32.whl", hash = "sha256:b7a2c10b93f8986666d0c803ee19b5990885872a7de910fc460f9b0c2fbf92ee", size = 8840714, upload-time = "2025-07-14T20:13:32.449Z" },
+    { url = "https://files.pythonhosted.org/packages/90/4b/07c77d8ba0e01349358082713400435347df8426208171ce297da32c313d/pywin32-311-cp314-cp314-win_amd64.whl", hash = "sha256:3aca44c046bd2ed8c90de9cb8427f581c479e594e99b5c0bb19b29c10fd6cb87", size = 9656800, upload-time = "2025-07-14T20:13:34.312Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/d2/21af5c535501a7233e734b8af901574572da66fcc254cb35d0609c9080dd/pywin32-311-cp314-cp314-win_arm64.whl", hash = "sha256:a508e2d9025764a8270f93111a970e1d0fbfc33f4153b388bb649b7eec4f9b42", size = 8932540, upload-time = "2025-07-14T20:13:36.379Z" },
+]
+
 [[package]]
 name = "pyyaml"
 version = "6.0.2"
@@ -1178,6 +1241,24 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fa/de/02b54f42487e3d3c6efb3f89428677074ca7bf43aae402517bc7cca949f3/PyYAML-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:8388ee1976c416731879ac16da0aff3f63b286ffdd57cdeb95f3f2e085687563", size = 156446, upload-time = "2024-08-06T20:33:04.33Z" },
 ]
 
+[[package]]
+name = "qdrant-client"
+version = "1.15.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "grpcio" },
+    { name = "httpx", extra = ["http2"] },
+    { name = "numpy" },
+    { name = "portalocker" },
+    { name = "protobuf" },
+    { name = "pydantic" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/79/8b/76c7d325e11d97cb8eb5e261c3759e9ed6664735afbf32fdded5b580690c/qdrant_client-1.15.1.tar.gz", hash = "sha256:631f1f3caebfad0fd0c1fba98f41be81d9962b7bf3ca653bed3b727c0e0cbe0e", size = 295297, upload-time = "2025-07-31T19:35:19.627Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ef/33/d8df6a2b214ffbe4138db9a1efe3248f67dc3c671f82308bea1582ecbbb7/qdrant_client-1.15.1-py3-none-any.whl", hash = "sha256:2b975099b378382f6ca1cfb43f0d59e541be6e16a5892f282a4b8de7eff5cb63", size = 337331, upload-time = "2025-07-31T19:35:17.539Z" },
+]
+
 [[package]]
 name = "rawpy"
 version = "0.25.1"

web/src/App.tsx

@@ -5,12 +5,10 @@ import { status as getStatus } from './api/config.ts';
 import type { SystemStatus } from './api/config.ts';
 import { SystemContext } from './contexts/SystemContext.tsx';
 import { ThemeProvider } from './contexts/ThemeContext.tsx';
-import { Spin, ConfigProvider } from 'antd';
+import { Spin } from 'antd';
 import { Routes, Route, Navigate } from 'react-router';
 import SetupPage from './pages/SetupPage.tsx';
-import { I18nProvider, useI18n } from './i18n';
-import zhCN from 'antd/locale/zh_CN';
-import enUS from 'antd/locale/en_US';
+import { I18nProvider } from './i18n';
 
 function AppInner() {
   const [status, setStatus] = useState<SystemStatus | null>(null);
@@ -39,26 +37,21 @@ function AppInner() {
     );
   }
 
-  const { lang } = useI18n();
-  const locale = lang === 'zh' ? zhCN : enUS;
-
   return (
-    <ConfigProvider locale={locale}>
-      <SystemContext.Provider value={status}>
-        <AuthProvider>
-          <ThemeProvider>
-            {!status.is_initialized ? (
-              <Routes>
-                <Route path="/setup" element={<SetupPage />} />
-                <Route path="*" element={<Navigate to="/setup" replace />} />
-              </Routes>
-            ) : (
-              <AppRouter />
-            )}
-          </ThemeProvider>
-        </AuthProvider>
-      </SystemContext.Provider>
-    </ConfigProvider>
+    <SystemContext.Provider value={status}>
+      <AuthProvider>
+        <ThemeProvider>
+          {!status.is_initialized ? (
+            <Routes>
+              <Route path="/setup" element={<SetupPage />} />
+              <Route path="*" element={<Navigate to="/setup" replace />} />
+            </Routes>
+          ) : (
+            <AppRouter />
+          )}
+        </ThemeProvider>
+      </AuthProvider>
+    </SystemContext.Provider>
   );
 }
 

web/src/api/processors.ts

@@ -15,7 +15,8 @@ export interface ProcessorTypeMeta {
   name: string;
   supported_exts: string[];
   config_schema: ProcessorTypeField[];
-  produces_file:boolean;
+  produces_file: boolean;
+  module_path?: string | null;
 }
 
 export const processorsApi = {
@@ -29,11 +30,21 @@ export const processorsApi = {
     save_to?: string;
     overwrite?: boolean;
   }) =>
-    request<any>('/processors/process', {
+    request<{ task_id: string }>('/processors/process', {
+      method: 'POST',
+      json: params,
+    }),
+  getSource: (type: string) =>
+    request<{ source: string; module_path: string }>('/processors/source/' + encodeURIComponent(type), {
+      method: 'GET',
+    }),
+  updateSource: (type: string, source: string) =>
+    request<boolean>('/processors/source/' + encodeURIComponent(type), {
+      method: 'PUT',
+      json: { source },
+    }),
+  reload: () =>
+    request<boolean>('/processors/reload', {
       method: 'POST',
-      body: JSON.stringify(params),
-      headers: {
-        'Content-Type': 'application/json'
-      }
     }),
 };

web/src/api/share.ts

@@ -23,10 +23,15 @@ export interface ShareCreatePayload {
   password?: string;
 }
 
+export interface ClearExpiredResult {
+  deleted_count: number;
+}
+
 export const shareApi = {
   create: (payload: ShareCreatePayload) => request<ShareInfoWithPassword>('/shares', { method: 'POST', json: payload }),
   list: () => request<ShareInfo[]>('/shares'),
   remove: (shareId: number) => request<void>(`/shares/${shareId}`, { method: 'DELETE' }),
+  clearExpired: () => request<ClearExpiredResult>(`/shares/expired`, { method: 'DELETE' }),
   get: (token: string) => request<ShareInfo>(`/s/${token}`),
   verifyPassword: (token: string, password: string) => request<void>(`/s/${token}/verify`, { method: 'POST', json: { password } }),
   listDir: (token: string, path: string = '/', password?: string) => {
@@ -40,4 +45,4 @@ export const shareApi = {
     const url = `${API_BASE_URL}/s/${token}/download?path=${encodeURIComponent(path)}`;
     return password ? `${url}&password=${encodeURIComponent(password)}` : url;
   },
-};
+};

web/src/api/vectorDB.ts

@@ -1,5 +1,65 @@
 import client from './client';
 
+export interface VectorDBIndexInfo {
+  index_name: string;
+  index_type?: string;
+  metric_type?: string;
+  indexed_rows: number;
+  pending_index_rows: number;
+  state?: string;
+}
+
+export interface VectorDBCollectionStats {
+  name: string;
+  row_count: number;
+  dimension: number | null;
+  estimated_memory_bytes: number;
+  is_vector_collection: boolean;
+  indexes: VectorDBIndexInfo[];
+}
+
+export interface VectorDBStats {
+  collections: VectorDBCollectionStats[];
+  collection_count: number;
+  total_vectors: number;
+  estimated_total_memory_bytes: number;
+  db_file_size_bytes: number | null;
+}
+
+export interface VectorDBProviderField {
+  key: string;
+  label: string;
+  type: 'text' | 'password';
+  required?: boolean;
+  default?: string;
+  placeholder?: string;
+}
+
+export interface VectorDBProviderMeta {
+  type: string;
+  label: string;
+  description?: string;
+  enabled: boolean;
+  config_schema: VectorDBProviderField[];
+}
+
+export interface VectorDBCurrentConfig {
+  type: string;
+  config: Record<string, string>;
+  label?: string;
+  enabled?: boolean;
+}
+
+export interface UpdateVectorDBConfigResponse {
+  config: VectorDBCurrentConfig;
+  stats: VectorDBStats;
+}
+
 export const vectorDBApi = {
+  getProviders: () => client<VectorDBProviderMeta[]>('/vector-db/providers', { method: 'GET' }),
+  getConfig: () => client<VectorDBCurrentConfig>('/vector-db/config', { method: 'GET' }),
+  getStats: () => client<VectorDBStats>('/vector-db/stats', { method: 'GET' }),
+  updateConfig: (payload: { type: string; config: Record<string, string> }) =>
+    client<UpdateVectorDBConfigResponse>('/vector-db/config', { method: 'POST', json: payload }),
   clearAll: () => client('/vector-db/clear-all', { method: 'POST' }),
-};
+};

web/src/components/PathSelectorModal.tsx

@@ -0,0 +1,143 @@
+import { memo, useEffect, useMemo, useState } from 'react';
+import { Modal, Button, List, Typography, Space, Input, message } from 'antd';
+import { FolderOutlined, ArrowUpOutlined } from '@ant-design/icons';
+import { useI18n } from '../i18n';
+import { vfsApi, type VfsEntry } from '../api/client';
+import { getFileIcon } from '../pages/FileExplorerPage/components/FileIcons';
+
+export type PathSelectorMode = 'directory' | 'file' | 'any';
+
+interface PathSelectorModalProps {
+  open: boolean;
+  mode?: PathSelectorMode;
+  initialPath?: string;
+  onOk: (path: string) => void;
+  onCancel: () => void;
+}
+
+function normalizePath(p: string): string {
+  if (!p) return '/';
+  const s = ('/' + p).replace(/\/+/, '/');
+  return s.replace(/\\/g, '/').replace(/\/+$/, '') || '/';
+}
+
+function joinPath(dir: string, name: string): string {
+  const base = normalizePath(dir);
+  if (base === '/') return `/${name}`;
+  return `${base}/${name}`.replace(/\/+/, '/');
+}
+
+const PathSelectorModal = memo(function PathSelectorModal({ open, mode = 'directory', initialPath = '/', onOk, onCancel }: PathSelectorModalProps) {
+  const { t } = useI18n();
+  const [path, setPath] = useState<string>(normalizePath(initialPath));
+  const [entries, setEntries] = useState<VfsEntry[]>([]);
+  const [loading, setLoading] = useState(false);
+  const [selected, setSelected] = useState<string | null>(null); // selected file name within current folder
+
+  const title = useMemo(() => {
+    if (mode === 'file') return t('Select File');
+    if (mode === 'any') return t('Select Path');
+    return t('Select Folder');
+  }, [mode, t]);
+
+  const load = async (p: string) => {
+    setLoading(true);
+    try {
+      const listing = await vfsApi.list(p, 1, 500, 'name', 'asc');
+      setEntries(listing.entries);
+      setPath(listing.path || p);
+      setSelected(null);
+    } catch (e: any) {
+      message.error(e.message || t('Load failed'));
+    } finally {
+      setLoading(false);
+    }
+  };
+
+  useEffect(() => {
+    if (open) {
+      load(normalizePath(initialPath));
+    }
+    // eslint-disable-next-line react-hooks/exhaustive-deps
+  }, [open, initialPath]);
+
+  const canOk = useMemo(() => {
+    if (mode === 'file') return !!selected;
+    return true;
+  }, [mode, selected]);
+
+  const handleOk = () => {
+    if (mode === 'directory') {
+      onOk(normalizePath(path));
+      return;
+    }
+    if (mode === 'file') {
+      if (!selected) {
+        message.warning(t('Please select a file'));
+        return;
+      }
+      onOk(joinPath(path, selected));
+      return;
+    }
+    // any
+    if (selected) onOk(joinPath(path, selected));
+    else onOk(normalizePath(path));
+  };
+
+  const goUp = () => {
+    const cur = normalizePath(path);
+    if (cur === '/') return;
+    const parent = cur.replace(/\/+$/, '').split('/').slice(0, -1).join('/') || '/';
+    load(parent);
+  };
+
+  return (
+    <Modal
+      title={title}
+      open={open}
+      onCancel={onCancel}
+      onOk={handleOk}
+      okButtonProps={{ disabled: !canOk }}
+      width={720}
+    >
+      <Space style={{ width: '100%', marginBottom: 12 }} align="center">
+        <Typography.Text type="secondary">{t('Current')}</Typography.Text>
+        <Input value={path} readOnly />
+        <Button onClick={goUp} icon={<ArrowUpOutlined />} disabled={path === '/'}>{t('Up')}</Button>
+        {mode !== 'file' && (
+          <Button type="primary" onClick={() => onOk(normalizePath(path))}>{t('Select Current Folder')}</Button>
+        )}
+      </Space>
+
+      <List
+        bordered
+        loading={loading}
+        dataSource={entries}
+        style={{ maxHeight: 420, overflow: 'auto' }}
+        renderItem={(item) => {
+          const isSelected = selected === item.name && !item.is_dir;
+          return (
+            <List.Item
+              onClick={() => {
+                if (item.is_dir) {
+                  load(joinPath(path, item.name));
+                } else {
+                  setSelected((prev) => (prev === item.name ? null : item.name));
+                }
+              }}
+              style={{ cursor: 'pointer', background: isSelected ? 'rgba(22,119,255,0.08)' : undefined }}
+            >
+              <Space>
+                {item.is_dir ? <FolderOutlined /> : getFileIcon(item.name)}
+                <Typography.Text strong={item.is_dir}>{item.name}</Typography.Text>
+              </Space>
+            </List.Item>
+          );
+        }}
+      />
+    </Modal>
+  );
+});
+
+export default PathSelectorModal;
+

web/src/components/ProfileModal.tsx

@@ -62,6 +62,7 @@ const ProfileModal = memo(function ProfileModal({ open, onClose }: ProfileModalP
       confirmLoading={loading}
       okText={t('Save')}
       cancelText={t('Cancel')}
+      forceRender
     >
       <Form form={form} layout="vertical">
         <Form.Item name="username" label={t('Username')}>

web/src/contexts/ThemeContext.tsx

@@ -1,10 +1,12 @@
 import React, { createContext, useContext, useEffect, useMemo, useRef, useState } from 'react';
 import { ConfigProvider, theme as antdTheme } from 'antd';
 import zhCN from 'antd/locale/zh_CN';
+import enUS from 'antd/locale/en_US';
 import type { ThemeConfig } from 'antd/es/config-provider/context';
 import { getAllConfig } from '../api/config';
 import { useAuth } from './AuthContext';
 import baseTheme from '../theme';
+import { useI18n } from '../i18n';
 
 type ThemeMode = 'light' | 'dark' | 'system';
 
@@ -101,6 +103,7 @@ function buildThemeConfig(state: ThemeState, systemDark: boolean): ThemeConfig {
 
 export function ThemeProvider({ children }: { children: React.ReactNode }) {
   const { isAuthenticated } = useAuth();
+  const { lang } = useI18n();
   const systemDark = useSystemDarkPreferred();
   const [state, setState] = useState<ThemeState>({ mode: 'light' });
   const styleTagRef = useRef<HTMLStyleElement | null>(null);
@@ -163,6 +166,7 @@ export function ThemeProvider({ children }: { children: React.ReactNode }) {
 
   const themeConfig = useMemo(() => buildThemeConfig(state, systemDark), [state, systemDark]);
   const resolvedMode: ThemeMode = useMemo(() => (state.mode === 'system' ? (systemDark ? 'dark' : 'light') : state.mode), [state.mode, systemDark]);
+  const locale = useMemo(() => (lang === 'zh' ? zhCN : enUS), [lang]);
 
   const ctxValue = useMemo<ThemeContextType>(() => ({
     refreshTheme,
@@ -173,7 +177,7 @@ export function ThemeProvider({ children }: { children: React.ReactNode }) {
 
   return (
     <Ctx.Provider value={ctxValue}>
-      <ConfigProvider theme={{ ...themeConfig, cssVar: true }} locale={zhCN}>
+      <ConfigProvider theme={{ ...themeConfig, cssVar: true }} locale={locale}>
         {children}
       </ConfigProvider>
     </Ctx.Provider>

web/src/global.css

@@ -40,3 +40,29 @@ body { font-family: system-ui,-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto
 .fx-grid-item .thumb .badge { position:absolute; top:6px; left:6px; background: var(--ant-color-primary, #111); color:#fff; font-size:10px; padding:2px 4px; border-radius:6px; line-height:1; letter-spacing:.5px; }
 .fx-grid-item .name { font-weight:600; font-size:13px; }
 .ellipsis { overflow:hidden; white-space:nowrap; text-overflow:ellipsis; }
+
+.processors-tabs {
+  flex: 1;
+  display: flex;
+  flex-direction: column;
+  min-height: 0;
+  padding: 5px;
+}
+.processors-tabs .ant-tabs-content-holder,
+.processors-tabs .ant-tabs-content {
+  flex: 1;
+  height: 100%;
+  min-height: 0;
+  display: flex;
+  flex-direction: column;
+}
+.processors-tabs .ant-tabs-tabpane {
+  flex: 1;
+  height: 100%;
+  min-height: 0;
+  display: none;
+  flex-direction: column;
+}
+.processors-tabs .ant-tabs-tabpane-active {
+  display: flex;
+}

web/src/i18n/locales/en.ts

@@ -53,6 +53,9 @@ export const en = {
   'Cancel failed': 'Cancel failed',
   'Load failed': 'Load failed',
   'Are you sure to cancel share?': 'Are you sure to cancel share?',
+  'Clear expired shares': 'Clear expired shares',
+  'Confirm clear expired shares?': 'Confirm clear expired shares?',
+  'Cleared {count} expired shares': 'Cleared {count} expired shares',
 
   'Share Name': 'Share Name',
   'Share Content': 'Share Content',
@@ -97,6 +100,8 @@ export const en = {
   'Open': 'Open',
   'Open With': 'Open With',
   'Default': 'Default',
+  'Processor': 'Processor',
+  'Share': 'Share',
   'Rename': 'Rename',
   'Delete': 'Delete',
   'Details': 'Details',
@@ -197,9 +202,38 @@ export const en = {
   'AI Settings': 'AI Settings',
   'Vision Model': 'Vision Model',
   'Embedding Model': 'Embedding Model',
+  'Embedding Dimension': 'Embedding Dimension',
   'Vector Database': 'Vector Database',
   'Vector Database Settings': 'Vector Database Settings',
+  'Current Statistics': 'Current Statistics',
+  'Collections': 'Collections',
+  'Vectors': 'Vectors',
+  'Database Size': 'Database Size',
+  'Estimated Memory': 'Estimated Memory',
+  'No collections': 'No collections',
+  'Dimension': 'Dimension',
+  'Non-vector collection': 'Non-vector collection',
+  'Estimated memory': 'Estimated memory',
+  'Indexes': 'Indexes',
+  'Unnamed index': 'Unnamed index',
+  'Indexed rows': 'Indexed rows',
+  'Pending rows': 'Pending rows',
+  'Estimated memory is calculated as vectors x dimension x 4 bytes (float32).': 'Estimated memory is calculated as vectors x dimension x 4 bytes (float32).',
+  'Database Provider': 'Database Provider',
+  'Please select a provider': 'Please select a provider',
+  'Coming soon': 'Coming soon',
+  'This provider is not available yet': 'This provider is not available yet',
+  'Database file path': 'Database file path',
+  'Server URI': 'Server URI',
+  'Token': 'Token',
+  'Server URL': 'Server URL',
+  'API Key': 'API Key',
+  'Embedded Milvus Lite (local file storage).': 'Embedded Milvus Lite (local file storage).',
+  'Remote Milvus instance accessed via URI.': 'Remote Milvus instance accessed via URI.',
+  'Qdrant vector database (HTTP API).': 'Qdrant vector database (HTTP API).',
   'Database Type': 'Database Type',
+  'Confirm embedding dimension change': 'Confirm embedding dimension change',
+  'Changing the embedding dimension will clear the vector database automatically. You will need to rebuild indexes afterwards. Continue?': 'Changing the embedding dimension will clear the vector database automatically. You will need to rebuild indexes afterwards. Continue?',
   'Confirm clear vector database?': 'Confirm clear vector database?',
   'This will delete all collections irreversibly.': 'This will delete all collections irreversibly.',
   'Confirm Clear': 'Confirm Clear',
@@ -308,6 +342,45 @@ export const en = {
   // Processor flow
   'Processing finished': 'Processing finished',
   'Processing failed': 'Processing failed',
+  'Processors': 'Processors',
+  'Processor List': 'Processor List',
+  'Reload': 'Reload',
+  'Run Processor': 'Run Processor',
+  'Target Path': 'Target Path',
+  'Please select a path': 'Please select a path',
+  'Select Directory': 'Select Directory',
+  'Overwrite original': 'Overwrite original',
+  'Save To': 'Save To',
+  'Optional output path': 'Optional output path',
+  'Run': 'Run',
+  'Select a processor': 'Select a processor',
+  'No module path': 'No module path',
+  'Source saved': 'Source saved',
+  'Processors reloaded': 'Processors reloaded',
+  'Unsaved changes': 'Unsaved changes',
+  'Switching processor will discard unsaved changes. Continue?': 'Switching processor will discard unsaved changes. Continue?',
+  'Task submitted': 'Task submitted',
+  'Supported Extensions': 'Supported Extensions',
+  'All': 'All',
+  'Produces File': 'Produces File',
+  'Yes': 'Yes',
+  'No': 'No',
+  'Please select a processor': 'Please select a processor',
+  'Select a path': 'Select a path',
+  'Source Editor': 'Source Editor',
+  'Module Path': 'Module Path',
+  'Directory processing always overwrites original files': 'Directory processing always overwrites original files',
+  'No data': 'No data',
+
+  // Path selector
+  'Select File': 'Select File',
+  'Select Path': 'Select Path',
+  'Select Folder': 'Select Folder',
+  'Select': 'Select',
+  'Current': 'Current',
+  'Up': 'Up',
+  'Select Current Folder': 'Select Current Folder',
+  'Please select a file': 'Please select a file',
 
   // Plugins page
   'Installed successfully': 'Installed successfully',

web/src/i18n/locales/zh.ts

@@ -8,7 +8,7 @@ export const zh = {
   'All Files': '全部文件',
   'Manage': '管理',
   'System': '系统',
-  'Automation': '自动化',
+  'Automation': '自动任务',
   'My Shares': '我的分享',
   'Offline Downloads': '离线下载',
   'Adapters': '存储挂载',
@@ -25,7 +25,7 @@ export const zh = {
   'Account Settings': '账户设置',
   'Language': '语言',
   'Chinese': '中文',
-  'English': '英文',
+  'English': 'English',
   'Full Name': '昵称',
   'Email': '邮箱',
   'Change Password': '修改密码',
@@ -57,6 +57,9 @@ export const zh = {
   'Cancel failed': '取消失败',
   'Load failed': '加载失败',
   'Are you sure to cancel share?': '确认取消分享?',
+  'Clear expired shares': '清空过期分享',
+  'Confirm clear expired shares?': '确认清空过期分享?',
+  'Cleared {count} expired shares': '已清理 {count} 个过期分享',
   'Share Name': '分享名称',
   'Share Content': '分享内容',
   'Created At': '创建时间',
@@ -98,6 +101,8 @@ export const zh = {
   'Open': '打开',
   'Open With': '打开方式',
   'Default': '默认',
+  'Processor': '处理器',
+  'Share': '分享',
   'Rename': '重命名',
   'Delete': '删除',
   'Details': '详情',
@@ -199,9 +204,38 @@ export const zh = {
   'AI Settings': 'AI设置',
   'Vision Model': '视觉模型',
   'Embedding Model': '嵌入模型',
+  'Embedding Dimension': '向量维度',
   'Vector Database': '向量数据库',
   'Vector Database Settings': '向量数据库设置',
+  'Current Statistics': '当前统计',
+  'Collections': '集合',
+  'Vectors': '向量',
+  'Database Size': '数据库大小',
+  'Estimated Memory': '估算内存',
+  'No collections': '暂无集合',
+  'Dimension': '维度',
+  'Non-vector collection': '非向量集合',
+  'Estimated memory': '估算内存',
+  'Indexes': '索引',
+  'Unnamed index': '未命名索引',
+  'Indexed rows': '已索引行数',
+  'Pending rows': '待索引行数',
+  'Estimated memory is calculated as vectors x dimension x 4 bytes (float32).': '估算内存 = 向量数量 x 维度 x 4 字节（float32）。',
+  'Database Provider': '数据库提供者',
+  'Please select a provider': '请选择提供者',
+  'Coming soon': '敬请期待',
+  'This provider is not available yet': '该提供者暂不可用',
+  'Database file path': '数据库文件路径',
+  'Server URI': '服务器 URI',
+  'Token': '令牌',
+  'Server URL': '服务器地址',
+  'API Key': 'API Key',
+  'Embedded Milvus Lite (local file storage).': '嵌入式 Milvus Lite，本地文件存储。',
+  'Remote Milvus instance accessed via URI.': '通过 URI 访问的远程 Milvus 实例。',
+  'Qdrant vector database (HTTP API).': 'Qdrant 向量数据库（HTTP API）。',
   'Database Type': '数据库类型',
+  'Confirm embedding dimension change': '确认修改向量维度',
+  'Changing the embedding dimension will clear the vector database automatically. You will need to rebuild indexes afterwards. Continue?': '修改向量维度会自动清空向量数据库，之后需要重建索引，是否继续？',
   'Confirm clear vector database?': '确认清空向量数据库？',
   'This will delete all collections irreversibly.': '此操作将删除所有集合中的所有数据，且不可逆。',
   'Confirm Clear': '确认清空',
@@ -310,6 +344,45 @@ export const zh = {
   // Processor flow
   'Processing finished': '处理完成',
   'Processing failed': '处理失败',
+  'Processors': '处理器',
+  'Processor List': '处理器列表',
+  'Reload': '重载',
+  'Run Processor': '运行处理器',
+  'Target Path': '目标路径',
+  'Please select a path': '请选择路径',
+  'Select Directory': '选择目录',
+  'Overwrite original': '覆盖原文件',
+  'Save To': '保存到',
+  'Optional output path': '可选输出路径',
+  'Run': '运行',
+  'Select a processor': '选择处理器',
+  'No module path': '未检测到模块路径',
+  'Source saved': '源码已保存',
+  'Processors reloaded': '处理器已重载',
+  'Unsaved changes': '存在未保存的修改',
+  'Switching processor will discard unsaved changes. Continue?': '切换处理器会丢失未保存的修改，确认继续？',
+  'Task submitted': '任务已提交',
+  'Supported Extensions': '支持的扩展名',
+  'All': '全部',
+  'Produces File': '生成文件',
+  'Yes': '是',
+  'No': '否',
+  'Please select a processor': '请选择处理器',
+  'Select a path': '请选择路径',
+  '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',
+  'No data': '暂无数据',
+
+  // Path selector
+  'Select File': '选择文件',
+  'Select Path': '选择路径',
+  'Select Folder': '选择目录',
+  'Select': '选择',
+  'Current': '当前',
+  'Up': '上一级',
+  'Select Current Folder': '选择当前目录',
+  'Please select a file': '请选择一个文件',
 
   // Plugins page
   'Installed successfully': '安装成功',

web/src/layout/nav.ts

@@ -9,6 +9,7 @@ import {
   BugOutlined,
   DatabaseOutlined,
   AppstoreOutlined,
+  CodeOutlined,
 } from '@ant-design/icons';
 import type { ReactNode } from 'react';
 
@@ -27,6 +28,7 @@ export const navGroups: NavGroup[] = [
     key: 'manage',
     title: 'Manage',
     children: [
+      { key: 'processors', icon: React.createElement(CodeOutlined), label: 'Processors' },
       { key: 'tasks', icon: React.createElement(RobotOutlined), label: 'Automation' },
       { key: 'share', icon: React.createElement(ShareAltOutlined), label: 'My Shares' },
       { key: 'offline', icon: React.createElement(CloudDownloadOutlined), label: 'Offline Downloads' },

web/src/pages/AdaptersPage.tsx

@@ -223,7 +223,7 @@ const AdaptersPage = memo(function AdaptersPage() {
         width={480}
         open={open}
         onClose={() => { setOpen(false); setEditing(null); }}
-        destroyOnClose
+        destroyOnHidden
         extra={
           <Space>
             <Button onClick={() => { setOpen(false); setEditing(null); }}>{t('Cancel')}</Button>

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

@@ -49,6 +49,18 @@ export const GridView: React.FC<Props> = ({ entries, thumbs, selectedEntries, lo
     const toHex = (v: number) => v.toString(16).padStart(2, '0');
     return `#${toHex(r)}${toHex(g)}${toHex(b)}`;
   };
+  const toRgba = (hex: string, alpha: number) => {
+    const s = hex.replace('#', '');
+    const normalized = s.length === 3 ? s.split('').map(c => c + c).join('') : s;
+    const num = parseInt(normalized, 16);
+    if (Number.isNaN(num) || normalized.length !== 6) {
+      return `rgba(22, 119, 255, ${alpha})`;
+    }
+    const r = (num >> 16) & 255;
+    const g = (num >> 8) & 255;
+    const b = num & 255;
+    return `rgba(${r}, ${g}, ${b}, ${alpha})`;
+  };
   const containerRef = useRef<HTMLDivElement | null>(null);
   const itemRefs = useRef<Record<string, HTMLDivElement | null>>({});
   const startRef = useRef<{ x: number, y: number } | null>(null);
@@ -168,7 +180,7 @@ export const GridView: React.FC<Props> = ({ entries, thumbs, selectedEntries, lo
             width: rect.width,
             height: rect.height,
             border: '1px dashed var(--ant-color-border, rgba(0,0,0,0.4))',
-            background: 'var(--ant-color-primary-bg, rgba(0, 120, 212, 0.08))',
+            background: toRgba(String(token.colorPrimary || '#1677ff'), 0.16),
             zIndex: 999
           }}
         />

web/src/pages/FileExplorerPage/components/Modals/CreateDirModal.tsx

@@ -29,7 +29,7 @@ export const CreateDirModal: React.FC<CreateDirModalProps> = ({ open, onOk, onCa
       onOk={handleOk}
       onCancel={onCancel}
       okButtonProps={{ disabled: !name.trim() }}
-      destroyOnClose
+      destroyOnHidden
     >
       <Input
         placeholder={t('Folder Name')}

web/src/pages/FileExplorerPage/components/Modals/ProcessorModal.tsx

@@ -58,7 +58,7 @@ export const ProcessorModal: React.FC<ProcessorModalProps> = (props) => {
       onCancel={onCancel}
       onOk={onOk}
       confirmLoading={loading}
-      destroyOnClose
+      destroyOnHidden
     >
       <Form form={form} layout="vertical" onValuesChange={handleFormValuesChange}>
         <Form.Item name="processor_type" label={t('Processor')} required>

web/src/pages/FileExplorerPage/components/Modals/RenameModal.tsx

@@ -32,7 +32,7 @@ export const RenameModal: React.FC<RenameModalProps> = ({ entry, onOk, onCancel
       onOk={handleOk}
       onCancel={onCancel}
       okButtonProps={{ disabled: !name.trim() || name.trim() === entry?.name }}
-      destroyOnClose
+      destroyOnHidden
     >
       <Input
         placeholder={t('New Name')}

web/src/pages/FileExplorerPage/hooks/useProcessor.ts

@@ -49,8 +49,8 @@ export function useProcessor({ path, processorTypes, refresh }: ProcessorParams)
         overwrite: overwrite ? true : undefined,
       };
 
-      await processorsApi.process(params);
-      message.success(t('Processing finished'));
+      const resp = await processorsApi.process(params);
+      message.success(`${t('Task submitted')}: ${resp.task_id}`);
       setModal({ entry: null, visible: false });
       if (overwrite || savingPath) refresh();
     } catch (e: any) {

web/src/pages/ProcessorsPage.tsx

@@ -0,0 +1,501 @@
+import { memo, useCallback, useEffect, useMemo, useState } from 'react';
+import {
+  Button,
+  Card,
+  Empty,
+  Flex,
+  Form,
+  Input,
+  message,
+  Modal,
+  Space,
+  Spin,
+  Switch,
+  Tabs,
+  Tag,
+  Typography,
+  theme,
+} from 'antd';
+import Editor from '@monaco-editor/react';
+import { ProcessorConfigForm } from '../components/ProcessorConfigForm';
+import PathSelectorModal, { type PathSelectorMode } from '../components/PathSelectorModal';
+import { processorsApi, type ProcessorTypeMeta } from '../api/processors';
+import { useI18n } from '../i18n';
+
+const { Text } = Typography;
+
+type TabKey = 'editor' | 'runner';
+
+const ProcessorsPage = memo(function ProcessorsPage() {
+  const { t } = useI18n();
+  const { token } = theme.useToken();
+  const [messageApi, contextHolder] = message.useMessage();
+  const [processors, setProcessors] = useState<ProcessorTypeMeta[]>([]);
+  const [loadingList, setLoadingList] = useState(false);
+  const [selectedType, setSelectedType] = useState<string>('');
+  const [source, setSource] = useState('');
+  const [initialSource, setInitialSource] = useState('');
+  const [modulePath, setModulePath] = useState('');
+  const [sourceLoading, setSourceLoading] = useState(false);
+  const [savingSource, setSavingSource] = useState(false);
+  const [reloading, setReloading] = useState(false);
+  const [form] = Form.useForm();
+  const [running, setRunning] = useState(false);
+  const [isDirectory, setIsDirectory] = useState(false);
+  const [pathModalOpen, setPathModalOpen] = useState(false);
+  const [pathModalMode, setPathModalMode] = useState<PathSelectorMode>('file');
+  const [pathModalField, setPathModalField] = useState<'path' | 'save_to'>('path');
+  const [activeTab, setActiveTab] = useState<TabKey>('editor');
+
+  const isDirty = source !== initialSource;
+
+  const selectedProcessorMeta = useMemo(
+    () => processors.find(p => p.type === selectedType),
+    [processors, selectedType]
+  );
+
+  const loadList = useCallback(async () => {
+    setLoadingList(true);
+    try {
+      const list = await processorsApi.list();
+      setProcessors(list);
+    } catch (err: any) {
+      messageApi.error(err?.message || t('Load failed'));
+    } finally {
+      setLoadingList(false);
+    }
+  }, [messageApi, t]);
+
+  useEffect(() => {
+    loadList();
+  }, [loadList]);
+
+  useEffect(() => {
+    if (!processors.length) {
+      setSelectedType('');
+      return;
+    }
+    if (!selectedType) {
+      setSelectedType(processors[0].type);
+    } else if (!processors.some(p => p.type === selectedType)) {
+      setSelectedType(processors[0].type);
+    }
+  }, [processors, selectedType]);
+
+  useEffect(() => {
+    if (!selectedType) {
+      setSource('');
+      setInitialSource('');
+      setModulePath('');
+      return;
+    }
+    const controller = new AbortController();
+    setSource('');
+    setInitialSource('');
+    setModulePath('');
+    setSourceLoading(true);
+    processorsApi.getSource(selectedType)
+      .then(resp => {
+        if (controller.signal.aborted) return;
+        setSource(resp.source ?? '');
+        setInitialSource(resp.source ?? '');
+        setModulePath(resp.module_path ?? '');
+      })
+      .catch((err: any) => {
+        if (controller.signal.aborted) return;
+        messageApi.error(err?.message || t('Load failed'));
+        setSource('');
+        setInitialSource('');
+        setModulePath('');
+      })
+      .finally(() => {
+        if (!controller.signal.aborted) {
+          setSourceLoading(false);
+        }
+      });
+    return () => controller.abort();
+  }, [messageApi, selectedType, t]);
+
+  useEffect(() => {
+    if (!selectedProcessorMeta) {
+      form.resetFields();
+      setIsDirectory(false);
+      return;
+    }
+    form.resetFields();
+    const defaults: Record<string, any> = {};
+    selectedProcessorMeta.config_schema?.forEach(field => {
+      if (field.default !== undefined) {
+        defaults[field.key] = field.default;
+      }
+    });
+    form.setFieldsValue({
+      path: '',
+      overwrite: !!selectedProcessorMeta.produces_file,
+      save_to: undefined,
+      config: defaults,
+    });
+    setIsDirectory(false);
+  }, [selectedProcessorMeta, form]);
+
+  const overwriteValue = Form.useWatch('overwrite', form) ?? false;
+
+  useEffect(() => {
+    if (overwriteValue) {
+      form.setFieldsValue({ save_to: undefined });
+    }
+  }, [overwriteValue, form]);
+
+  useEffect(() => {
+    if (isDirectory) {
+      form.setFieldsValue({ overwrite: true, save_to: undefined });
+    }
+  }, [isDirectory, form]);
+
+  const handleSelectProcessor = useCallback((type: string) => {
+    if (type === selectedType) return;
+    if (isDirty) {
+      Modal.confirm({
+        title: t('Unsaved changes'),
+        content: t('Switching processor will discard unsaved changes. Continue?'),
+        okText: t('Confirm'),
+        cancelText: t('Cancel'),
+        onOk: () => {
+          setSelectedType(type);
+          setActiveTab('editor');
+        },
+      });
+    } else {
+      setSelectedType(type);
+      setActiveTab('editor');
+    }
+  }, [isDirty, selectedType, t]);
+
+  const handleSaveSource = useCallback(async () => {
+    if (!selectedType) return;
+    try {
+      setSavingSource(true);
+      await processorsApi.updateSource(selectedType, source);
+      setInitialSource(source);
+      messageApi.success(t('Source saved'));
+    } catch (err: any) {
+      messageApi.error(err?.message || t('Operation failed'));
+    } finally {
+      setSavingSource(false);
+    }
+  }, [messageApi, selectedType, source, t]);
+
+  const handleReloadProcessors = useCallback(async () => {
+    try {
+      setReloading(true);
+      await processorsApi.reload();
+      messageApi.success(t('Processors reloaded'));
+      await loadList();
+    } catch (err: any) {
+      messageApi.error(err?.message || t('Operation failed'));
+    } finally {
+      setReloading(false);
+    }
+  }, [loadList, messageApi, t]);
+
+  const openPathSelector = useCallback((field: 'path' | 'save_to', mode: PathSelectorMode) => {
+    setPathModalField(field);
+    setPathModalMode(mode);
+    setPathModalOpen(true);
+  }, []);
+
+  const handlePathSelected = useCallback((selectedPath: string) => {
+    if (pathModalField === 'path') {
+      form.setFieldsValue({ path: selectedPath });
+      setIsDirectory(pathModalMode === 'directory');
+    } else {
+      form.setFieldsValue({ save_to: selectedPath });
+    }
+    setPathModalOpen(false);
+  }, [form, pathModalField, pathModalMode]);
+
+  const handleRun = useCallback(async () => {
+    if (!selectedType) {
+      messageApi.warning(t('Please select a processor'));
+      return;
+    }
+    try {
+      const values = await form.validateFields();
+      const schema = selectedProcessorMeta?.config_schema || [];
+      const finalConfig: Record<string, any> = {};
+      schema.forEach(field => {
+        const value = values.config?.[field.key];
+        if (value === undefined) {
+          finalConfig[field.key] = field.default;
+        } else {
+          finalConfig[field.key] = value;
+        }
+      });
+      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 resp = await processorsApi.process(payload);
+      messageApi.success(`${t('Task submitted')}: ${resp.task_id}`);
+    } catch (err: any) {
+      if (err?.errorFields) {
+        return;
+      }
+      messageApi.error(err?.message || t('Operation failed'));
+    } finally {
+      setRunning(false);
+    }
+  }, [form, messageApi, selectedProcessorMeta, selectedType, t]);
+
+  const selectedConfigPath = pathModalField === 'path'
+    ? (selectedType ? form.getFieldValue('path') : undefined) || '/'
+    : (selectedType ? form.getFieldValue('save_to') : undefined) || '/';
+
+  const renderProcessorList = () => {
+    if (loadingList) {
+      return (
+        <Flex align="center" justify="center" style={{ height: '100%' }}>
+          <Spin />
+        </Flex>
+      );
+    }
+    if (!processors.length) {
+      return (
+        <Flex align="center" justify="center" style={{ height: '100%' }}>
+          <Empty description={t('No data')} />
+        </Flex>
+      );
+    }
+    return (
+      <div style={{ padding: 8, overflowY: 'auto', height: '100%' }}>
+        {processors.map(item => {
+          const selected = item.type === selectedType;
+          const onClick = () => handleSelectProcessor(item.type);
+          return (
+            <div
+              key={item.type}
+              onClick={onClick}
+              style={{
+                border: `1px solid ${selected ? token.colorPrimary : token.colorBorderSecondary}`,
+                background: selected ? token.colorPrimaryBg : token.colorBgContainer,
+                borderRadius: 10,
+                padding: 12,
+                marginBottom: 8,
+                cursor: 'pointer',
+                transition: 'all 0.2s ease',
+              }}
+            >
+              <Flex justify="space-between" align="center">
+                <Space size={8} align="center">
+                  <span
+                    style={{
+                      width: 8,
+                      height: 8,
+                      borderRadius: '50%',
+                      background: selected ? token.colorPrimary : token.colorBorderSecondary,
+                      display: 'inline-block',
+                    }}
+                  />
+                  <Text strong>{item.name}</Text>
+                </Space>
+                <Tag color={selected ? token.colorPrimary : token.colorBorderSecondary}>{item.type}</Tag>
+              </Flex>
+              <Space direction="vertical" size={6} style={{ marginTop: 8 }}>
+                <div>
+                  <Text type="secondary" style={{ marginRight: 8 }}>{t('Supported Extensions')}:</Text>
+                  {item.supported_exts?.length ? (
+                    <Space wrap size={[4, 4]}>
+                      {item.supported_exts.map(ext => (
+                        <Tag key={ext}>{ext}</Tag>
+                      ))}
+                    </Space>
+                  ) : (
+                    <Tag>{t('All')}</Tag>
+                  )}
+                </div>
+                <Text type="secondary">
+                  {t('Produces File')}: {item.produces_file ? t('Yes') : t('No')}
+                </Text>
+              </Space>
+            </div>
+          );
+        })}
+      </div>
+    );
+  };
+
+  const tabs = [
+    {
+      key: 'editor',
+      label: t('Source Editor'),
+      children: selectedType ? (
+        <div style={{ height: '100%', display: 'flex', flexDirection: 'column' }}>
+          <div style={{ padding: '8px 12px', borderBottom: `1px solid ${token.colorBorderSecondary}` }}>
+            {modulePath ? (
+              <Space size={8}>
+                <Text type="secondary">{t('Module Path')}:</Text>
+                <Text code>{modulePath}</Text>
+              </Space>
+            ) : (
+              <Text type="secondary">{t('No module path')}</Text>
+            )}
+          </div>
+          <div style={{ flex: 1, minHeight: 0 }}>
+            {sourceLoading ? (
+              <Flex align="center" justify="center" style={{ height: '100%' }}>
+                <Spin />
+              </Flex>
+            ) : (
+              <Editor
+                language="python"
+                value={source}
+                onChange={(val) => setSource(val ?? '')}
+                height="100%"
+                options={{
+                  automaticLayout: true,
+                  minimap: { enabled: false },
+                  fontSize: 13,
+                  scrollBeyondLastLine: false,
+                }}
+              />
+            )}
+          </div>
+        </div>
+      ) : (
+        <Empty style={{ marginTop: 64 }} description={t('Select a processor')} />
+      ),
+    },
+    {
+      key: 'runner',
+      label: t('Run Processor'),
+      forceRender: true,
+      children: (
+        <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
+              >
+                <Flex gap={8} align="center">
+                  <div style={{ flex: 1 }}>
+                    <Form.Item
+                      name="path"
+                      rules={[{ required: true, message: t('Please select a path') }]}
+                      noStyle
+                    >
+                      <Input placeholder={t('Select a path')} />
+                    </Form.Item>
+                  </div>
+                  <Button onClick={() => openPathSelector('path', 'file')}>{t('Select File')}</Button>
+                  <Button onClick={() => openPathSelector('path', 'directory')}>{t('Select Directory')}</Button>
+                </Flex>
+              </Form.Item>
+
+              <Form.Item
+                name="overwrite"
+                label={t('Overwrite original')}
+                valuePropName="checked"
+              >
+                <Switch disabled={isDirectory} />
+              </Form.Item>
+
+              {selectedProcessorMeta?.produces_file && !overwriteValue && (
+                <Form.Item label={t('Save To')}>
+                  <Flex gap={8} align="center">
+                    <div style={{ flex: 1 }}>
+                      <Form.Item name="save_to" noStyle>
+                        <Input placeholder={t('Optional output path')} />
+                      </Form.Item>
+                    </div>
+                    <Button onClick={() => openPathSelector('save_to', 'any')}>{t('Select')}</Button>
+                  </Flex>
+                </Form.Item>
+              )}
+
+              <ProcessorConfigForm
+                processorMeta={selectedProcessorMeta}
+                form={form}
+                configPath={['config']}
+              />
+
+              <Form.Item>
+                <Button type="primary" onClick={handleRun} loading={running} disabled={!selectedType}>
+                  {t('Run')}
+                </Button>
+              </Form.Item>
+            </>
+          ) : (
+            <Empty style={{ marginTop: 64 }} description={t('Select a processor')} />
+          )}
+        </Form>
+      ),
+    },
+  ];
+
+  return (
+    <>
+      {contextHolder}
+      <Flex gap={16} style={{ height: 'calc(100vh - 88px)' }}>
+        <Card
+          style={{ flex: '0 0 320px', minWidth: 280, display: 'flex', flexDirection: 'column' }}
+          title={t('Processor List')}
+          extra={
+            <Space size={8}>
+              <Button size="small" onClick={loadList} loading={loadingList}>{t('Refresh')}</Button>
+              <Button size="small" onClick={handleReloadProcessors} loading={reloading}>{t('Reload')}</Button>
+            </Space>
+          }
+          styles={{ body: { padding: 0, flex: 1, display: 'flex' } }}
+        >
+          {renderProcessorList()}
+        </Card>
+
+        <Card
+          style={{ flex: 1, minWidth: 0, display: 'flex', flexDirection: 'column' }}
+          title={selectedProcessorMeta ? `${selectedProcessorMeta.name} (${selectedProcessorMeta.type})` : t('Select a processor')}
+          extra={
+            <Space size={8}>
+              <Button size="small" onClick={handleSaveSource} loading={savingSource} disabled={!selectedType || !isDirty}>
+                {t('Save')}
+              </Button>
+              <Button size="small" onClick={handleReloadProcessors} loading={reloading} disabled={!selectedType}>
+                {t('Reload')}
+              </Button>
+            </Space>
+          }
+          styles={{ body: { padding: 0, flex: 1, display: 'flex', flexDirection: 'column' } }}
+        >
+          <Tabs
+            activeKey={activeTab}
+            onChange={key => setActiveTab(key as TabKey)}
+            items={tabs as any}
+            className="processors-tabs"
+            tabBarGutter={32}
+          />
+        </Card>
+      </Flex>
+
+      <PathSelectorModal
+        open={pathModalOpen}
+        mode={pathModalMode}
+        initialPath={selectedConfigPath}
+        onOk={handlePathSelected}
+        onCancel={() => setPathModalOpen(false)}
+      />
+    </>
+  );
+});
+
+export default ProcessorsPage;

web/src/pages/SharePage.tsx

@@ -44,6 +44,16 @@ const SharePage = memo(function SharePage() {
     }
   };
 
+  const handleClearExpired = async () => {
+    try {
+      const res = await shareApi.clearExpired();
+      message.success(t('Cleared {count} expired shares', { count: String(res.deleted_count) }));
+      fetchList();
+    } catch (e: any) {
+      message.error(e.message || t('Clear failed'));
+    }
+  };
+
   const columns = [
     { 
       title: t('Share Name'), 
@@ -100,7 +110,14 @@ const SharePage = memo(function SharePage() {
   return (
     <PageCard
       title={t('My Shares')}
-      extra={<Button onClick={fetchList} loading={loading}>{t('Refresh')}</Button>}
+      extra={
+        <Space>
+          <Button onClick={fetchList} loading={loading}>{t('Refresh')}</Button>
+          <Popconfirm title={t('Confirm clear expired shares?')} onConfirm={handleClearExpired}>
+            <Button danger>{t('Clear expired shares')}</Button>
+          </Popconfirm>
+        </Space>
+      }
     >
       <Table
         rowKey="id"

web/src/pages/SystemSettingsPage/SystemSettingsPage.tsx

@@ -1,8 +1,8 @@
-import { Form, Input, Button, message, Tabs, Space, Card, Select, Modal, Radio, InputNumber } from 'antd';
-import { useEffect, useState } from 'react';
+import { Form, Input, Button, message, Tabs, Space, Card, Select, Modal, Radio, InputNumber, Spin, Empty, Alert } from 'antd';
+import { useEffect, useState, useCallback } from 'react';
 import PageCard from '../../components/PageCard';
 import { getAllConfig, setConfig } from '../../api/config';
-import { vectorDBApi } from '../../api/vectorDB';
+import { vectorDBApi, type VectorDBStats, type VectorDBProviderMeta, type VectorDBCurrentConfig } from '../../api/vectorDB';
 import { AppstoreOutlined, RobotOutlined, DatabaseOutlined, SkinOutlined } from '@ant-design/icons';
 import { useTheme } from '../../contexts/ThemeContext';
 import '../../styles/settings-tabs.css';
@@ -21,13 +21,30 @@ const VISION_CONFIG_KEYS = [
   { key: 'AI_VISION_API_KEY', label: 'Vision API Key' },
 ];
 
+const DEFAULT_EMBED_DIMENSION = 4096;
+const EMBED_DIM_KEY = 'AI_EMBED_DIM';
+
 const EMBED_CONFIG_KEYS = [
   { 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];
+const ALL_AI_KEYS = [...VISION_CONFIG_KEYS, ...EMBED_CONFIG_KEYS, { key: EMBED_DIM_KEY, default: DEFAULT_EMBED_DIMENSION }];
+
+const formatBytes = (bytes?: number | null) => {
+  if (bytes === null || bytes === undefined) return '-';
+  if (bytes === 0) return '0 B';
+  const units = ['B', 'KB', 'MB', 'GB', 'TB'];
+  let value = bytes;
+  let unitIndex = 0;
+  while (value >= 1024 && unitIndex < units.length - 1) {
+    value /= 1024;
+    unitIndex += 1;
+  }
+  const precision = value >= 10 || unitIndex === 0 ? 0 : 1;
+  return `${value.toFixed(precision)} ${units[unitIndex]}`;
+};
 
 // Theme related config keys
 const THEME_KEYS = {
@@ -39,9 +56,19 @@ const THEME_KEYS = {
 };
 
 export default function SystemSettingsPage() {
+  const [vectorConfigForm] = Form.useForm();
   const [loading, setLoading] = useState(false);
   const [config, setConfigState] = useState<Record<string, string> | null>(null);
   const [activeTab, setActiveTab] = useState('appearance');
+  const [vectorStats, setVectorStats] = useState<VectorDBStats | null>(null);
+  const [vectorStatsLoading, setVectorStatsLoading] = useState(false);
+  const [vectorStatsError, setVectorStatsError] = useState<string | null>(null);
+  const [vectorProviders, setVectorProviders] = useState<VectorDBProviderMeta[]>([]);
+  const [vectorConfig, setVectorConfig] = useState<VectorDBCurrentConfig | null>(null);
+  const [vectorConfigLoading, setVectorConfigLoading] = useState(false);
+  const [vectorConfigSaving, setVectorConfigSaving] = useState(false);
+  const [vectorMetaError, setVectorMetaError] = useState<string | null>(null);
+  const [selectedProviderType, setSelectedProviderType] = useState<string | null>(null);
   const { refreshTheme, previewTheme } = useTheme();
   const { t } = useI18n();
 
@@ -49,6 +76,72 @@ export default function SystemSettingsPage() {
     getAllConfig().then((data) => setConfigState(data as Record<string, string>));
   }, []);
 
+  const fetchVectorStats = useCallback(async () => {
+    setVectorStatsLoading(true);
+    setVectorStatsError(null);
+    try {
+      const data = await vectorDBApi.getStats();
+      setVectorStats(data);
+    } catch (e: any) {
+      const msg = e?.message || t('Load failed');
+      setVectorStatsError(msg);
+      message.error(msg);
+    } finally {
+      setVectorStatsLoading(false);
+    }
+  }, [t]);
+
+  const buildProviderConfigValues = useCallback((provider: VectorDBProviderMeta | undefined, existing?: Record<string, string>) => {
+    if (!provider) return {};
+    const values: Record<string, string> = {};
+    const schema = provider.config_schema || [];
+    schema.forEach((field) => {
+      const current = existing && existing[field.key] !== undefined && existing[field.key] !== null
+        ? String(existing[field.key])
+        : undefined;
+      if (current !== undefined) {
+        values[field.key] = current;
+      } else if (field.default !== undefined && field.default !== null) {
+        values[field.key] = String(field.default);
+      } else {
+        values[field.key] = '';
+      }
+    });
+    return values;
+  }, []);
+
+  const fetchVectorMeta = useCallback(async () => {
+    setVectorConfigLoading(true);
+    setVectorMetaError(null);
+    try {
+      const [providers, current] = await Promise.all([
+        vectorDBApi.getProviders(),
+        vectorDBApi.getConfig(),
+      ]);
+      setVectorProviders(providers);
+      setVectorConfig(current);
+
+      const enabled = providers.filter((item) => item.enabled);
+      let nextType: string | null = current?.type ?? null;
+      if (nextType && !providers.some((item) => item.type === nextType)) {
+        nextType = null;
+      }
+      if (!nextType) {
+        nextType = enabled[0]?.type ?? providers[0]?.type ?? null;
+      }
+      setSelectedProviderType(nextType);
+      const provider = providers.find((item) => item.type === nextType);
+      const configValues = buildProviderConfigValues(provider, nextType === current?.type ? current?.config : undefined);
+      vectorConfigForm.setFieldsValue({ type: nextType || undefined, config: configValues });
+    } catch (e: any) {
+      const msg = e?.message || t('Load failed');
+      setVectorMetaError(msg);
+      message.error(msg);
+    } finally {
+      setVectorConfigLoading(false);
+    }
+  }, [buildProviderConfigValues, message, t, vectorConfigForm]);
+
   const handleSave = async (values: any) => {
     setLoading(true);
     try {
@@ -67,6 +160,40 @@ export default function SystemSettingsPage() {
     setLoading(false);
   };
 
+  const handleProviderChange = useCallback((value: string) => {
+    setSelectedProviderType(value);
+    const provider = vectorProviders.find((item) => item.type === value);
+    const existing = value === vectorConfig?.type ? vectorConfig?.config : undefined;
+    const configValues = buildProviderConfigValues(provider, existing);
+    vectorConfigForm.setFieldsValue({ type: value, config: configValues });
+  }, [vectorProviders, vectorConfig, buildProviderConfigValues, vectorConfigForm]);
+
+  const handleVectorConfigSave = useCallback(async (values: { type: string; config?: Record<string, string> }) => {
+    if (!values?.type) {
+      return;
+    }
+    setVectorConfigSaving(true);
+    try {
+      const configPayload = Object.fromEntries(
+        Object.entries(values.config || {}).filter(([, val]) => val !== undefined && val !== null && String(val).trim() !== '')
+          .map(([key, val]) => [key, String(val)])
+      );
+      const response = await vectorDBApi.updateConfig({ type: values.type, config: configPayload });
+      setVectorConfig(response.config);
+      setVectorStats(response.stats);
+      setVectorStatsError(null);
+      setSelectedProviderType(response.config.type);
+      const provider = vectorProviders.find((item) => item.type === response.config.type);
+      const mergedValues = buildProviderConfigValues(provider, response.config.config);
+      vectorConfigForm.setFieldsValue({ type: response.config.type, config: mergedValues });
+      message.success(t('Saved successfully'));
+    } catch (e: any) {
+      message.error(e?.message || t('Save failed'));
+    } finally {
+      setVectorConfigSaving(false);
+    }
+  }, [buildProviderConfigValues, message, t, vectorConfigForm, vectorProviders]);
+
   // 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') {
@@ -74,6 +201,27 @@ export default function SystemSettingsPage() {
     }
   }, [activeTab]);
 
+  useEffect(() => {
+    if (activeTab === 'vector-db') {
+      if (!vectorProviders.length && !vectorConfigLoading) {
+        fetchVectorMeta();
+      }
+      if (!vectorStats && !vectorStatsLoading) {
+        fetchVectorStats();
+      }
+    }
+  }, [
+    activeTab,
+    fetchVectorMeta,
+    fetchVectorStats,
+    vectorProviders.length,
+    vectorConfigLoading,
+    vectorStats,
+    vectorStatsLoading,
+  ]);
+
+  const selectedProvider = vectorProviders.find((item) => item.type === selectedProviderType || (!selectedProviderType && item.enabled));
+
   if (!config) {
     return <PageCard title={t('System Settings')}><div>{t('Loading...')}</div></PageCard>;
   }
@@ -213,9 +361,27 @@ export default function SystemSettingsPage() {
                 <Form
                   layout="vertical"
                   initialValues={{
-                    ...Object.fromEntries(ALL_AI_KEYS.map(({ key, default: def }) => [key, config[key] ?? def ?? ''])),
+                    ...Object.fromEntries(ALL_AI_KEYS.map(({ key, default: def }) => [key, key === EMBED_DIM_KEY
+                      ? Number(config[key] ?? def ?? DEFAULT_EMBED_DIMENSION)
+                      : config[key] ?? def ?? ''])),
+                  }}
+                  onFinish={async (vals) => {
+                    const currentDim = Number(config[EMBED_DIM_KEY] ?? DEFAULT_EMBED_DIMENSION);
+                    const nextDim = Number(vals[EMBED_DIM_KEY] ?? DEFAULT_EMBED_DIMENSION);
+                    if (currentDim !== nextDim) {
+                      Modal.confirm({
+                        title: t('Confirm embedding dimension change'),
+                        content: t('Changing the embedding dimension will clear the vector database automatically. You will need to rebuild indexes afterwards. Continue?'),
+                        okText: t('Confirm'),
+                        cancelText: t('Cancel'),
+                        onOk: async () => {
+                          await handleSave(vals);
+                        },
+                      });
+                      return;
+                    }
+                    await handleSave(vals);
                   }}
-                  onFinish={handleSave}
                   style={{ marginTop: 24 }}
                   key={JSON.stringify(config)}
                 >
@@ -232,6 +398,9 @@ export default function SystemSettingsPage() {
                         <Input size="large" />
                       </Form.Item>
                     ))}
+                    <Form.Item name={EMBED_DIM_KEY} label={t('Embedding Dimension')}>
+                      <InputNumber min={1} max={32768} style={{ width: '100%' }} />
+                    </Form.Item>
                   </Card>
                   <Form.Item style={{ marginTop: 24 }}>
                     <Button type="primary" htmlType="submit" loading={loading} block>
@@ -251,41 +420,187 @@ export default function SystemSettingsPage() {
               ),
               children: (
                 <Card title={t('Vector Database Settings')} style={{ marginTop: 24 }}>
-                  <Form layout="vertical">
-                    <Form.Item label={t('Database Type')}>
-                      <Select
-                        size="large"
-                        value={'Milvus Lite'}
-                        disabled
-                        options={[{ value: 'Milvus Lite', label: 'Milvus Lite' }]}
-                      />
-                    </Form.Item>
-                    <Form.Item>
-                      <Button
-                        danger
-                        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'));
-                              } catch (e: any) {
-                                message.error(e.message || t('Clear failed'));
-                              }
-                            },
-                          });
-                        }}
+                  <Space direction="vertical" size={24} style={{ width: '100%' }}>
+                    <Space direction="vertical" size={16} style={{ width: '100%' }}>
+                      <div style={{ display: 'flex', justifyContent: 'space-between', alignItems: 'center', flexWrap: 'wrap', gap: 12 }}>
+                        <strong>{t('Current Statistics')}</strong>
+                        <Button onClick={() => { fetchVectorMeta(); fetchVectorStats(); }} loading={vectorStatsLoading || vectorConfigLoading} disabled={(vectorStatsLoading || vectorConfigLoading) && !vectorStats}>
+                          {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>
+                                </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')} />
+                      )}
+                    </Space>
+                    {vectorConfigLoading && !vectorProviders.length ? (
+                      <Spin />
+                    ) : (
+                      <Form
+                        layout="vertical"
+                        form={vectorConfigForm}
+                        onFinish={handleVectorConfigSave}
+                        initialValues={{ type: selectedProviderType || undefined, config: {} }}
                       >
-                        {t('Clear Vector DB')}
-                      </Button>
-                    </Form.Item>
-                  </Form>
+                        <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>
               ),
             },

web/src/pages/TasksPage.tsx

@@ -5,6 +5,7 @@ import { tasksApi, type AutomationTask, type QueuedTask } from '../api/tasks';
 import { processorsApi, type ProcessorTypeMeta } from '../api/processors';
 import { ProcessorConfigForm } from '../components/ProcessorConfigForm';
 import { useI18n } from '../i18n';
+import PathSelectorModal from '../components/PathSelectorModal';
 
 const TasksPage = memo(function TasksPage() {
   const [loading, setLoading] = useState(false);
@@ -17,6 +18,7 @@ const TasksPage = memo(function TasksPage() {
   const [queuedTasks, setQueuedTasks] = useState<QueuedTask[]>([]);
   const [queueLoading, setQueueLoading] = useState(false);
   const { t } = useI18n();
+  const [pathPickerOpen, setPathPickerOpen] = useState(false);
 
   const fetchList = useCallback(async () => {
     setLoading(true);
@@ -151,6 +153,7 @@ const TasksPage = memo(function TasksPage() {
 
   const selectedProcessor = Form.useWatch('processor_type', form);
   const currentProcessorMeta = availableProcessors.find(p => p.type === selectedProcessor);
+  const watchedPathPattern = Form.useWatch('path_pattern', form);
 
 
   return (
@@ -177,7 +180,7 @@ const TasksPage = memo(function TasksPage() {
         width={480}
         open={open}
         onClose={() => { setOpen(false); setEditing(null); }}
-        destroyOnClose
+        destroyOnHidden
         extra={
           <Space>
             <Button onClick={() => { setOpen(false); setEditing(null); }}>{t('Cancel')}</Button>
@@ -197,7 +200,10 @@ const TasksPage = memo(function TasksPage() {
           </Form.Item>
           <Typography.Title level={5} style={{ marginTop: 8, fontSize: 14 }}>{t('Matching Rules')}</Typography.Title>
           <Form.Item name="path_pattern" label={t('Path Prefix (optional)')}>
-            <Input placeholder="/images/screenshots" />
+            <Input
+              placeholder="/images/screenshots"
+              addonAfter={<Button size="small" onClick={() => setPathPickerOpen(true)}>{t('Select')}</Button>}
+            />
           </Form.Item>
           <Form.Item name="filename_regex" label={t('Filename Regex (optional)')}>
             <Input placeholder=".*\.png$" />
@@ -219,6 +225,13 @@ const TasksPage = memo(function TasksPage() {
           />
         </Form>
       </Drawer>
+      <PathSelectorModal
+        open={pathPickerOpen}
+        mode="directory"
+        initialPath={watchedPathPattern || '/'}
+        onCancel={() => setPathPickerOpen(false)}
+        onOk={(p) => { form.setFieldsValue({ path_pattern: p }); setPathPickerOpen(false); }}
+      />
       <Modal
         title={t('Current Task Queue')}
         open={queueModalOpen}

web/src/router/LayoutShell.tsx

@@ -7,6 +7,7 @@ import FileExplorerPage from '../pages/FileExplorerPage/FileExplorerPage.tsx';
 import AdaptersPage from '../pages/AdaptersPage.tsx';
 import SharePage from '../pages/SharePage.tsx';
 import TasksPage from '../pages/TasksPage.tsx';
+import ProcessorsPage from '../pages/ProcessorsPage.tsx';
 import OfflineDownloadPage from '../pages/OfflineDownloadPage.tsx';
 import SystemSettingsPage from '../pages/SystemSettingsPage/SystemSettingsPage.tsx';
 import LogsPage from '../pages/LogsPage.tsx';
@@ -37,6 +38,7 @@ const ShellBody = memo(function ShellBody() {
               {navKey === 'files' && <FileExplorerPage />}
               {navKey === 'share' && <SharePage />}
               {navKey === 'tasks' && <TasksPage />}
+              {navKey === 'processors' && <ProcessorsPage />}
               {navKey === 'offline' && <OfflineDownloadPage />}
               {navKey === 'plugins' && <PluginsPage />}
               {navKey === 'settings' && <SystemSettingsPage />}