feat: v1.2.0 - 图片去重与管理、微信机器人优化、搜索设置可配置

主要功能:
- 图片上传时 OCR 内容去重（3个上传端点统一使用公共函数 _check_ocr_duplicate）
- 图片管理 Tab：展示所有图片、手动删除、一键去重
- 搜索结果详情弹窗增加删除按钮（带确认弹窗）
- 图片管理卡片点击查看详情（复用 showOcrDetailModal）
- 搜索限制和 LLM 批量判断数量可通过网站设置
- MiniMax API 调用添加 reasoning_split=True
- 企业微信机器人：WebSocket 长连接、图片搜索、配置化搜索数量
- 版本号升级至 1.2.0

sql/init.sql

@@ -0,0 +1,129 @@
+-- ============================================================
+-- EduBrain 数据库初始化脚本
+-- 包含 pgvector 扩展、zhparser 中文分词扩展
+-- ============================================================
+
+-- 创建 pgvector 扩展（向量相似度搜索）
+CREATE EXTENSION IF NOT EXISTS vector;
+
+-- 创建 zhparser 中文分词扩展（全文搜索）
+CREATE EXTENSION IF NOT EXISTS zhparser;
+
+-- 创建基于 zhparser 的中文全文搜索配置
+CREATE TEXT SEARCH CONFIGURATION chinese_zh (PARSER = zhparser);
+
+-- 配置中文全文搜索映射：名词、动词、形容词、成语、叹词、习语使用 simple 字典
+ALTER TEXT SEARCH CONFIGURATION chinese_zh ADD MAPPING FOR n,v,a,i,e,l WITH simple;
+
+-- ============================================================
+-- 知识页面表
+-- ============================================================
+CREATE TABLE IF NOT EXISTS knowledge_pages (
+    id              SERIAL PRIMARY KEY,
+    title           VARCHAR(500) NOT NULL,
+    content         TEXT NOT NULL,
+    source_file     VARCHAR(500),
+    course_name     VARCHAR(200),
+    teacher_name    VARCHAR(100),
+    live_date       VARCHAR(20),
+    page_number     INTEGER,
+    metadata_json   TEXT,
+    created_at      TIMESTAMPTZ DEFAULT NOW(),
+    updated_at      TIMESTAMPTZ DEFAULT NOW()
+);
+
+-- 索引
+CREATE INDEX IF NOT EXISTS idx_pages_course ON knowledge_pages(course_name);
+CREATE INDEX IF NOT EXISTS idx_pages_teacher ON knowledge_pages(teacher_name);
+CREATE INDEX IF NOT EXISTS idx_pages_date ON knowledge_pages(live_date);
+CREATE INDEX IF NOT EXISTS idx_pages_created ON knowledge_pages(created_at DESC);
+
+-- ============================================================
+-- 知识分块表（向量检索单元）
+-- ============================================================
+CREATE TABLE IF NOT EXISTS knowledge_chunks (
+    id              SERIAL PRIMARY KEY,
+    page_id         INTEGER NOT NULL REFERENCES knowledge_pages(id) ON DELETE CASCADE,
+    chunk_index     INTEGER NOT NULL,
+    content         TEXT NOT NULL,
+    embedding       vector(1024),           -- 嵌入向量（默认 1024 维）
+    search_vector   TSVECTOR,               -- 中文全文搜索向量
+    created_at      TIMESTAMPTZ DEFAULT NOW(),
+    updated_at      TIMESTAMPTZ DEFAULT NOW()
+);
+
+-- 索引
+CREATE INDEX IF NOT EXISTS idx_chunks_page ON knowledge_chunks(page_id);
+CREATE INDEX IF NOT EXISTS idx_chunks_page_index ON knowledge_chunks(page_id, chunk_index);
+
+-- HNSW 向量索引（适合高维向量，查询速度快）
+CREATE INDEX IF NOT EXISTS idx_chunks_embedding
+    ON knowledge_chunks
+    USING hnsw (embedding vector_cosine_ops)
+    WITH (m = 16, ef_construction = 200);
+
+-- GIN 全文搜索索引
+CREATE INDEX IF NOT EXISTS idx_chunks_search
+    ON knowledge_chunks
+    USING gin(search_vector);
+
+-- ============================================================
+-- OCR 图片记录表
+-- ============================================================
+CREATE TABLE IF NOT EXISTS ocr_images (
+    id              SERIAL PRIMARY KEY,
+    file_path       VARCHAR(500) NOT NULL,
+    ocr_text        TEXT,
+    confidence      FLOAT,
+    provider        VARCHAR(50),
+    status          VARCHAR(20) DEFAULT 'pending',
+    error_message   TEXT,
+    created_at      TIMESTAMPTZ DEFAULT NOW(),
+    updated_at      TIMESTAMPTZ DEFAULT NOW()
+);
+
+-- 索引
+CREATE INDEX IF NOT EXISTS idx_ocr_status ON ocr_images(status);
+CREATE INDEX IF NOT EXISTS idx_ocr_created ON ocr_images(created_at DESC);
+
+-- ============================================================
+-- updated_at 自动更新触发器
+-- ============================================================
+CREATE OR REPLACE FUNCTION update_updated_at_column()
+RETURNS TRIGGER AS $$
+BEGIN
+    NEW.updated_at = NOW();
+    RETURN NEW;
+END;
+$$ LANGUAGE plpgsql;
+
+-- 为所有表添加 updated_at 触发器
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_trigger
+        WHERE tgname = 'tr_pages_updated_at'
+    ) THEN
+        CREATE TRIGGER tr_pages_updated_at
+            BEFORE UPDATE ON knowledge_pages
+            FOR EACH ROW EXECUTE FUNCTION update_updated_at_column();
+    END IF;
+
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_trigger
+        WHERE tgname = 'tr_chunks_updated_at'
+    ) THEN
+        CREATE TRIGGER tr_chunks_updated_at
+            BEFORE UPDATE ON knowledge_chunks
+            FOR EACH ROW EXECUTE FUNCTION update_updated_at_column();
+    END IF;
+
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_trigger
+        WHERE tgname = 'tr_ocr_updated_at'
+    ) THEN
+        CREATE TRIGGER tr_ocr_updated_at
+            BEFORE UPDATE ON ocr_images
+            FOR EACH ROW EXECUTE FUNCTION update_updated_at_column();
+    END IF;
+END $$;