Add Phase 3 feature documentation

- 新增实体编辑 API (名称、类型、定义、别名)
- 新增实体删除和合并功能
- 新增关系管理 (创建、删除)
- 新增转录文本编辑功能
- 新增划词创建实体功能
- 前端新增实体编辑器模态框
- 前端新增右键菜单和工具栏
- 文本与图谱双向联动优化

Dockerfile

@@ -1,29 +1,33 @@
+# InsightFlow - Audio to Knowledge Graph Platform
+# Phase 3: Memory & Growth
+
 FROM python:3.11-slim
 
 WORKDIR /app
 
-# Install uv
+# Install system dependencies
-COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
-
-# Install system deps
 RUN apt-get update && apt-get install -y \
-    ffmpeg \
+    gcc \
-    git \
+    libpq-dev \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy project files
+# Copy backend requirements
-COPY backend/pyproject.toml backend/uv.lock ./
+COPY backend/requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
 
-# Install dependencies using uv sync
+# Copy application code
-RUN uv sync --frozen --no-install-project
-
-# Copy code
 COPY backend/ ./backend/
 COPY frontend/ ./frontend/
 
-# Install project
+# Create data directory
-RUN uv sync --frozen
+RUN mkdir -p /app/data
 
+# Set environment variables
+ENV PYTHONPATH=/app
+ENV DB_PATH=/app/data/insightflow.db
+
+# Expose port
 EXPOSE 8000
 
-CMD ["uv", "run", "python", "backend/main.py"]
+# Run the application
+CMD ["python", "-m", "uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "8000"]

README.md

@@ -1,27 +1,88 @@
-# InsightFlow
+# InsightFlow - Audio to Knowledge Graph Platform
 
-音频与文档的领域知识构建平台
+## Phase 3: Memory & Growth - Completed ✅
 
-## 产品定位
+### 新增功能
-将会议录音和文档转化为结构化的知识图谱，通过人机回圈(Human-in-the-Loop)实现知识持续生长。
 
-## 核心特性
+#### 1. 多文件图谱融合 ✅
-- 🎙️ ASR 语音识别 + 热词注入
+- 支持上传多个音频文件到同一项目
-- 🧠 LLM 实体抽取与解释
+- 系统自动对齐实体，合并图谱
-- 🔗 双视图联动（文档视图 + 图谱视图）
+- 实体提及跨文件追踪
-- 📈 知识生长（多文件实体对齐）
+- 文件选择器切换不同转录内容
 
-## 技术栈
+#### 2. 实体对齐算法优化 ✅
-- 前端: Next.js + Tailwind
+- 新增 `entity_aligner.py` 模块
-- 后端: Node.js / Python
+- 支持使用 Kimi API embedding 进行语义相似度匹配
-- 数据库: MySQL + Neo4j
+- 余弦相似度计算
-- ASR: Whisper
+- 自动别名建议
-- LLM: OpenAI / Kimi
+- 批量实体对齐 API
 
-## 开发阶段
+#### 3. PDF/DOCX 文档导入 ✅
-- [ ] Phase 1: 骨架与单体分析 (MVP)
+- 新增 `document_processor.py` 模块
-- [ ] Phase 2: 交互与纠错工作台
+- 支持 PDF、DOCX、TXT、MD 格式
-- [ ] Phase 3: 记忆与生长
+- 文档文本提取并参与实体提取
+- 文档类型标记（音频/文档）
 
-## 文档
+#### 4. 项目知识库面板 ✅
-- [PRD v2.0](docs/PRD-v2.0.md)
+- 全新的知识库视图
+- 统计面板：实体数、关系数、文件数、术语数
+- 实体网格展示（带提及统计）
+- 关系列表展示
+- 术语表管理（添加/删除）
+- 文件列表展示
+
+### 技术栈
+- 后端: FastAPI + SQLite
+- 前端: 原生 HTML/JS + D3.js
+- ASR: 阿里云听悟
+- LLM: Kimi API
+- 文档处理: PyPDF2, python-docx
+
+### 部署
+
+```bash
+# 构建 Docker 镜像
+docker build -t insightflow:phase3 .
+
+# 运行容器
+docker run -d \
+  -p 18000:8000 \
+  -v /opt/data:/app/data \
+  -e KIMI_API_KEY=your_key \
+  -e ALIYUN_ACCESS_KEY_ID=your_key \
+  -e ALIYUN_ACCESS_KEY_SECRET=your_secret \
+  insightflow:phase3
+```
+
+### API 文档
+
+#### 新增 API
+
+**文档上传**
+```
+POST /api/v1/projects/{project_id}/upload-document
+Content-Type: multipart/form-data
+file: <文件>
+```
+
+**知识库查询**
+```
+GET /api/v1/projects/{project_id}/knowledge-base
+```
+
+**术语表管理**
+```
+POST /api/v1/projects/{project_id}/glossary
+GET /api/v1/projects/{project_id}/glossary
+DELETE /api/v1/glossary/{term_id}
+```
+
+**实体对齐**
+```
+POST /api/v1/projects/{project_id}/align-entities?threshold=0.85
+```
+
+### 数据库 Schema 更新
+- `transcripts` 表新增 `type` 字段（audio/document）
+- `entities` 表新增 `embedding` 字段
+- 新增索引优化查询性能

STATUS.md

@@ -4,11 +4,13 @@
 
 ## 当前阶段
 
-Phase 1: 骨架与单体分析 (MVP) - **已完成 ✅**
+Phase 3: 记忆与生长 - **已完成 ✅**
 
 ## 已完成
 
-### 后端 (backend/)
+### Phase 1: 骨架与单体分析 (MVP) ✅
+
+#### 后端 (backend/)
 - ✅ FastAPI 项目框架搭建
 - ✅ SQLite 数据库设计 (schema.sql)
 - ✅ 数据库管理模块 (db_manager.py)
@@ -26,7 +28,7 @@ Phase 1: 骨架与单体分析 (MVP) - **已完成 ✅**
 - ✅ entity_mentions 表数据写入
 - ✅ entity_relations 表数据写入
 
-### 前端 (frontend/)
+#### 前端 (frontend/)
 - ✅ 项目管理页面 (index.html)
 - ✅ 知识工作台页面 (workbench.html)
 - ✅ D3.js 知识图谱可视化
@@ -35,35 +37,97 @@ Phase 1: 骨架与单体分析 (MVP) - **已完成 ✅**
 - ✅ 转录文本中实体高亮显示
 - ✅ 图谱与文本联动（点击实体双向高亮）
 
-### 基础设施
+### Phase 2: 交互与纠错工作台 ✅
-- ✅ Dockerfile
-- ✅ docker-compose.yml
-- ✅ Git 仓库初始化
 
-## Phase 2 计划 (交互与纠错工作台) - **即将开始**
+#### 后端 API 新增
+- ✅ 实体编辑 API (PUT /api/v1/entities/{id})
+- ✅ 实体删除 API (DELETE /api/v1/entities/{id})
+- ✅ 实体合并 API (POST /api/v1/entities/{id}/merge)
+- ✅ 手动创建实体 API (POST /api/v1/projects/{id}/entities)
+- ✅ 关系创建 API (POST /api/v1/projects/{id}/relations)
+- ✅ 关系删除 API (DELETE /api/v1/relations/{id})
+- ✅ 转录编辑 API (PUT /api/v1/transcripts/{id})
 
-- 实体定义编辑功能
+#### 前端交互功能
-- 实体合并功能
+- ✅ 实体编辑器模态框（名称、类型、定义、别名）
-- 关系编辑功能（添加/删除）
+- ✅ 右键菜单（编辑实体、合并实体、标记为实体）
-- 人工修正数据保存
+- ✅ 实体合并功能
-- 文本编辑器增强（支持编辑转录文本）
+- ✅ 关系管理（添加、删除）
+- ✅ 转录文本编辑模式
+- ✅ 划词创建实体
+- ✅ 文本与图谱双向联动
 
-## Phase 3 计划 (记忆与生长)
+#### 数据库更新
+- ✅ update_entity() - 更新实体信息
+- ✅ delete_entity() - 删除实体及关联数据
+- ✅ delete_relation() - 删除关系
+- ✅ update_relation() - 更新关系
+- ✅ update_transcript() - 更新转录文本
 
-- 多文件图谱融合
+### Phase 3: 记忆与生长 ✅
-- 实体对齐算法优化
+
-- PDF/DOCX 文档导入
+#### 多文件图谱融合
-- 项目知识库面板
+- ✅ 支持上传多个音频文件到同一项目
+- ✅ 系统自动对齐实体，合并图谱
+- ✅ 实体提及跨文件追踪
+- ✅ 文件选择器切换不同转录内容
+- ✅ 转录列表 API 返回文件类型
+
+#### 实体对齐算法优化
+- ✅ 新增 `entity_aligner.py` 模块
+- ✅ 使用 Kimi API embedding 进行语义相似度匹配
+- ✅ 余弦相似度计算
+- ✅ 自动别名建议
+- ✅ 批量实体对齐 API
+- ✅ 实体对齐回退机制（字符串匹配）
+
+#### PDF/DOCX 文档导入
+- ✅ 新增 `document_processor.py` 模块
+- ✅ 支持 PDF、DOCX、TXT、MD 格式
+- ✅ 文档文本提取并参与实体提取
+- ✅ 文档上传 API (/api/v1/projects/{id}/upload-document)
+- ✅ 文档类型标记（audio/document）
+
+#### 项目知识库面板
+- ✅ 全新的知识库视图
+- ✅ 侧边栏导航切换（工作台/知识库）
+- ✅ 统计面板：实体数、关系数、文件数、术语数
+- ✅ 实体网格展示（带提及统计）
+- ✅ 关系列表展示
+- ✅ 术语表管理（添加/删除）
+- ✅ 文件列表展示（区分音频/文档）
+
+#### 术语表功能
+- ✅ 术语表数据库表 (glossary)
+- ✅ 添加术语 API
+- ✅ 获取术语列表 API
+- ✅ 删除术语 API
+- ✅ 前端术语表管理界面
+
+#### 数据库更新
+- ✅ transcripts 表新增 `type` 字段
+- ✅ entities 表新增 `embedding` 字段
+- ✅ 新增 glossary 表
+- ✅ 新增索引优化查询性能
 
 ## 技术债务
 
 - 听悟 SDK fallback 到 mock 需要更好的错误处理
-- 实体相似度匹配目前只是简单字符串包含，需要 embedding 方案
 - 前端需要状态管理（目前使用全局变量）
 - 需要添加 API 文档 (OpenAPI/Swagger)
+- Embedding 缓存需要持久化
+- 实体对齐算法需要更多测试
 
 ## 部署信息
 
 - 服务器: 122.51.127.111
 - 项目路径: /opt/projects/insightflow
 - 端口: 18000
+- Docker 镜像: insightflow:phase3
+
+## 下一步 (Phase 4)
+
+- 知识推理与问答
+- 实体属性扩展
+- 时间线视图
+- 导出功能（PDF/图片）

backend/db_manager.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
 """
-InsightFlow Database Manager
+InsightFlow Database Manager - Phase 3
 处理项目、实体、关系的持久化
+支持文档类型和多文件融合
 """
 
 import os
@@ -166,6 +167,18 @@ class DatabaseManager:
             (target_id, source_id)
         )
         
+        # 更新关系 - source 作为 source_entity_id
+        conn.execute(
+            "UPDATE entity_relations SET source_entity_id = ? WHERE source_entity_id = ?",
+            (target_id, source_id)
+        )
+        
+        # 更新关系 - source 作为 target_entity_id
+        conn.execute(
+            "UPDATE entity_relations SET target_entity_id = ? WHERE target_entity_id = ?",
+            (target_id, source_id)
+        )
+        
         # 删除源实体
         conn.execute("DELETE FROM entities WHERE id = ?", (source_id,))
         
@@ -222,13 +235,13 @@ class DatabaseManager:
         return [EntityMention(**dict(r)) for r in rows]
 
     # Transcript operations
-    def save_transcript(self, transcript_id: str, project_id: str, filename: str, full_text: str):
+    def save_transcript(self, transcript_id: str, project_id: str, filename: str, full_text: str, transcript_type: str = "audio"):
         """保存转录记录"""
         conn = self.get_conn()
         now = datetime.now().isoformat()
         conn.execute(
-            "INSERT INTO transcripts (id, project_id, filename, full_text, created_at) VALUES (?, ?, ?, ?, ?)",
+            "INSERT INTO transcripts (id, project_id, filename, full_text, type, created_at) VALUES (?, ?, ?, ?, ?, ?)",
-            (transcript_id, project_id, filename, full_text, now)
+            (transcript_id, project_id, filename, full_text, transcript_type, now)
         )
         conn.commit()
         conn.close()
@@ -291,6 +304,156 @@ class DatabaseManager:
         conn.close()
         return [dict(r) for r in rows]
     
+    def update_entity(self, entity_id: str, **kwargs) -> Entity:
+        """更新实体信息"""
+        conn = self.get_conn()
+        
+        # 构建更新字段
+        allowed_fields = ['name', 'type', 'definition', 'canonical_name']
+        updates = []
+        values = []
+        
+        for field in allowed_fields:
+            if field in kwargs:
+                updates.append(f"{field} = ?")
+                values.append(kwargs[field])
+        
+        # 处理别名
+        if 'aliases' in kwargs:
+            updates.append("aliases = ?")
+            values.append(json.dumps(kwargs['aliases']))
+        
+        if not updates:
+            conn.close()
+            return self.get_entity(entity_id)
+        
+        updates.append("updated_at = ?")
+        values.append(datetime.now().isoformat())
+        values.append(entity_id)
+        
+        query = f"UPDATE entities SET {', '.join(updates)} WHERE id = ?"
+        conn.execute(query, values)
+        conn.commit()
+        conn.close()
+        
+        return self.get_entity(entity_id)
+    
+    def delete_entity(self, entity_id: str):
+        """删除实体及其关联数据"""
+        conn = self.get_conn()
+        
+        # 删除提及记录
+        conn.execute("DELETE FROM entity_mentions WHERE entity_id = ?", (entity_id,))
+        
+        # 删除关系
+        conn.execute("DELETE FROM entity_relations WHERE source_entity_id = ? OR target_entity_id = ?", 
+                     (entity_id, entity_id))
+        
+        # 删除实体
+        conn.execute("DELETE FROM entities WHERE id = ?", (entity_id,))
+        
+        conn.commit()
+        conn.close()
+    
+    def delete_relation(self, relation_id: str):
+        """删除关系"""
+        conn = self.get_conn()
+        conn.execute("DELETE FROM entity_relations WHERE id = ?", (relation_id,))
+        conn.commit()
+        conn.close()
+    
+    def update_relation(self, relation_id: str, **kwargs) -> dict:
+        """更新关系"""
+        conn = self.get_conn()
+        
+        allowed_fields = ['relation_type', 'evidence']
+        updates = []
+        values = []
+        
+        for field in allowed_fields:
+            if field in kwargs:
+                updates.append(f"{field} = ?")
+                values.append(kwargs[field])
+        
+        if updates:
+            query = f"UPDATE entity_relations SET {', '.join(updates)} WHERE id = ?"
+            values.append(relation_id)
+            conn.execute(query, values)
+            conn.commit()
+        
+        row = conn.execute("SELECT * FROM entity_relations WHERE id = ?", (relation_id,)).fetchone()
+        conn.close()
+        
+        return dict(row) if row else None
+    
+    def update_transcript(self, transcript_id: str, full_text: str) -> dict:
+        """更新转录文本"""
+        conn = self.get_conn()
+        now = datetime.now().isoformat()
+        
+        conn.execute(
+            "UPDATE transcripts SET full_text = ?, updated_at = ? WHERE id = ?",
+            (full_text, now, transcript_id)
+        )
+        conn.commit()
+        
+        row = conn.execute("SELECT * FROM transcripts WHERE id = ?", (transcript_id,)).fetchone()
+        conn.close()
+        
+        return dict(row) if row else None
+    
+    # Phase 3: Glossary operations
+    def add_glossary_term(self, project_id: str, term: str, pronunciation: str = "") -> str:
+        """添加术语到术语表"""
+        conn = self.get_conn()
+        
+        # 检查是否已存在
+        existing = conn.execute(
+            "SELECT * FROM glossary WHERE project_id = ? AND term = ?",
+            (project_id, term)
+        ).fetchone()
+        
+        if existing:
+            # 更新频率
+            conn.execute(
+                "UPDATE glossary SET frequency = frequency + 1 WHERE id = ?",
+                (existing['id'],)
+            )
+            conn.commit()
+            conn.close()
+            return existing['id']
+        
+        term_id = str(uuid.uuid4())[:8]
+        conn.execute(
+            "INSERT INTO glossary (id, project_id, term, pronunciation, frequency) VALUES (?, ?, ?, ?, ?)",
+            (term_id, project_id, term, pronunciation, 1)
+        )
+        conn.commit()
+        conn.close()
+        return term_id
+    
+    def list_glossary(self, project_id: str) -> List[dict]:
+        """列出项目术语表"""
+        conn = self.get_conn()
+        rows = conn.execute(
+            "SELECT * FROM glossary WHERE project_id = ? ORDER BY frequency DESC",
+            (project_id,)
+        ).fetchall()
+        conn.close()
+        return [dict(r) for r in rows]
+    
+    def delete_glossary_term(self, term_id: str):
+        """删除术语"""
+        conn = self.get_conn()
+        conn.execute("DELETE FROM glossary WHERE id = ?", (term_id,))
+        conn.commit()
+        conn.close()
+    
+    # Phase 3: Get all entities for embedding
+    def get_all_entities_for_embedding(self, project_id: str) -> List[Entity]:
+        """获取所有实体用于 embedding 计算"""
+        return self.list_project_entities(project_id)
+
 
 # Singleton instance
 _db_manager = None

backend/document_processor.py

@@ -0,0 +1,180 @@
+#!/usr/bin/env python3
+"""
+Document Processor - Phase 3
+支持 PDF 和 DOCX 文档导入
+"""
+
+import os
+import io
+from typing import Dict, Optional
+
+class DocumentProcessor:
+    """文档处理器 - 提取 PDF/DOCX 文本"""
+    
+    def __init__(self):
+        self.supported_formats = {
+            '.pdf': self._extract_pdf,
+            '.docx': self._extract_docx,
+            '.doc': self._extract_docx,
+            '.txt': self._extract_txt,
+            '.md': self._extract_txt,
+        }
+    
+    def process(self, content: bytes, filename: str) -> Dict[str, str]:
+        """
+        处理文档并提取文本
+        
+        Args:
+            content: 文件二进制内容
+            filename: 文件名
+            
+        Returns:
+            {"text": "提取的文本内容", "format": "文件格式"}
+        """
+        ext = os.path.splitext(filename.lower())[1]
+        
+        if ext not in self.supported_formats:
+            raise ValueError(f"Unsupported file format: {ext}. Supported: {list(self.supported_formats.keys())}")
+        
+        extractor = self.supported_formats[ext]
+        text = extractor(content)
+        
+        # 清理文本
+        text = self._clean_text(text)
+        
+        return {
+            "text": text,
+            "format": ext,
+            "filename": filename
+        }
+    
+    def _extract_pdf(self, content: bytes) -> str:
+        """提取 PDF 文本"""
+        try:
+            import PyPDF2
+            pdf_file = io.BytesIO(content)
+            reader = PyPDF2.PdfReader(pdf_file)
+            
+            text_parts = []
+            for page in reader.pages:
+                page_text = page.extract_text()
+                if page_text:
+                    text_parts.append(page_text)
+            
+            return "\n\n".join(text_parts)
+        except ImportError:
+            # Fallback: 尝试使用 pdfplumber
+            try:
+                import pdfplumber
+                text_parts = []
+                with pdfplumber.open(io.BytesIO(content)) as pdf:
+                    for page in pdf.pages:
+                        page_text = page.extract_text()
+                        if page_text:
+                            text_parts.append(page_text)
+                return "\n\n".join(text_parts)
+            except ImportError:
+                raise ImportError("PDF processing requires PyPDF2 or pdfplumber. Install with: pip install PyPDF2")
+        except Exception as e:
+            raise ValueError(f"PDF extraction failed: {str(e)}")
+    
+    def _extract_docx(self, content: bytes) -> str:
+        """提取 DOCX 文本"""
+        try:
+            import docx
+            doc_file = io.BytesIO(content)
+            doc = docx.Document(doc_file)
+            
+            text_parts = []
+            for para in doc.paragraphs:
+                if para.text.strip():
+                    text_parts.append(para.text)
+            
+            # 提取表格中的文本
+            for table in doc.tables:
+                for row in table.rows:
+                    row_text = []
+                    for cell in row.cells:
+                        if cell.text.strip():
+                            row_text.append(cell.text.strip())
+                    if row_text:
+                        text_parts.append(" | ".join(row_text))
+            
+            return "\n\n".join(text_parts)
+        except ImportError:
+            raise ImportError("DOCX processing requires python-docx. Install with: pip install python-docx")
+        except Exception as e:
+            raise ValueError(f"DOCX extraction failed: {str(e)}")
+    
+    def _extract_txt(self, content: bytes) -> str:
+        """提取纯文本"""
+        # 尝试多种编码
+        encodings = ['utf-8', 'gbk', 'gb2312', 'latin-1']
+        
+        for encoding in encodings:
+            try:
+                return content.decode(encoding)
+            except UnicodeDecodeError:
+                continue
+        
+        # 如果都失败了，使用 latin-1 并忽略错误
+        return content.decode('latin-1', errors='ignore')
+    
+    def _clean_text(self, text: str) -> str:
+        """清理提取的文本"""
+        if not text:
+            return ""
+        
+        # 移除多余的空白字符
+        lines = text.split('\n')
+        cleaned_lines = []
+        
+        for line in lines:
+            line = line.strip()
+            # 移除空行，但保留段落分隔
+            if line:
+                cleaned_lines.append(line)
+        
+        # 合并行，保留段落结构
+        text = '\n\n'.join(cleaned_lines)
+        
+        # 移除多余的空格
+        text = ' '.join(text.split())
+        
+        # 移除控制字符
+        text = ''.join(char for char in text if ord(char) >= 32 or char in '\n\r\t')
+        
+        return text.strip()
+    
+    def is_supported(self, filename: str) -> bool:
+        """检查文件格式是否支持"""
+        ext = os.path.splitext(filename.lower())[1]
+        return ext in self.supported_formats
+
+
+# 简单的文本提取器（不需要外部依赖）
+class SimpleTextExtractor:
+    """简单的文本提取器，用于测试"""
+    
+    def extract(self, content: bytes, filename: str) -> str:
+        """尝试提取文本"""
+        encodings = ['utf-8', 'gbk', 'latin-1']
+        
+        for encoding in encodings:
+            try:
+                return content.decode(encoding)
+            except UnicodeDecodeError:
+                continue
+        
+        return content.decode('latin-1', errors='ignore')
+
+
+if __name__ == "__main__":
+    # 测试
+    processor = DocumentProcessor()
+    
+    # 测试文本提取
+    test_text = "Hello World\n\nThis is a test document.\n\nMultiple paragraphs."
+    result = processor.process(test_text.encode('utf-8'), "test.txt")
+    print(f"Text extraction test: {len(result['text'])} chars")
+    print(result['text'][:100])

backend/entity_aligner.py

@@ -0,0 +1,372 @@
+#!/usr/bin/env python3
+"""
+Entity Aligner - Phase 3
+使用 embedding 进行实体对齐
+"""
+
+import os
+import json
+import httpx
+import numpy as np
+from typing import List, Optional, Dict
+from dataclasses import dataclass
+
+# API Keys
+KIMI_API_KEY = os.getenv("KIMI_API_KEY", "")
+KIMI_BASE_URL = os.getenv("KIMI_BASE_URL", "https://api.kimi.com/coding")
+
+@dataclass
+class EntityEmbedding:
+    entity_id: str
+    name: str
+    definition: str
+    embedding: List[float]
+
+class EntityAligner:
+    """实体对齐器 - 使用 embedding 进行相似度匹配"""
+    
+    def __init__(self, similarity_threshold: float = 0.85):
+        self.similarity_threshold = similarity_threshold
+        self.embedding_cache: Dict[str, List[float]] = {}
+        
+    def get_embedding(self, text: str) -> Optional[List[float]]:
+        """
+        使用 Kimi API 获取文本的 embedding
+        
+        Args:
+            text: 输入文本
+            
+        Returns:
+            embedding 向量或 None
+        """
+        if not KIMI_API_KEY:
+            return None
+        
+        # 检查缓存
+        cache_key = hash(text)
+        if cache_key in self.embedding_cache:
+            return self.embedding_cache[cache_key]
+        
+        try:
+            response = httpx.post(
+                f"{KIMI_BASE_URL}/v1/embeddings",
+                headers={"Authorization": f"Bearer {KIMI_API_KEY}", "Content-Type": "application/json"},
+                json={
+                    "model": "k2p5",
+                    "input": text[:500]  # 限制长度
+                },
+                timeout=30.0
+            )
+            response.raise_for_status()
+            result = response.json()
+            
+            embedding = result["data"][0]["embedding"]
+            self.embedding_cache[cache_key] = embedding
+            return embedding
+            
+        except Exception as e:
+            print(f"Embedding API failed: {e}")
+            return None
+    
+    def compute_similarity(self, embedding1: List[float], embedding2: List[float]) -> float:
+        """
+        计算两个 embedding 的余弦相似度
+        
+        Args:
+            embedding1: 第一个向量
+            embedding2: 第二个向量
+            
+        Returns:
+            相似度分数 (0-1)
+        """
+        vec1 = np.array(embedding1)
+        vec2 = np.array(embedding2)
+        
+        # 余弦相似度
+        dot_product = np.dot(vec1, vec2)
+        norm1 = np.linalg.norm(vec1)
+        norm2 = np.linalg.norm(vec2)
+        
+        if norm1 == 0 or norm2 == 0:
+            return 0.0
+        
+        return float(dot_product / (norm1 * norm2))
+    
+    def get_entity_text(self, name: str, definition: str = "") -> str:
+        """
+        构建用于 embedding 的实体文本
+        
+        Args:
+            name: 实体名称
+            definition: 实体定义
+            
+        Returns:
+            组合文本
+        """
+        if definition:
+            return f"{name}: {definition}"
+        return name
+    
+    def find_similar_entity(
+        self, 
+        project_id: str, 
+        name: str, 
+        definition: str = "",
+        exclude_id: Optional[str] = None,
+        threshold: Optional[float] = None
+    ) -> Optional[object]:
+        """
+        查找相似的实体
+        
+        Args:
+            project_id: 项目 ID
+            name: 实体名称
+            definition: 实体定义
+            exclude_id: 要排除的实体 ID
+            threshold: 相似度阈值
+            
+        Returns:
+            相似的实体或 None
+        """
+        if threshold is None:
+            threshold = self.similarity_threshold
+        
+        try:
+            from db_manager import get_db_manager
+            db = get_db_manager()
+        except ImportError:
+            return None
+        
+        # 获取项目的所有实体
+        entities = db.get_all_entities_for_embedding(project_id)
+        
+        if not entities:
+            return None
+        
+        # 获取查询实体的 embedding
+        query_text = self.get_entity_text(name, definition)
+        query_embedding = self.get_embedding(query_text)
+        
+        if query_embedding is None:
+            # 如果 embedding API 失败，回退到简单匹配
+            return self._fallback_similarity_match(entities, name, exclude_id)
+        
+        best_match = None
+        best_score = threshold
+        
+        for entity in entities:
+            if exclude_id and entity.id == exclude_id:
+                continue
+            
+            # 获取实体的 embedding
+            entity_text = self.get_entity_text(entity.name, entity.definition)
+            entity_embedding = self.get_embedding(entity_text)
+            
+            if entity_embedding is None:
+                continue
+            
+            # 计算相似度
+            similarity = self.compute_similarity(query_embedding, entity_embedding)
+            
+            if similarity > best_score:
+                best_score = similarity
+                best_match = entity
+        
+        return best_match
+    
+    def _fallback_similarity_match(
+        self, 
+        entities: List[object], 
+        name: str, 
+        exclude_id: Optional[str] = None
+    ) -> Optional[object]:
+        """
+        回退到简单的相似度匹配（不使用 embedding）
+        
+        Args:
+            entities: 实体列表
+            name: 查询名称
+            exclude_id: 要排除的实体 ID
+            
+        Returns:
+            最相似的实体或 None
+        """
+        name_lower = name.lower()
+        
+        # 1. 精确匹配
+        for entity in entities:
+            if exclude_id and entity.id == exclude_id:
+                continue
+            if entity.name.lower() == name_lower:
+                return entity
+            if entity.aliases and name_lower in [a.lower() for a in entity.aliases]:
+                return entity
+        
+        # 2. 包含匹配
+        for entity in entities:
+            if exclude_id and entity.id == exclude_id:
+                continue
+            if name_lower in entity.name.lower() or entity.name.lower() in name_lower:
+                return entity
+        
+        return None
+    
+    def batch_align_entities(
+        self, 
+        project_id: str, 
+        new_entities: List[Dict],
+        threshold: Optional[float] = None
+    ) -> List[Dict]:
+        """
+        批量对齐实体
+        
+        Args:
+            project_id: 项目 ID
+            new_entities: 新实体列表 [{"name": "...", "definition": "..."}]
+            threshold: 相似度阈值
+            
+        Returns:
+            对齐结果列表 [{"new_entity": {...}, "matched_entity": {...}, "similarity": 0.9}]
+        """
+        if threshold is None:
+            threshold = self.similarity_threshold
+        
+        results = []
+        
+        for new_ent in new_entities:
+            matched = self.find_similar_entity(
+                project_id,
+                new_ent["name"],
+                new_ent.get("definition", ""),
+                threshold=threshold
+            )
+            
+            result = {
+                "new_entity": new_ent,
+                "matched_entity": None,
+                "similarity": 0.0,
+                "should_merge": False
+            }
+            
+            if matched:
+                # 计算相似度
+                query_text = self.get_entity_text(new_ent["name"], new_ent.get("definition", ""))
+                matched_text = self.get_entity_text(matched.name, matched.definition)
+                
+                query_emb = self.get_embedding(query_text)
+                matched_emb = self.get_embedding(matched_text)
+                
+                if query_emb and matched_emb:
+                    similarity = self.compute_similarity(query_emb, matched_emb)
+                    result["matched_entity"] = {
+                        "id": matched.id,
+                        "name": matched.name,
+                        "type": matched.type,
+                        "definition": matched.definition
+                    }
+                    result["similarity"] = similarity
+                    result["should_merge"] = similarity >= threshold
+            
+            results.append(result)
+        
+        return results
+    
+    def suggest_entity_aliases(self, entity_name: str, entity_definition: str = "") -> List[str]:
+        """
+        使用 LLM 建议实体的别名
+        
+        Args:
+            entity_name: 实体名称
+            entity_definition: 实体定义
+            
+        Returns:
+            建议的别名列表
+        """
+        if not KIMI_API_KEY:
+            return []
+        
+        prompt = f"""为以下实体生成可能的别名或简称：
+
+实体名称：{entity_name}
+定义：{entity_definition}
+
+请返回 JSON 格式的别名列表：
+{{"aliases": ["别名1", "别名2", "别名3"]}}
+
+只返回 JSON，不要其他内容。"""
+        
+        try:
+            response = httpx.post(
+                f"{KIMI_BASE_URL}/v1/chat/completions",
+                headers={"Authorization": f"Bearer {KIMI_API_KEY}", "Content-Type": "application/json"},
+                json={
+                    "model": "k2p5",
+                    "messages": [{"role": "user", "content": prompt}],
+                    "temperature": 0.3
+                },
+                timeout=30.0
+            )
+            response.raise_for_status()
+            result = response.json()
+            content = result["choices"][0]["message"]["content"]
+            
+            import re
+            json_match = re.search(r'\{{.*?\}}', content, re.DOTALL)
+            if json_match:
+                data = json.loads(json_match.group())
+                return data.get("aliases", [])
+        except Exception as e:
+            print(f"Alias suggestion failed: {e}")
+        
+        return []
+
+
+# 简单的字符串相似度计算（不使用 embedding）
+def simple_similarity(str1: str, str2: str) -> float:
+    """
+    计算两个字符串的简单相似度
+    
+    Args:
+        str1: 第一个字符串
+        str2: 第二个字符串
+        
+    Returns:
+        相似度分数 (0-1)
+    """
+    if str1 == str2:
+        return 1.0
+    
+    if not str1 or not str2:
+        return 0.0
+    
+    # 转换为小写
+    s1 = str1.lower()
+    s2 = str2.lower()
+    
+    # 包含关系
+    if s1 in s2 or s2 in s1:
+        return 0.8
+    
+    # 计算编辑距离相似度
+    from difflib import SequenceMatcher
+    return SequenceMatcher(None, s1, s2).ratio()
+
+
+if __name__ == "__main__":
+    # 测试
+    aligner = EntityAligner()
+    
+    # 测试 embedding
+    test_text = "Kubernetes 容器编排平台"
+    embedding = aligner.get_embedding(test_text)
+    if embedding:
+        print(f"Embedding dimension: {len(embedding)}")
+        print(f"First 5 values: {embedding[:5]}")
+    else:
+        print("Embedding API not available")
+    
+    # 测试相似度计算
+    emb1 = [1.0, 0.0, 0.0]
+    emb2 = [0.9, 0.1, 0.0]
+    sim = aligner.compute_similarity(emb1, emb2)
+    print(f"Similarity: {sim:.4f}")

backend/main.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """
-InsightFlow Backend - Phase 3 (Production Ready)
+InsightFlow Backend - Phase 3 (Memory & Growth)
-Knowledge Growth: Multi-file fusion + Entity Alignment
+Knowledge Growth: Multi-file fusion + Entity Alignment + Document Import
 ASR: 阿里云听悟 + OSS
 """
 
@@ -9,6 +9,7 @@ import os
 import json
 import httpx
 import uuid
+import re
 from fastapi import FastAPI, File, UploadFile, HTTPException, Form
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles
@@ -35,6 +36,18 @@ try:
 except ImportError:
     DB_AVAILABLE = False
 
+try:
+    from document_processor import DocumentProcessor
+    DOC_PROCESSOR_AVAILABLE = True
+except ImportError:
+    DOC_PROCESSOR_AVAILABLE = False
+
+try:
+    from entity_aligner import EntityAligner
+    ALIGNER_AVAILABLE = True
+except ImportError:
+    ALIGNER_AVAILABLE = False
+
 app = FastAPI(title="InsightFlow", version="0.3.0")
 
 app.add_middleware(
@@ -71,9 +84,270 @@ class ProjectCreate(BaseModel):
     name: str
     description: str = ""
 
+class EntityUpdate(BaseModel):
+    name: Optional[str] = None
+    type: Optional[str] = None
+    definition: Optional[str] = None
+    aliases: Optional[List[str]] = None
+
+class RelationCreate(BaseModel):
+    source_entity_id: str
+    target_entity_id: str
+    relation_type: str
+    evidence: Optional[str] = ""
+
+class TranscriptUpdate(BaseModel):
+    full_text: str
+
+class EntityMergeRequest(BaseModel):
+    source_entity_id: str
+    target_entity_id: str
+
+class GlossaryTermCreate(BaseModel):
+    term: str
+    pronunciation: Optional[str] = ""
+
 # API Keys
 KIMI_API_KEY = os.getenv("KIMI_API_KEY", "")
-KIMI_BASE_URL = "https://api.kimi.com/coding"
+KIMI_BASE_URL = os.getenv("KIMI_BASE_URL", "https://api.kimi.com/coding")
+
+# Phase 3: Entity Aligner singleton
+_aligner = None
+def get_aligner():
+    global _aligner
+    if _aligner is None and ALIGNER_AVAILABLE:
+        _aligner = EntityAligner()
+    return _aligner
+
+# Phase 3: Document Processor singleton
+_doc_processor = None
+def get_doc_processor():
+    global _doc_processor
+    if _doc_processor is None and DOC_PROCESSOR_AVAILABLE:
+        _doc_processor = DocumentProcessor()
+    return _doc_processor
+
+# Phase 2: Entity Edit API
+@app.put("/api/v1/entities/{entity_id}")
+async def update_entity(entity_id: str, update: EntityUpdate):
+    """更新实体信息（名称、类型、定义、别名）"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    entity = db.get_entity(entity_id)
+    if not entity:
+        raise HTTPException(status_code=404, detail="Entity not found")
+    
+    # 更新字段
+    update_data = {k: v for k, v in update.dict().items() if v is not None}
+    updated = db.update_entity(entity_id, **update_data)
+    
+    return {
+        "id": updated.id,
+        "name": updated.name,
+        "type": updated.type,
+        "definition": updated.definition,
+        "aliases": updated.aliases
+    }
+
+@app.delete("/api/v1/entities/{entity_id}")
+async def delete_entity(entity_id: str):
+    """删除实体"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    entity = db.get_entity(entity_id)
+    if not entity:
+        raise HTTPException(status_code=404, detail="Entity not found")
+    
+    db.delete_entity(entity_id)
+    return {"success": True, "message": f"Entity {entity_id} deleted"}
+
+@app.post("/api/v1/entities/{entity_id}/merge")
+async def merge_entities_endpoint(entity_id: str, merge_req: EntityMergeRequest):
+    """合并两个实体"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    
+    # 验证两个实体都存在
+    source = db.get_entity(merge_req.source_entity_id)
+    target = db.get_entity(merge_req.target_entity_id)
+    
+    if not source or not target:
+        raise HTTPException(status_code=404, detail="Entity not found")
+    
+    result = db.merge_entities(merge_req.target_entity_id, merge_req.source_entity_id)
+    return {
+        "success": True,
+        "merged_entity": {
+            "id": result.id,
+            "name": result.name,
+            "type": result.type,
+            "definition": result.definition,
+            "aliases": result.aliases
+        }
+    }
+
+# Phase 2: Relation Edit API
+@app.post("/api/v1/projects/{project_id}/relations")
+async def create_relation_endpoint(project_id: str, relation: RelationCreate):
+    """创建新的实体关系"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    
+    # 验证实体存在
+    source = db.get_entity(relation.source_entity_id)
+    target = db.get_entity(relation.target_entity_id)
+    
+    if not source or not target:
+        raise HTTPException(status_code=404, detail="Source or target entity not found")
+    
+    relation_id = db.create_relation(
+        project_id=project_id,
+        source_entity_id=relation.source_entity_id,
+        target_entity_id=relation.target_entity_id,
+        relation_type=relation.relation_type,
+        evidence=relation.evidence
+    )
+    
+    return {
+        "id": relation_id,
+        "source_id": relation.source_entity_id,
+        "target_id": relation.target_entity_id,
+        "type": relation.relation_type,
+        "success": True
+    }
+
+@app.delete("/api/v1/relations/{relation_id}")
+async def delete_relation(relation_id: str):
+    """删除关系"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    db.delete_relation(relation_id)
+    return {"success": True, "message": f"Relation {relation_id} deleted"}
+
+@app.put("/api/v1/relations/{relation_id}")
+async def update_relation(relation_id: str, relation: RelationCreate):
+    """更新关系"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    updated = db.update_relation(
+        relation_id=relation_id,
+        relation_type=relation.relation_type,
+        evidence=relation.evidence
+    )
+    
+    return {
+        "id": relation_id,
+        "type": updated["relation_type"],
+        "evidence": updated["evidence"],
+        "success": True
+    }
+
+# Phase 2: Transcript Edit API
+@app.get("/api/v1/transcripts/{transcript_id}")
+async def get_transcript(transcript_id: str):
+    """获取转录详情"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    transcript = db.get_transcript(transcript_id)
+    
+    if not transcript:
+        raise HTTPException(status_code=404, detail="Transcript not found")
+    
+    return transcript
+
+@app.put("/api/v1/transcripts/{transcript_id}")
+async def update_transcript(transcript_id: str, update: TranscriptUpdate):
+    """更新转录文本（人工修正）"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    transcript = db.get_transcript(transcript_id)
+    
+    if not transcript:
+        raise HTTPException(status_code=404, detail="Transcript not found")
+    
+    updated = db.update_transcript(transcript_id, update.full_text)
+    return {
+        "id": transcript_id,
+        "full_text": updated["full_text"],
+        "updated_at": updated["updated_at"],
+        "success": True
+    }
+
+# Phase 2: Manual Entity Creation
+class ManualEntityCreate(BaseModel):
+    name: str
+    type: str = "OTHER"
+    definition: str = ""
+    transcript_id: Optional[str] = None
+    start_pos: Optional[int] = None
+    end_pos: Optional[int] = None
+
+@app.post("/api/v1/projects/{project_id}/entities")
+async def create_manual_entity(project_id: str, entity: ManualEntityCreate):
+    """手动创建实体（划词新建）"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    
+    # 检查是否已存在
+    existing = db.get_entity_by_name(project_id, entity.name)
+    if existing:
+        return {
+            "id": existing.id,
+            "name": existing.name,
+            "type": existing.type,
+            "existed": True
+        }
+    
+    entity_id = str(uuid.uuid4())[:8]
+    new_entity = db.create_entity(Entity(
+        id=entity_id,
+        project_id=project_id,
+        name=entity.name,
+        type=entity.type,
+        definition=entity.definition
+    ))
+    
+    # 如果有提及位置信息，保存提及
+    if entity.transcript_id and entity.start_pos is not None and entity.end_pos is not None:
+        transcript = db.get_transcript(entity.transcript_id)
+        if transcript:
+            text = transcript["full_text"]
+            mention = EntityMention(
+                id=str(uuid.uuid4())[:8],
+                entity_id=entity_id,
+                transcript_id=entity.transcript_id,
+                start_pos=entity.start_pos,
+                end_pos=entity.end_pos,
+                text_snippet=text[max(0, entity.start_pos-20):min(len(text), entity.end_pos+20)],
+                confidence=1.0
+            )
+            db.add_mention(mention)
+    
+    return {
+        "id": new_entity.id,
+        "name": new_entity.name,
+        "type": new_entity.type,
+        "definition": new_entity.definition,
+        "success": True
+    }
 
 def transcribe_audio(audio_data: bytes, filename: str) -> dict:
     """转录音频：OSS上传 + 听悟转录"""
@@ -165,12 +439,21 @@ def extract_entities_with_llm(text: str) -> tuple[List[dict], List[dict]]:
     
     return [], []
 
-def align_entity(project_id: str, name: str, db) -> Optional[Entity]:
+def align_entity(project_id: str, name: str, db, definition: str = "") -> Optional[Entity]:
-    """实体对齐"""
+    """实体对齐 - Phase 3: 使用 embedding 对齐"""
+    # 1. 首先尝试精确匹配
     existing = db.get_entity_by_name(project_id, name)
     if existing:
         return existing
     
+    # 2. 使用 embedding 对齐（如果可用）
+    aligner = get_aligner()
+    if aligner:
+        similar = aligner.find_similar_entity(project_id, name, definition)
+        if similar:
+            return similar
+    
+    # 3. 回退到简单相似度匹配
     similar = db.find_similar_entities(project_id, name)
     if similar:
         return similar[0]
@@ -202,7 +485,7 @@ async def list_projects():
 
 @app.post("/api/v1/projects/{project_id}/upload", response_model=AnalysisResult)
 async def upload_audio(project_id: str, file: UploadFile = File(...)):
-    """上传音频到指定项目"""
+    """上传音频到指定项目 - Phase 3: 支持多文件融合"""
     if not DB_AVAILABLE:
         raise HTTPException(status_code=500, detail="Database not available")
     
@@ -230,12 +513,12 @@ async def upload_audio(project_id: str, file: UploadFile = File(...)):
         full_text=tw_result["full_text"]
     )
     
-    # 实体对齐并保存
+    # 实体对齐并保存 - Phase 3: 使用增强对齐
     aligned_entities = []
     entity_name_to_id = {}  # 用于关系映射
     
     for raw_ent in raw_entities:
-        existing = align_entity(project_id, raw_ent["name"], db)
+        existing = align_entity(project_id, raw_ent["name"], db, raw_ent.get("definition", ""))
         
         if existing:
             ent_model = EntityModel(
@@ -310,6 +593,302 @@ async def upload_audio(project_id: str, file: UploadFile = File(...)):
         created_at=datetime.now().isoformat()
     )
 
+# Phase 3: Document Upload API
+@app.post("/api/v1/projects/{project_id}/upload-document")
+async def upload_document(project_id: str, file: UploadFile = File(...)):
+    """上传 PDF/DOCX 文档到指定项目"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    if not DOC_PROCESSOR_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Document processor not available")
+    
+    db = get_db_manager()
+    project = db.get_project(project_id)
+    if not project:
+        raise HTTPException(status_code=404, detail="Project not found")
+    
+    content = await file.read()
+    
+    # 处理文档
+    processor = get_doc_processor()
+    try:
+        result = processor.process(content, file.filename)
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Document processing failed: {str(e)}")
+    
+    # 保存文档转录记录
+    transcript_id = str(uuid.uuid4())[:8]
+    db.save_transcript(
+        transcript_id=transcript_id,
+        project_id=project_id,
+        filename=file.filename,
+        full_text=result["text"],
+        transcript_type="document"
+    )
+    
+    # 提取实体和关系
+    raw_entities, raw_relations = extract_entities_with_llm(result["text"])
+    
+    # 实体对齐并保存
+    aligned_entities = []
+    entity_name_to_id = {}
+    
+    for raw_ent in raw_entities:
+        existing = align_entity(project_id, raw_ent["name"], db, raw_ent.get("definition", ""))
+        
+        if existing:
+            entity_name_to_id[raw_ent["name"]] = existing.id
+            aligned_entities.append(EntityModel(
+                id=existing.id,
+                name=existing.name,
+                type=existing.type,
+                definition=existing.definition,
+                aliases=existing.aliases
+            ))
+        else:
+            new_ent = db.create_entity(Entity(
+                id=str(uuid.uuid4())[:8],
+                project_id=project_id,
+                name=raw_ent["name"],
+                type=raw_ent.get("type", "OTHER"),
+                definition=raw_ent.get("definition", "")
+            ))
+            entity_name_to_id[raw_ent["name"]] = new_ent.id
+            aligned_entities.append(EntityModel(
+                id=new_ent.id,
+                name=new_ent.name,
+                type=new_ent.type,
+                definition=new_ent.definition
+            ))
+        
+        # 保存实体提及位置
+        full_text = result["text"]
+        name = raw_ent["name"]
+        start_pos = 0
+        while True:
+            pos = full_text.find(name, start_pos)
+            if pos == -1:
+                break
+            mention = EntityMention(
+                id=str(uuid.uuid4())[:8],
+                entity_id=entity_name_to_id[name],
+                transcript_id=transcript_id,
+                start_pos=pos,
+                end_pos=pos + len(name),
+                text_snippet=full_text[max(0, pos-20):min(len(full_text), pos+len(name)+20)],
+                confidence=1.0
+            )
+            db.add_mention(mention)
+            start_pos = pos + 1
+    
+    # 保存关系
+    for rel in raw_relations:
+        source_id = entity_name_to_id.get(rel.get("source", ""))
+        target_id = entity_name_to_id.get(rel.get("target", ""))
+        if source_id and target_id:
+            db.create_relation(
+                project_id=project_id,
+                source_entity_id=source_id,
+                target_entity_id=target_id,
+                relation_type=rel.get("type", "related"),
+                evidence=result["text"][:200],
+                transcript_id=transcript_id
+            )
+    
+    return {
+        "transcript_id": transcript_id,
+        "project_id": project_id,
+        "filename": file.filename,
+        "text_length": len(result["text"]),
+        "entities": [e.dict() for e in aligned_entities],
+        "created_at": datetime.now().isoformat()
+    }
+
+# Phase 3: Knowledge Base API
+@app.get("/api/v1/projects/{project_id}/knowledge-base")
+async def get_knowledge_base(project_id: str):
+    """获取项目知识库 - 包含所有实体、关系、术语表"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    project = db.get_project(project_id)
+    if not project:
+        raise HTTPException(status_code=404, detail="Project not found")
+    
+    # 获取所有实体
+    entities = db.list_project_entities(project_id)
+    
+    # 获取所有关系
+    relations = db.list_project_relations(project_id)
+    
+    # 获取所有转录
+    transcripts = db.list_project_transcripts(project_id)
+    
+    # 获取术语表
+    glossary = db.list_glossary(project_id)
+    
+    # 构建实体统计
+    entity_stats = {}
+    for ent in entities:
+        mentions = db.get_entity_mentions(ent.id)
+        entity_stats[ent.id] = {
+            "mention_count": len(mentions),
+            "transcript_ids": list(set([m.transcript_id for m in mentions]))
+        }
+    
+    # 构建实体名称映射
+    entity_map = {e.id: e.name for e in entities}
+    
+    return {
+        "project": {
+            "id": project.id,
+            "name": project.name,
+            "description": project.description
+        },
+        "stats": {
+            "entity_count": len(entities),
+            "relation_count": len(relations),
+            "transcript_count": len(transcripts),
+            "glossary_count": len(glossary)
+        },
+        "entities": [
+            {
+                "id": e.id,
+                "name": e.name,
+                "type": e.type,
+                "definition": e.definition,
+                "aliases": e.aliases,
+                "mention_count": entity_stats.get(e.id, {}).get("mention_count", 0),
+                "appears_in": entity_stats.get(e.id, {}).get("transcript_ids", [])
+            }
+            for e in entities
+        ],
+        "relations": [
+            {
+                "id": r["id"],
+                "source_id": r["source_entity_id"],
+                "source_name": entity_map.get(r["source_entity_id"], "Unknown"),
+                "target_id": r["target_entity_id"],
+                "target_name": entity_map.get(r["target_entity_id"], "Unknown"),
+                "type": r["relation_type"],
+                "evidence": r["evidence"]
+            }
+            for r in relations
+        ],
+        "glossary": [
+            {
+                "id": g["id"],
+                "term": g["term"],
+                "pronunciation": g["pronunciation"],
+                "frequency": g["frequency"]
+            }
+            for g in glossary
+        ],
+        "transcripts": [
+            {
+                "id": t["id"],
+                "filename": t["filename"],
+                "type": t.get("type", "audio"),
+                "created_at": t["created_at"]
+            }
+            for t in transcripts
+        ]
+    }
+
+# Phase 3: Glossary API
+@app.post("/api/v1/projects/{project_id}/glossary")
+async def add_glossary_term(project_id: str, term: GlossaryTermCreate):
+    """添加术语到项目术语表"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    project = db.get_project(project_id)
+    if not project:
+        raise HTTPException(status_code=404, detail="Project not found")
+    
+    term_id = db.add_glossary_term(
+        project_id=project_id,
+        term=term.term,
+        pronunciation=term.pronunciation
+    )
+    
+    return {
+        "id": term_id,
+        "term": term.term,
+        "pronunciation": term.pronunciation,
+        "success": True
+    }
+
+@app.get("/api/v1/projects/{project_id}/glossary")
+async def get_glossary(project_id: str):
+    """获取项目术语表"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    glossary = db.list_glossary(project_id)
+    return glossary
+
+@app.delete("/api/v1/glossary/{term_id}")
+async def delete_glossary_term(term_id: str):
+    """删除术语"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    db = get_db_manager()
+    db.delete_glossary_term(term_id)
+    return {"success": True}
+
+# Phase 3: Entity Alignment API
+@app.post("/api/v1/projects/{project_id}/align-entities")
+async def align_project_entities(project_id: str, threshold: float = 0.85):
+    """运行实体对齐算法，合并相似实体"""
+    if not DB_AVAILABLE:
+        raise HTTPException(status_code=500, detail="Database not available")
+    
+    aligner = get_aligner()
+    if not aligner:
+        raise HTTPException(status_code=500, detail="Entity aligner not available")
+    
+    db = get_db_manager()
+    entities = db.list_project_entities(project_id)
+    
+    merged_count = 0
+    merged_pairs = []
+    
+    # 使用 embedding 对齐
+    for i, entity in enumerate(entities):
+        # 跳过已合并的实体
+        existing = db.get_entity(entity.id)
+        if not existing:
+            continue
+            
+        similar = aligner.find_similar_entity(
+            project_id, 
+            entity.name, 
+            entity.definition,
+            exclude_id=entity.id,
+            threshold=threshold
+        )
+        
+        if similar:
+            # 合并实体
+            db.merge_entities(similar.id, entity.id)
+            merged_count += 1
+            merged_pairs.append({
+                "source": entity.name,
+                "target": similar.name
+            })
+    
+    return {
+        "success": True,
+        "merged_count": merged_count,
+        "merged_pairs": merged_pairs
+    }
+
 @app.get("/api/v1/projects/{project_id}/entities")
 async def get_project_entities(project_id: str):
     """获取项目的全局实体列表"""
@@ -318,7 +897,7 @@ async def get_project_entities(project_id: str):
     
     db = get_db_manager()
     entities = db.list_project_entities(project_id)
-    return [{"id": e.id, "name": e.name, "type": e.type, "definition": e.definition} for e in entities]
+    return [{"id": e.id, "name": e.name, "type": e.type, "definition": e.definition, "aliases": e.aliases} for e in entities]
 
 
 @app.get("/api/v1/projects/{project_id}/relations")
@@ -356,6 +935,7 @@ async def get_project_transcripts(project_id: str):
     return [{
         "id": t["id"],
         "filename": t["filename"],
+        "type": t.get("type", "audio"),
         "created_at": t["created_at"],
         "preview": t["full_text"][:100] + "..." if len(t["full_text"]) > 100 else t["full_text"]
     } for t in transcripts]
@@ -378,25 +958,18 @@ async def get_entity_mentions(entity_id: str):
         "confidence": m.confidence
     } for m in mentions]
 
-@app.post("/api/v1/entities/{entity_id}/merge")
-async def merge_entities(entity_id: str, target_entity_id: str):
-    """合并两个实体"""
-    if not DB_AVAILABLE:
-        raise HTTPException(status_code=500, detail="Database not available")
-    
-    db = get_db_manager()
-    result = db.merge_entities(target_entity_id, entity_id)
-    return {"success": True, "merged_entity": {"id": result.id, "name": result.name}}
-
 # Health check
 @app.get("/health")
 async def health_check():
     return {
         "status": "ok",
         "version": "0.3.0",
+        "phase": "Phase 3 - Memory & Growth",
         "oss_available": OSS_AVAILABLE,
         "tingwu_available": TINGWU_AVAILABLE,
-        "db_available": DB_AVAILABLE
+        "db_available": DB_AVAILABLE,
+        "doc_processor_available": DOC_PROCESSOR_AVAILABLE,
+        "aligner_available": ALIGNER_AVAILABLE
     }
 
 # Serve frontend

backend/requirements.txt

@@ -0,0 +1,24 @@
+# InsightFlow Backend Dependencies
+
+# Web Framework
+fastapi==0.109.0
+uvicorn[standard]==0.27.0
+python-multipart==0.0.6
+
+# HTTP Client
+httpx==0.26.0
+
+# Document Processing
+PyPDF2==3.0.1
+python-docx==1.1.0
+
+# Data Processing
+numpy==1.26.3
+
+# Aliyun SDK
+aliyun-python-sdk-core==2.14.0
+aliyun-python-sdk-oss==2.18.5
+oss2==2.18.5
+
+# Utilities
+python-dotenv==1.0.0

backend/schema.sql

@@ -16,7 +16,9 @@ CREATE TABLE IF NOT EXISTS transcripts (
     project_id TEXT NOT NULL,
     filename TEXT,
     full_text TEXT,
+    type TEXT DEFAULT 'audio',  -- 'audio' 或 'document'
     created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+    updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
     FOREIGN KEY (project_id) REFERENCES projects(id)
 );
 
@@ -29,6 +31,7 @@ CREATE TABLE IF NOT EXISTS entities (
     type TEXT,
     definition TEXT,
     aliases TEXT,  -- JSON 数组：["别名1", "别名2"]
+    embedding TEXT,  -- JSON 数组：实体名称+定义的 embedding
     created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
     updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
     FOREIGN KEY (project_id) REFERENCES projects(id)
@@ -71,3 +74,12 @@ CREATE TABLE IF NOT EXISTS glossary (
     frequency INTEGER DEFAULT 1,
     FOREIGN KEY (project_id) REFERENCES projects(id)
 );
+
+-- 创建索引以提高查询性能
+CREATE INDEX IF NOT EXISTS idx_entities_project ON entities(project_id);
+CREATE INDEX IF NOT EXISTS idx_entities_name ON entities(name);
+CREATE INDEX IF NOT EXISTS idx_transcripts_project ON transcripts(project_id);
+CREATE INDEX IF NOT EXISTS idx_mentions_entity ON entity_mentions(entity_id);
+CREATE INDEX IF NOT EXISTS idx_mentions_transcript ON entity_mentions(transcript_id);
+CREATE INDEX IF NOT EXISTS idx_relations_project ON entity_relations(project_id);
+CREATE INDEX IF NOT EXISTS idx_glossary_project ON glossary(project_id);

deploy.sh

@@ -0,0 +1,80 @@
+#!/bin/bash
+# InsightFlow Phase 3 部署脚本
+
+set -e
+
+echo "🚀 InsightFlow Phase 3 部署脚本"
+echo "================================"
+
+# 检查环境
+if ! command -v docker &> /dev/null; then
+    echo "❌ Docker 未安装，请先安装 Docker"
+    exit 1
+fi
+
+if ! command -v git &> /dev/null; then
+    echo "❌ Git 未安装，请先安装 Git"
+    exit 1
+fi
+
+# 配置
+IMAGE_NAME="insightflow"
+IMAGE_TAG="phase3"
+CONTAINER_NAME="insightflow-app"
+PORT="18000"
+DATA_DIR="/opt/data/insightflow"
+
+# 检查环境变量
+if [ -z "$KIMI_API_KEY" ]; then
+    echo "⚠️  警告: KIMI_API_KEY 未设置"
+fi
+
+if [ -z "$ALIYUN_ACCESS_KEY_ID" ]; then
+    echo "⚠️  警告: ALIYUN_ACCESS_KEY_ID 未设置"
+fi
+
+if [ -z "$ALIYUN_ACCESS_KEY_SECRET" ]; then
+    echo "⚠️  警告: ALIYUN_ACCESS_KEY_SECRET 未设置"
+fi
+
+echo ""
+echo "📦 构建 Docker 镜像..."
+docker build -t ${IMAGE_NAME}:${IMAGE_TAG} .
+
+echo ""
+echo "🛑 停止旧容器..."
+docker stop ${CONTAINER_NAME} 2>/dev/null || true
+docker rm ${CONTAINER_NAME} 2>/dev/null || true
+
+echo ""
+echo "📁 创建数据目录..."
+mkdir -p ${DATA_DIR}
+
+echo ""
+echo "🚀 启动新容器..."
+docker run -d \
+  --name ${CONTAINER_NAME} \
+  -p ${PORT}:8000 \
+  -v ${DATA_DIR}:/app/data \
+  -e KIMI_API_KEY="${KIMI_API_KEY}" \
+  -e KIMI_BASE_URL="${KIMI_BASE_URL:-https://api.kimi.com/coding}" \
+  -e ALIYUN_ACCESS_KEY_ID="${ALIYUN_ACCESS_KEY_ID}" \
+  -e ALIYUN_ACCESS_KEY_SECRET="${ALIYUN_ACCESS_KEY_SECRET}" \
+  -e DB_PATH="/app/data/insightflow.db" \
+  --restart unless-stopped \
+  ${IMAGE_NAME}:${IMAGE_TAG}
+
+echo ""
+echo "⏳ 等待服务启动..."
+sleep 3
+
+echo ""
+echo "✅ 部署完成！"
+echo ""
+echo "📊 服务状态:"
+docker ps --filter "name=${CONTAINER_NAME}" --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}"
+
+echo ""
+echo "🔗 访问地址: http://localhost:${PORT}"
+echo "📋 查看日志: docker logs -f ${CONTAINER_NAME}"
+echo ""

docs/PHASE3_FEATURES.md

@@ -0,0 +1,198 @@
+# InsightFlow Phase 3 功能说明
+
+## 概述
+
+Phase 3 实现了 InsightFlow 的"记忆与生长"能力，支持多文件知识融合、文档导入和项目级知识库管理。
+
+## 功能清单
+
+### 1. 多文件图谱融合 ✅
+
+#### 功能描述
+- 支持向同一项目上传多个音频文件
+- 系统自动对齐新文件中的实体与已有实体
+- 合并知识图谱，保持实体一致性
+- 跨文件追踪实体提及
+
+#### 使用方式
+1. 在工作台点击"+ 上传文件"
+2. 选择音频文件（MP3/WAV/M4A）
+3. 系统自动转录并提取实体
+4. 新实体与已有实体自动对齐
+5. 使用"📁 选择文件"切换不同转录内容
+
+#### API
+```
+POST /api/v1/projects/{project_id}/upload
+Content-Type: multipart/form-data
+file: <音频文件>
+```
+
+### 2. 实体对齐算法优化 ✅
+
+#### 功能描述
+- 使用 Kimi API 的 embedding 服务计算语义相似度
+- 余弦相似度匹配算法
+- 支持阈值调整（默认 0.85）
+- 自动别名建议
+- 失败时回退到字符串匹配
+
+#### 实现模块
+- `backend/entity_aligner.py`
+
+#### 核心算法
+```python
+# 余弦相似度计算
+def compute_similarity(embedding1, embedding2):
+    vec1 = np.array(embedding1)
+    vec2 = np.array(embedding2)
+    dot_product = np.dot(vec1, vec2)
+    norm1 = np.linalg.norm(vec1)
+    norm2 = np.linalg.norm(vec2)
+    return dot_product / (norm1 * norm2)
+```
+
+#### API
+```
+POST /api/v1/projects/{project_id}/align-entities?threshold=0.85
+```
+
+### 3. PDF/DOCX 文档导入 ✅
+
+#### 功能描述
+- 支持 PDF、DOCX、DOC、TXT、MD 格式
+- 自动提取文档文本
+- 文本参与实体提取和关系构建
+- 文档类型标记和区分
+
+#### 使用方式
+1. 在工作台点击"+ 上传文件"
+2. 切换到"📄 文档"标签
+3. 选择文档文件
+4. 系统自动解析并提取知识
+
+#### 实现模块
+- `backend/document_processor.py`
+
+#### API
+```
+POST /api/v1/projects/{project_id}/upload-document
+Content-Type: multipart/form-data
+file: <文档文件>
+```
+
+### 4. 项目知识库面板 ✅
+
+#### 功能描述
+- 项目级全域知识库视图
+- 统计面板（实体数、关系数、文件数、术语数）
+- 实体网格展示（带提及统计）
+- 关系列表展示
+- 术语表管理
+- 文件列表（区分音频/文档）
+
+#### 使用方式
+1. 在工作台点击左侧"📚"图标
+2. 查看项目统计概览
+3. 切换侧边栏标签浏览不同内容
+4. 点击实体可跳转回工作台查看详情
+
+#### API
+```
+GET /api/v1/projects/{project_id}/knowledge-base
+```
+
+### 5. 术语表管理 ✅
+
+#### 功能描述
+- 项目级术语表
+- 支持添加术语和发音提示
+- 频率统计
+- 用于 ASR 热词优化
+
+#### 使用方式
+1. 在知识库面板切换到"📖 术语表"
+2. 点击"+ 添加术语"
+3. 输入术语和发音提示
+4. 可删除不需要的术语
+
+#### API
+```
+POST /api/v1/projects/{project_id}/glossary
+GET /api/v1/projects/{project_id}/glossary
+DELETE /api/v1/glossary/{term_id}
+```
+
+## 数据库 Schema 更新
+
+### transcripts 表
+```sql
+ALTER TABLE transcripts ADD COLUMN type TEXT DEFAULT 'audio';
+-- 'audio' 或 'document'
+```
+
+### entities 表
+```sql
+ALTER TABLE entities ADD COLUMN embedding TEXT;
+-- JSON 数组存储 embedding 向量
+```
+
+### glossary 表（新增）
+```sql
+CREATE TABLE glossary (
+    id TEXT PRIMARY KEY,
+    project_id TEXT NOT NULL,
+    term TEXT NOT NULL,
+    pronunciation TEXT,
+    frequency INTEGER DEFAULT 1
+);
+```
+
+## 前端更新
+
+### 新增组件
+1. **侧边栏导航** - 切换工作台/知识库视图
+2. **文件选择器** - 切换不同转录文件
+3. **上传标签页** - 区分音频/文档上传
+4. **知识库面板** - 统计卡片、实体网格、关系列表、术语表
+
+### 更新文件
+- `frontend/workbench.html` - 新增知识库 UI
+- `frontend/app.js` - 新增知识库逻辑、多文件支持
+
+## 部署说明
+
+### 环境变量
+```bash
+KIMI_API_KEY=your_kimi_api_key
+KIMI_BASE_URL=https://api.kimi.com/coding
+ALIYUN_ACCESS_KEY_ID=your_aliyun_key
+ALIYUN_ACCESS_KEY_SECRET=your_aliyun_secret
+```
+
+### 部署命令
+```bash
+# 使用部署脚本
+./deploy.sh
+
+# 或手动部署
+docker build -t insightflow:phase3 .
+docker run -d \
+  -p 18000:8000 \
+  -v /opt/data:/app/data \
+  -e KIMI_API_KEY=$KIMI_API_KEY \
+  insightflow:phase3
+```
+
+## 测试检查清单
+
+- [ ] 上传多个音频文件到同一项目
+- [ ] 检查实体是否正确对齐
+- [ ] 上传 PDF 文档
+- [ ] 上传 DOCX 文档
+- [ ] 切换不同转录文件
+- [ ] 查看知识库面板统计
+- [ ] 添加术语到术语表
+- [ ] 删除术语
+- [ ] 实体合并功能
+- [ ] 关系创建/删除

frontend/app.js

@@ -1,4 +1,5 @@
-// InsightFlow Frontend - Production Version
+// InsightFlow Frontend - Phase 3 (Memory & Growth)
+// Knowledge Growth: Multi-file fusion + Entity Alignment + Document Import
 const API_BASE = '/api/v1';
 
 let currentProject = null;
@@ -6,6 +7,12 @@ let currentData = null;
 let selectedEntity = null;
 let projectRelations = [];
 let projectEntities = [];
+let currentTranscript = null;
+let projectTranscripts = [];
+let editMode = false;
+let contextMenuTarget = null;
+let currentUploadTab = 'audio';
+let knowledgeBaseData = null;
 
 // Init
 document.addEventListener('DOMContentLoaded', () => {
@@ -37,6 +44,8 @@ async function initWorkbench() {
         if (nameEl) nameEl.textContent = currentProject.name;
         
         initUpload();
+        initContextMenu();
+        initTextSelection();
         await loadProjectData();
         
     } catch (err) {
@@ -65,12 +74,131 @@ async function uploadAudio(file) {
     return await res.json();
 }
 
+// Phase 3: Document Upload API
+async function uploadDocument(file) {
+    const formData = new FormData();
+    formData.append('file', file);
+    
+    const res = await fetch(`${API_BASE}/projects/${currentProject.id}/upload-document`, {
+        method: 'POST',
+        body: formData
+    });
+    
+    if (!res.ok) {
+        const error = await res.json();
+        throw new Error(error.detail || 'Document upload failed');
+    }
+    return await res.json();
+}
+
+// Phase 3: Knowledge Base API
+async function fetchKnowledgeBase() {
+    const res = await fetch(`${API_BASE}/projects/${currentProject.id}/knowledge-base`);
+    if (!res.ok) throw new Error('Failed to fetch knowledge base');
+    return await res.json();
+}
+
+// Phase 3: Glossary API
+async function addGlossaryTerm(term, pronunciation = '') {
+    const res = await fetch(`${API_BASE}/projects/${currentProject.id}/glossary`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ term, pronunciation })
+    });
+    if (!res.ok) throw new Error('Failed to add glossary term');
+    return await res.json();
+}
+
+async function deleteGlossaryTerm(termId) {
+    const res = await fetch(`${API_BASE}/glossary/${termId}`, {
+        method: 'DELETE'
+    });
+    if (!res.ok) throw new Error('Failed to delete glossary term');
+    return await res.json();
+}
+
+// Phase 2: Entity Edit API
+async function updateEntity(entityId, data) {
+    const res = await fetch(`${API_BASE}/entities/${entityId}`, {
+        method: 'PUT',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify(data)
+    });
+    if (!res.ok) throw new Error('Failed to update entity');
+    return await res.json();
+}
+
+async function deleteEntityApi(entityId) {
+    const res = await fetch(`${API_BASE}/entities/${entityId}`, {
+        method: 'DELETE'
+    });
+    if (!res.ok) throw new Error('Failed to delete entity');
+    return await res.json();
+}
+
+async function mergeEntitiesApi(sourceId, targetId) {
+    const res = await fetch(`${API_BASE}/entities/${sourceId}/merge`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ source_entity_id: sourceId, target_entity_id: targetId })
+    });
+    if (!res.ok) throw new Error('Failed to merge entities');
+    return await res.json();
+}
+
+async function createEntityApi(data) {
+    const res = await fetch(`${API_BASE}/projects/${currentProject.id}/entities`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify(data)
+    });
+    if (!res.ok) throw new Error('Failed to create entity');
+    return await res.json();
+}
+
+// Phase 2: Relation API
+async function createRelationApi(data) {
+    const res = await fetch(`${API_BASE}/projects/${currentProject.id}/relations`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify(data)
+    });
+    if (!res.ok) throw new Error('Failed to create relation');
+    return await res.json();
+}
+
+async function deleteRelationApi(relationId) {
+    const res = await fetch(`${API_BASE}/relations/${relationId}`, {
+        method: 'DELETE'
+    });
+    if (!res.ok) throw new Error('Failed to delete relation');
+    return await res.json();
+}
+
+// Phase 2: Transcript API
+async function getTranscript(transcriptId) {
+    const res = await fetch(`${API_BASE}/transcripts/${transcriptId}`);
+    if (!res.ok) throw new Error('Failed to get transcript');
+    return await res.json();
+}
+
+async function updateTranscript(transcriptId, fullText) {
+    const res = await fetch(`${API_BASE}/transcripts/${transcriptId}`, {
+        method: 'PUT',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ full_text: fullText })
+    });
+    if (!res.ok) throw new Error('Failed to update transcript');
+    return await res.json();
+}
+
 async function loadProjectData() {
     try {
-        // 并行加载实体和关系
+        // 并行加载实体、关系和转录列表
-        const [entitiesRes, relationsRes] = await Promise.all([
+        const [entitiesRes, relationsRes, transcriptsRes] = await Promise.all([
             fetch(`${API_BASE}/projects/${currentProject.id}/entities`),
-            fetch(`${API_BASE}/projects/${currentProject.id}/relations`)
+            fetch(`${API_BASE}/projects/${currentProject.id}/relations`),
+            fetch(`${API_BASE}/projects/${currentProject.id}/transcripts`)
         ]);
         
         if (entitiesRes.ok) {
@@ -79,39 +207,228 @@ async function loadProjectData() {
         if (relationsRes.ok) {
             projectRelations = await relationsRes.json();
         }
+        if (transcriptsRes.ok) {
+            projectTranscripts = await transcriptsRes.json();
+        }
         
+        // 加载最新的转录
+        if (projectTranscripts.length > 0) {
+            currentTranscript = await getTranscript(projectTranscripts[0].id);
             currentData = {
-            transcript_id: 'project_view',
+                transcript_id: currentTranscript.id,
                 project_id: currentProject.id,
-            segments: [],
+                segments: [{ speaker: '全文', text: currentTranscript.full_text }],
                 entities: projectEntities,
-            full_text: '',
+                full_text: currentTranscript.full_text,
-            created_at: new Date().toISOString()
+                created_at: currentTranscript.created_at
             };
+            renderTranscript();
+        }
         
         renderGraph();
         renderEntityList();
+        renderTranscriptDropdown();
         
     } catch (err) {
         console.error('Load project data failed:', err);
     }
 }
 
+// Phase 3: View Switching
+window.switchView = function(viewName) {
+    // Update sidebar buttons
+    document.querySelectorAll('.sidebar-btn').forEach(btn => {
+        btn.classList.remove('active');
+    });
+    event.target.classList.add('active');
+    
+    if (viewName === 'workbench') {
+        document.getElementById('workbenchView').style.display = 'flex';
+        document.getElementById('knowledgeBaseView').classList.remove('show');
+    } else if (viewName === 'knowledge-base') {
+        document.getElementById('workbenchView').style.display = 'none';
+        document.getElementById('knowledgeBaseView').classList.add('show');
+        loadKnowledgeBase();
+    }
+};
+
+// Phase 3: Load Knowledge Base
+async function loadKnowledgeBase() {
+    try {
+        knowledgeBaseData = await fetchKnowledgeBase();
+        renderKnowledgeBase();
+    } catch (err) {
+        console.error('Load knowledge base failed:', err);
+    }
+}
+
+// Phase 3: Render Knowledge Base
+function renderKnowledgeBase() {
+    if (!knowledgeBaseData) return;
+    
+    // Update stats
+    document.getElementById('kbEntityCount').textContent = knowledgeBaseData.stats.entity_count;
+    document.getElementById('kbRelationCount').textContent = knowledgeBaseData.stats.relation_count;
+    document.getElementById('kbTranscriptCount').textContent = knowledgeBaseData.stats.transcript_count;
+    document.getElementById('kbGlossaryCount').textContent = knowledgeBaseData.stats.glossary_count;
+    
+    // Render entities
+    const entityGrid = document.getElementById('kbEntityGrid');
+    entityGrid.innerHTML = knowledgeBaseData.entities.map(e => `
+        <div class="kb-entity-card" onclick="selectEntity('${e.id}'); switchView('workbench');">
+            <span class="entity-type-badge type-${e.type}">${e.type}</span>
+            <div class="kb-entity-name">${e.name}</div>
+            <div class="kb-entity-def">${e.definition || '暂无定义'}</div>
+            <div class="kb-entity-meta">提及 ${e.mention_count} 次 | 出现在 ${e.appears_in.length} 个文件中</div>
+        </div>
+    `).join('');
+    
+    // Render relations
+    const relationsList = document.getElementById('kbRelationsList');
+    relationsList.innerHTML = knowledgeBaseData.relations.map(r => `
+        <div class="kb-glossary-item">
+            <div>
+                <strong>${r.source_name}</strong> 
+                <span style="color:#666;">→ ${r.type} →</span> 
+                <strong>${r.target_name}</strong>
+                <div style="font-size:0.8rem;color:#666;margin-top:4px;">${r.evidence || '无证据'}</div>
+            </div>
+        </div>
+    `).join('');
+    
+    // Render glossary
+    const glossaryList = document.getElementById('kbGlossaryList');
+    glossaryList.innerHTML = knowledgeBaseData.glossary.map(g => `
+        <div class="kb-glossary-item">
+            <div>
+                <strong>${g.term}</strong>
+                ${g.pronunciation ? `<span style="color:#666;font-size:0.85rem;"> (${g.pronunciation})</span>` : ''}
+                <span style="color:#00d4ff;font-size:0.8rem;margin-left:8px;">出现 ${g.frequency} 次</span>
+            </div>
+            <button class="btn-icon" onclick="deleteGlossaryTerm('${g.id}').then(loadKnowledgeBase)">删除</button>
+        </div>
+    `).join('');
+    
+    // Render transcripts
+    const transcriptsList = document.getElementById('kbTranscriptsList');
+    transcriptsList.innerHTML = knowledgeBaseData.transcripts.map(t => `
+        <div class="kb-transcript-item">
+            <div>
+                <span class="file-type-icon type-${t.type}">${t.type === 'audio' ? '🎵' : '📄'}</span>
+                <span style="margin-left:8px;">${t.filename}</span>
+            </div>
+            <span style="color:#666;font-size:0.8rem;">${new Date(t.created_at).toLocaleDateString()}</span>
+        </div>
+    `).join('');
+}
+
+// Phase 3: KB Tab Switching
+window.switchKBTab = function(tabName) {
+    document.querySelectorAll('.kb-nav-item').forEach(item => {
+        item.classList.remove('active');
+    });
+    event.target.classList.add('active');
+    
+    document.querySelectorAll('.kb-section').forEach(section => {
+        section.classList.remove('active');
+    });
+    document.getElementById(`kb${tabName.charAt(0).toUpperCase() + tabName.slice(1)}Section`).classList.add('active');
+};
+
+// Phase 3: Transcript Dropdown
+window.toggleTranscriptDropdown = function() {
+    const dropdown = document.getElementById('transcriptDropdown');
+    dropdown.classList.toggle('show');
+};
+
+function renderTranscriptDropdown() {
+    const dropdown = document.getElementById('transcriptDropdown');
+    if (!dropdown || projectTranscripts.length === 0) return;
+    
+    dropdown.innerHTML = projectTranscripts.map(t => `
+        <div class="transcript-option ${currentTranscript && currentTranscript.id === t.id ? 'active' : ''}" 
+             onclick="switchTranscript('${t.id}')">
+            <span class="file-type-icon type-${t.type || 'audio'}">${(t.type || 'audio') === 'audio' ? '🎵' : '📄'}</span>
+            <span style="margin-left:4px;">${t.filename}</span>
+        </div>
+    `).join('');
+}
+
+window.switchTranscript = async function(transcriptId) {
+    try {
+        currentTranscript = await getTranscript(transcriptId);
+        currentData = {
+            transcript_id: currentTranscript.id,
+            project_id: currentProject.id,
+            segments: [{ speaker: '全文', text: currentTranscript.full_text }],
+            entities: projectEntities,
+            full_text: currentTranscript.full_text,
+            created_at: currentTranscript.created_at
+        };
+        renderTranscript();
+        renderTranscriptDropdown();
+        document.getElementById('transcriptDropdown').classList.remove('show');
+    } catch (err) {
+        console.error('Switch transcript failed:', err);
+        alert('切换文件失败');
+    }
+};
+
+// Phase 2: Transcript Edit Mode
+window.toggleEditMode = function() {
+    editMode = !editMode;
+    const editBtn = document.getElementById('editBtn');
+    const saveBtn = document.getElementById('saveBtn');
+    const content = document.getElementById('transcriptContent');
+    
+    if (editMode) {
+        editBtn.style.display = 'none';
+        saveBtn.style.display = 'inline-block';
+        content.contentEditable = 'true';
+        content.style.background = '#0f0f0f';
+        content.style.border = '1px solid #00d4ff';
+        content.focus();
+    } else {
+        editBtn.style.display = 'inline-block';
+        saveBtn.style.display = 'none';
+        content.contentEditable = 'false';
+        content.style.background = '';
+        content.style.border = '';
+    }
+};
+
+window.saveTranscript = async function() {
+    if (!currentTranscript) return;
+    
+    const content = document.getElementById('transcriptContent');
+    const fullText = content.innerText;
+    
+    try {
+        await updateTranscript(currentTranscript.id, fullText);
+        currentTranscript.full_text = fullText;
+        toggleEditMode();
+        alert('转录文本已保存');
+    } catch (err) {
+        console.error('Save failed:', err);
+        alert('保存失败: ' + err.message);
+    }
+};
+
 // Render transcript with entity highlighting
 function renderTranscript() {
     const container = document.getElementById('transcriptContent');
-    if (!container || !currentData || !currentData.segments) return;
+    if (!container || !currentData) return;
     
     container.innerHTML = '';
     
-    currentData.segments.forEach((seg, idx) => {
+    if (editMode) {
-        const div = document.createElement('div');
+        container.innerText = currentData.full_text || '';
-        div.className = 'segment';
+        return;
-        div.dataset.index = idx;
+    }
     
     // 高亮实体
-        let text = seg.text;
+    let text = currentData.full_text || '';
-        const entities = findEntitiesInText(seg.text);
+    const entities = findEntitiesInText(text);
     
     // 按位置倒序替换，避免位置偏移
     entities.sort((a, b) => b.start - a.start);
@@ -123,13 +440,14 @@ function renderTranscript() {
         text = before + `<span class="entity" data-id="${ent.id}" onclick="window.selectEntity('${ent.id}')">${name}</span>` + after;
     });
     
+    const div = document.createElement('div');
+    div.className = 'segment';
     div.innerHTML = `
-            <div class="speaker">${seg.speaker}</div>
+        <div class="speaker">${currentTranscript.filename || '转录文本'}</div>
         <div class="segment-text">${text}</div>
     `;
     
     container.appendChild(div);
-    });
 }
 
 // 在文本中查找实体位置
@@ -181,7 +499,7 @@ function renderGraph() {
             .attr('y', '50%')
             .attr('text-anchor', 'middle')
             .attr('fill', '#666')
-            .text('暂无实体数据，请上传音频');
+            .text('暂无实体数据，请上传音频或文档');
         return;
     }
     
@@ -201,6 +519,7 @@ function renderGraph() {
     
     // 使用数据库中的关系
     const links = projectRelations.map(r => ({
+        id: r.id,
         source: r.source_id,
         target: r.target_id,
         type: r.type
@@ -256,7 +575,11 @@ function renderGraph() {
             .on('start', dragstarted)
             .on('drag', dragged)
             .on('end', dragended))
-        .on('click', (e, d) => window.selectEntity(d.id));
+        .on('click', (e, d) => window.selectEntity(d.id))
+        .on('contextmenu', (e, d) => {
+            e.preventDefault();
+            showContextMenu(e, d.id);
+        });
     
     // 节点圆圈
     node.append('circle')
@@ -323,7 +646,7 @@ function renderEntityList() {
     container.innerHTML = '<h3 style="margin-bottom:12px;color:#888;font-size:0.9rem;">项目实体</h3>';
     
     if (!projectEntities || projectEntities.length === 0) {
-        container.innerHTML += '<p style="color:#666;font-size:0.85rem;">暂无实体，请上传音频文件</p>';
+        container.innerHTML += '<p style="color:#666;font-size:0.85rem;">暂无实体，请上传音频或文档文件</p>';
         return;
     }
     
@@ -332,9 +655,13 @@ function renderEntityList() {
         div.className = 'entity-item';
         div.dataset.id = ent.id;
         div.onclick = () => window.selectEntity(ent.id);
+        div.oncontextmenu = (e) => {
+            e.preventDefault();
+            showContextMenu(e, ent.id);
+        };
         
         div.innerHTML = `
-            <span class="entity-type-badge type-${ent.type.toLowerCase()}">${ent.type}</span>
+            <span class="entity-type-badge type-${ent.type}">${ent.type}</span>
             <div>
                 <div style="font-weight:500;">${ent.name}</div>
                 <div style="font-size:0.8rem;color:#666;">${ent.definition || '暂无定义'}</div>
@@ -354,11 +681,9 @@ window.selectEntity = function(entityId) {
     // 高亮文本中的实体
     document.querySelectorAll('.entity').forEach(el => {
         if (el.dataset.id === entityId) {
-            el.style.background = '#ff6b6b';
+            el.classList.add('selected');
-            el.style.color = '#fff';
         } else {
-            el.style.background = '';
+            el.classList.remove('selected');
-            el.style.color = '';
         }
     });
     
@@ -371,17 +696,308 @@ window.selectEntity = function(entityId) {
     // 高亮实体列表
     document.querySelectorAll('.entity-item').forEach(el => {
         if (el.dataset.id === entityId) {
-            el.style.background = '#2a2a2a';
+            el.classList.add('selected');
-            el.style.borderLeft = '3px solid #ff6b6b';
         } else {
-            el.style.background = '';
+            el.classList.remove('selected');
-            el.style.borderLeft = '';
         }
     });
     
     console.log('Selected:', entity.name, entity.definition);
 };
 
+// Phase 2: Context Menu
+function initContextMenu() {
+    document.addEventListener('click', () => {
+        hideContextMenu();
+    });
+}
+
+function showContextMenu(e, entityId) {
+    contextMenuTarget = entityId;
+    const menu = document.getElementById('contextMenu');
+    menu.style.left = e.pageX + 'px';
+    menu.style.top = e.pageY + 'px';
+    menu.classList.add('show');
+}
+
+function hideContextMenu() {
+    const menu = document.getElementById('contextMenu');
+    menu.classList.remove('show');
+    contextMenuTarget = null;
+}
+
+// Phase 2: Entity Editor Modal
+window.editEntity = function() {
+    hideContextMenu();
+    if (!contextMenuTarget && !selectedEntity) return;
+    
+    const entityId = contextMenuTarget || selectedEntity;
+    const entity = projectEntities.find(e => e.id === entityId);
+    if (!entity) return;
+    
+    document.getElementById('entityName').value = entity.name;
+    document.getElementById('entityType').value = entity.type;
+    document.getElementById('entityDefinition').value = entity.definition || '';
+    document.getElementById('entityAliases').value = (entity.aliases || []).join(', ');
+    
+    // 显示关系编辑器
+    document.getElementById('relationEditor').style.display = 'block';
+    renderRelationList(entityId);
+    
+    document.getElementById('entityModal').dataset.entityId = entityId;
+    document.getElementById('entityModal').classList.add('show');
+};
+
+function renderRelationList(entityId) {
+    const container = document.getElementById('relationList');
+    const entityRelations = projectRelations.filter(r => 
+        r.source_id === entityId || r.target_id === entityId
+    );
+    
+    if (entityRelations.length === 0) {
+        container.innerHTML = '<p style="color:#666;font-size:0.8rem;">暂无关系</p>';
+        return;
+    }
+    
+    container.innerHTML = entityRelations.map(r => {
+        const isSource = r.source_id === entityId;
+        const otherId = isSource ? r.target_id : r.source_id;
+        const other = projectEntities.find(e => e.id === otherId);
+        const otherName = other ? other.name : 'Unknown';
+        const arrow = isSource ? '→' : '←';
+        
+        return `
+            <div class="relation-item">
+                <span>${arrow} ${otherName} (${r.type})</span>
+                <button onclick="deleteRelation('${r.id}')">删除</button>
+            </div>
+        `;
+    }).join('');
+}
+
+window.hideEntityModal = function() {
+    document.getElementById('entityModal').classList.remove('show');
+};
+
+window.saveEntity = async function() {
+    const entityId = document.getElementById('entityModal').dataset.entityId;
+    if (!entityId) return;
+    
+    const data = {
+        name: document.getElementById('entityName').value,
+        type: document.getElementById('entityType').value,
+        definition: document.getElementById('entityDefinition').value,
+        aliases: document.getElementById('entityAliases').value.split(',').map(s => s.trim()).filter(s => s)
+    };
+    
+    try {
+        await updateEntity(entityId, data);
+        await loadProjectData();
+        hideEntityModal();
+    } catch (err) {
+        console.error('Save failed:', err);
+        alert('保存失败: ' + err.message);
+    }
+};
+
+window.deleteEntity = async function() {
+    const entityId = document.getElementById('entityModal').dataset.entityId;
+    if (!entityId) return;
+    
+    if (!confirm('确定要删除这个实体吗？相关的提及和关系也会被删除。')) return;
+    
+    try {
+        await deleteEntityApi(entityId);
+        await loadProjectData();
+        hideEntityModal();
+    } catch (err) {
+        console.error('Delete failed:', err);
+        alert('删除失败: ' + err.message);
+    }
+};
+
+// Phase 2: Merge Modal
+window.showMergeModal = function() {
+    hideContextMenu();
+    if (!contextMenuTarget && !selectedEntity) return;
+    
+    const sourceId = contextMenuTarget || selectedEntity;
+    const source = projectEntities.find(e => e.id === sourceId);
+    if (!source) return;
+    
+    document.getElementById('mergeSource').value = source.name;
+    document.getElementById('mergeModal').dataset.sourceId = sourceId;
+    
+    // 填充目标实体选项（排除自己）
+    const select = document.getElementById('mergeTarget');
+    select.innerHTML = projectEntities
+        .filter(e => e.id !== sourceId)
+        .map(e => `<option value="${e.id}">${e.name} (${e.type})</option>`)
+        .join('');
+    
+    document.getElementById('mergeModal').classList.add('show');
+};
+
+window.hideMergeModal = function() {
+    document.getElementById('mergeModal').classList.remove('show');
+};
+
+window.confirmMerge = async function() {
+    const sourceId = document.getElementById('mergeModal').dataset.sourceId;
+    const targetId = document.getElementById('mergeTarget').value;
+    
+    if (!sourceId || !targetId) return;
+    
+    try {
+        await mergeEntitiesApi(sourceId, targetId);
+        await loadProjectData();
+        hideMergeModal();
+    } catch (err) {
+        console.error('Merge failed:', err);
+        alert('合并失败: ' + err.message);
+    }
+};
+
+// Phase 2: Relation Modal
+window.showAddRelation = function() {
+    const entityId = document.getElementById('entityModal').dataset.entityId;
+    if (!entityId) return;
+    
+    const entity = projectEntities.find(e => e.id === entityId);
+    document.getElementById('relationModal').dataset.sourceId = entityId;
+    
+    // 填充目标选项
+    const select = document.getElementById('relationTarget');
+    select.innerHTML = projectEntities
+        .filter(e => e.id !== entityId)
+        .map(e => `<option value="${e.id}">${e.name}</option>`)
+        .join('');
+    
+    document.getElementById('relationModal').classList.add('show');
+};
+
+window.hideRelationModal = function() {
+    document.getElementById('relationModal').classList.remove('show');
+};
+
+window.saveRelation = async function() {
+    const sourceId = document.getElementById('relationModal').dataset.sourceId;
+    const targetId = document.getElementById('relationTarget').value;
+    const type = document.getElementById('relationType').value;
+    const evidence = document.getElementById('relationEvidence').value;
+    
+    if (!sourceId || !targetId) return;
+    
+    try {
+        await createRelationApi({
+            source_entity_id: sourceId,
+            target_entity_id: targetId,
+            relation_type: type,
+            evidence: evidence
+        });
+        await loadProjectData();
+        renderRelationList(sourceId);
+        hideRelationModal();
+    } catch (err) {
+        console.error('Create relation failed:', err);
+        alert('创建关系失败: ' + err.message);
+    }
+};
+
+window.deleteRelation = async function(relationId) {
+    if (!confirm('确定要删除这个关系吗？')) return;
+    
+    try {
+        await deleteRelationApi(relationId);
+        await loadProjectData();
+        const entityId = document.getElementById('entityModal').dataset.entityId;
+        if (entityId) renderRelationList(entityId);
+    } catch (err) {
+        console.error('Delete relation failed:', err);
+        alert('删除关系失败: ' + err.message);
+    }
+};
+
+// Phase 2: Text Selection - Create Entity
+function initTextSelection() {
+    document.addEventListener('selectionchange', () => {
+        const selection = window.getSelection();
+        const text = selection.toString().trim();
+        
+        if (text.length > 0 && text.length < 50) {
+            showSelectionToolbar();
+        } else {
+            hideSelectionToolbar();
+        }
+    });
+}
+
+function showSelectionToolbar() {
+    document.getElementById('selectionToolbar').classList.add('show');
+}
+
+window.hideSelectionToolbar = function() {
+    document.getElementById('selectionToolbar').classList.remove('show');
+    window.getSelection().removeAllRanges();
+};
+
+window.createEntityFromSelection = async function() {
+    const selection = window.getSelection();
+    const text = selection.toString().trim();
+    
+    if (!text) return;
+    
+    // 获取选中文本在全文中的位置
+    const container = document.getElementById('transcriptContent');
+    const fullText = currentTranscript ? currentTranscript.full_text : '';
+    const startPos = fullText.indexOf(text);
+    
+    try {
+        const result = await createEntityApi({
+            name: text,
+            type: 'OTHER',
+            definition: '',
+            transcript_id: currentTranscript ? currentTranscript.id : null,
+            start_pos: startPos >= 0 ? startPos : null,
+            end_pos: startPos >= 0 ? startPos + text.length : null
+        });
+        
+        hideSelectionToolbar();
+        await loadProjectData();
+        
+        if (!result.existed) {
+            alert(`已创建实体: ${text}`);
+        } else {
+            alert(`实体 "${text}" 已存在`);
+        }
+    } catch (err) {
+        console.error('Create entity failed:', err);
+        alert('创建实体失败: ' + err.message);
+    }
+};
+
+// Phase 3: Upload Tab Switching
+window.switchUploadTab = function(tab) {
+    currentUploadTab = tab;
+    document.querySelectorAll('.upload-tab').forEach(t => t.classList.remove('active'));
+    event.target.classList.add('active');
+    
+    const hint = document.getElementById('uploadHint');
+    if (tab === 'audio') {
+        hint.textContent = '支持 MP3, WAV, M4A (最大 500MB)';
+    } else {
+        hint.textContent = '支持 PDF, DOCX, DOC, TXT, MD';
+    }
+};
+
+window.triggerFileSelect = function() {
+    if (currentUploadTab === 'audio') {
+        document.getElementById('fileInput').click();
+    } else {
+        document.getElementById('docInput').click();
+    }
+};
+
 // Show/hide upload
 window.showUpload = function() {
     const el = document.getElementById('uploadOverlay');
@@ -393,46 +1009,105 @@ window.hideUpload = function() {
     if (el) el.classList.remove('show');
 };
 
+// Phase 3: Glossary Modal
+window.showAddTermModal = function() {
+    document.getElementById('glossaryModal').classList.add('show');
+};
+
+window.hideGlossaryModal = function() {
+    document.getElementById('glossaryModal').classList.remove('show');
+    document.getElementById('glossaryTerm').value = '';
+    document.getElementById('glossaryPronunciation').value = '';
+};
+
+window.saveGlossaryTerm = async function() {
+    const term = document.getElementById('glossaryTerm').value.trim();
+    const pronunciation = document.getElementById('glossaryPronunciation').value.trim();
+    
+    if (!term) {
+        alert('请输入术语');
+        return;
+    }
+    
+    try {
+        await addGlossaryTerm(term, pronunciation);
+        hideGlossaryModal();
+        loadKnowledgeBase();
+    } catch (err) {
+        console.error('Add term failed:', err);
+        alert('添加术语失败: ' + err.message);
+    }
+};
+
 // Upload handling
 function initUpload() {
-    const input = document.getElementById('fileInput');
+    // Audio upload
+    const audioInput = document.getElementById('fileInput');
+    if (audioInput) {
+        audioInput.addEventListener('change', async (e) => {
+            if (!e.target.files.length) return;
+            await handleFileUpload(e.target.files[0], 'audio');
+        });
+    }
+    
+    // Document upload
+    const docInput = document.getElementById('docInput');
+    if (docInput) {
+        docInput.addEventListener('change', async (e) => {
+            if (!e.target.files.length) return;
+            await handleFileUpload(e.target.files[0], 'document');
+        });
+    }
+}
+
+async function handleFileUpload(file, type) {
     const overlay = document.getElementById('uploadOverlay');
     
-    if (!input) return;
-    
-    input.addEventListener('change', async (e) => {
-        if (!e.target.files.length) return;
-        
-        const file = e.target.files[0];
-        if (overlay) {
     overlay.innerHTML = `
         <div style="text-align:center;">
             <h2>正在分析...</h2>
             <p style="color:#666;margin-top:10px;">${file.name}</p>
-                    <p style="color:#888;margin-top:20px;font-size:0.9rem;">ASR转录 + 实体提取中</p>
+            <p style="color:#888;margin-top:20px;font-size:0.9rem;">${type === 'audio' ? 'ASR转录 + 实体提取中' : '文档解析 + 实体提取中'}</p>
         </div>
     `;
-        }
     
     try {
-            const result = await uploadAudio(file);
+        let result;
+        if (type === 'audio') {
+            result = await uploadAudio(file);
+        } else {
+            result = await uploadDocument(file);
+        }
         
         // 更新当前数据
         currentData = result;
         
-            // 重新加载项目数据（包含新实体和关系）
+        // 重新加载项目数据
         await loadProjectData();
         
-            // 渲染转录文本
+        // 重置上传界面
-            if (result.segments && result.segments.length > 0) {
+        overlay.innerHTML = `
-                renderTranscript();
+            <div class="upload-box">
-            }
+                <h2 style="margin-bottom:10px;">上传文件</h2>
+                <div class="upload-tabs">
+                    <div class="upload-tab active" onclick="switchUploadTab('audio')">🎵 音频</div>
+                    <div class="upload-tab" onclick="switchUploadTab('document')">📄 文档</div>
+                </div>
+                <p style="color:#666;" id="uploadHint">支持 MP3, WAV, M4A (最大 500MB)</p>
+                <input type="file" id="fileInput" accept="audio/*" hidden>
+                <input type="file" id="docInput" accept=".pdf,.docx,.doc,.txt,.md" hidden>
+                <button class="btn" onclick="triggerFileSelect()">选择文件</button>
+                <br><br>
+                <button class="btn btn-secondary" onclick="hideUpload()">取消</button>
+            </div>
+        `;
         
-            if (overlay) overlay.classList.remove('show');
+        // 重新绑定事件
+        initUpload();
+        overlay.classList.remove('show');
         
     } catch (err) {
         console.error('Upload failed:', err);
-            if (overlay) {
         overlay.innerHTML = `
             <div style="text-align:center;">
                 <h2 style="color:#ff6b6b;">分析失败</h2>
@@ -441,6 +1116,13 @@ function initUpload() {
             </div>
         `;
     }
-        }
-    });
 }
+
+// Close dropdown when clicking outside
+document.addEventListener('click', (e) => {
+    const dropdown = document.getElementById('transcriptDropdown');
+    const selector = document.querySelector('.transcript-selector');
+    if (dropdown && selector && !selector.contains(e.target)) {
+        dropdown.classList.remove('show');
+    }
+});

frontend/workbench.html

@@ -3,7 +3,7 @@
 <head>
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>InsightFlow - 知识工作台</title>
+    <title>InsightFlow - 知识工作台 (Phase 3)</title>
     <script src="https://d3js.org/d3.v7.min.js"></script>
     <style>
         * { margin: 0; padding: 0; box-sizing: border-box; }
@@ -46,10 +46,44 @@
             color: #888;
             font-size: 0.9rem;
         }
+        .header-actions {
+            display: flex;
+            gap: 10px;
+        }
         .main {
             display: flex;
             height: calc(100vh - 50px);
         }
+        .sidebar {
+            width: 60px;
+            background: #111;
+            border-right: 1px solid #222;
+            display: flex;
+            flex-direction: column;
+            align-items: center;
+            padding: 10px 0;
+        }
+        .sidebar-btn {
+            width: 44px;
+            height: 44px;
+            background: transparent;
+            border: none;
+            color: #666;
+            font-size: 1.2rem;
+            cursor: pointer;
+            border-radius: 8px;
+            margin-bottom: 8px;
+            transition: all 0.2s;
+        }
+        .sidebar-btn:hover, .sidebar-btn.active {
+            background: #1a1a1a;
+            color: #00d4ff;
+        }
+        .content-area {
+            flex: 1;
+            display: flex;
+            overflow: hidden;
+        }
         .editor-panel {
             width: 50%;
             border-right: 1px solid #222;
@@ -66,6 +100,23 @@
             justify-content: space-between;
             align-items: center;
         }
+        .panel-actions {
+            display: flex;
+            gap: 8px;
+        }
+        .btn-icon {
+            background: transparent;
+            border: 1px solid #333;
+            color: #888;
+            padding: 4px 10px;
+            border-radius: 4px;
+            cursor: pointer;
+            font-size: 0.8rem;
+        }
+        .btn-icon:hover {
+            border-color: #00d4ff;
+            color: #00d4ff;
+        }
         .transcript-content {
             flex: 1;
             padding: 20px;
@@ -92,6 +143,13 @@
         }
         .segment-text {
             color: #e0e0e0;
+            outline: none;
+        }
+        .segment-text[contenteditable="true"] {
+            background: #1a1a1a;
+            padding: 8px;
+            border-radius: 4px;
+            border: 1px solid #00d4ff;
         }
         .entity {
             background: rgba(123, 44, 191, 0.3);
@@ -99,10 +157,16 @@
             padding: 0 4px;
             border-radius: 3px;
             cursor: pointer;
+            position: relative;
         }
         .entity:hover {
             background: rgba(123, 44, 191, 0.5);
         }
+        .entity.selected {
+            background: #ff6b6b;
+            border-color: #ff6b6b;
+            color: #fff;
+        }
         .graph-panel {
             width: 50%;
             display: flex;
@@ -127,10 +191,15 @@
             border-radius: 6px;
             margin-bottom: 8px;
             cursor: pointer;
+            transition: all 0.2s;
         }
         .entity-item:hover {
             background: #222;
         }
+        .entity-item.selected {
+            background: #2a2a2a;
+            border-left: 3px solid #ff6b6b;
+        }
         .entity-type-badge {
             padding: 2px 8px;
             border-radius: 4px;
@@ -139,11 +208,11 @@
             margin-right: 12px;
             text-transform: uppercase;
         }
-        .type-project { background: #7b2cbf; }
+        .type-PROJECT { background: #7b2cbf; }
-        .type-tech { background: #00d4ff; color: #000; }
+        .type-TECH { background: #00d4ff; color: #000; }
-        .type-person { background: #ff6b6b; }
+        .type-PERSON { background: #ff6b6b; }
-        .type-org { background: #4ecdc4; color: #000; }
+        .type-ORG { background: #4ecdc4; color: #000; }
-        .type-other { background: #666; }
+        .type-OTHER { background: #666; }
         .upload-overlay {
             position: fixed;
             top: 0;
@@ -164,10 +233,29 @@
             border-radius: 16px;
             padding: 60px;
             text-align: center;
+            max-width: 500px;
         }
         .upload-box:hover {
             border-color: #00d4ff;
         }
+        .upload-tabs {
+            display: flex;
+            gap: 10px;
+            margin-bottom: 20px;
+            justify-content: center;
+        }
+        .upload-tab {
+            padding: 8px 16px;
+            background: #1a1a1a;
+            border: 1px solid #333;
+            border-radius: 6px;
+            cursor: pointer;
+            color: #888;
+        }
+        .upload-tab.active {
+            border-color: #00d4ff;
+            color: #00d4ff;
+        }
         .btn {
             background: linear-gradient(90deg, #00d4ff, #7b2cbf);
             color: white;
@@ -186,10 +274,316 @@
             font-size: 0.85rem;
             margin-top: 0;
         }
+        .btn-danger {
+            background: #ff6b6b;
+        }
+        .btn-secondary {
+            background: #333;
+        }
         .empty-state {
             text-align: center;
             padding: 60px 20px;
         }
+        /* Phase 2: Entity Editor Modal */
+        .modal-overlay {
+            position: fixed;
+            top: 0;
+            left: 0;
+            right: 0;
+            bottom: 0;
+            background: rgba(0,0,0,0.8);
+            display: none;
+            align-items: center;
+            justify-content: center;
+            z-index: 3000;
+        }
+        .modal-overlay.show {
+            display: flex;
+        }
+        .modal {
+            background: #1a1a1a;
+            border-radius: 12px;
+            padding: 24px;
+            width: 90%;
+            max-width: 500px;
+            max-height: 80vh;
+            overflow-y: auto;
+        }
+        .modal-header {
+            font-size: 1.2rem;
+            margin-bottom: 20px;
+            color: #fff;
+        }
+        .form-group {
+            margin-bottom: 16px;
+        }
+        .form-group label {
+            display: block;
+            margin-bottom: 6px;
+            color: #888;
+            font-size: 0.85rem;
+        }
+        .form-group input,
+        .form-group select,
+        .form-group textarea {
+            width: 100%;
+            padding: 10px 12px;
+            background: #0a0a0a;
+            border: 1px solid #333;
+            border-radius: 6px;
+            color: #e0e0e0;
+            font-size: 0.95rem;
+        }
+        .form-group input:focus,
+        .form-group select:focus,
+        .form-group textarea:focus {
+            outline: none;
+            border-color: #00d4ff;
+        }
+        .form-group textarea {
+            min-height: 80px;
+            resize: vertical;
+        }
+        .modal-actions {
+            display: flex;
+            gap: 10px;
+            justify-content: flex-end;
+            margin-top: 20px;
+        }
+        /* Phase 2: Context Menu */
+        .context-menu {
+            position: absolute;
+            background: #1a1a1a;
+            border: 1px solid #333;
+            border-radius: 6px;
+            padding: 6px 0;
+            z-index: 4000;
+            display: none;
+            min-width: 160px;
+        }
+        .context-menu.show {
+            display: block;
+        }
+        .context-menu-item {
+            padding: 8px 16px;
+            cursor: pointer;
+            font-size: 0.9rem;
+            color: #e0e0e0;
+        }
+        .context-menu-item:hover {
+            background: #2a2a2a;
+        }
+        .context-menu-divider {
+            height: 1px;
+            background: #333;
+            margin: 6px 0;
+        }
+        /* Phase 2: Relation Editor */
+        .relation-editor {
+            margin-top: 16px;
+            padding-top: 16px;
+            border-top: 1px solid #333;
+        }
+        .relation-item {
+            display: flex;
+            align-items: center;
+            gap: 8px;
+            padding: 8px;
+            background: #0a0a0a;
+            border-radius: 4px;
+            margin-bottom: 8px;
+            font-size: 0.85rem;
+        }
+        .relation-item button {
+            background: transparent;
+            border: none;
+            color: #ff6b6b;
+            cursor: pointer;
+            font-size: 0.8rem;
+        }
+        /* Phase 2: Selection toolbar */
+        .selection-toolbar {
+            position: fixed;
+            bottom: 20px;
+            left: 50%;
+            transform: translateX(-50%);
+            background: #1a1a1a;
+            border: 1px solid #333;
+            border-radius: 8px;
+            padding: 10px 20px;
+            display: none;
+            gap: 10px;
+            z-index: 3500;
+            box-shadow: 0 4px 20px rgba(0,0,0,0.5);
+        }
+        .selection-toolbar.show {
+            display: flex;
+        }
+        /* Graph node styles */
+        .node-circle {
+            cursor: pointer;
+        }
+        .node-label {
+            pointer-events: none;
+        }
+        /* Phase 3: Knowledge Base Panel */
+        .kb-panel {
+            width: 100%;
+            height: 100%;
+            display: none;
+            flex-direction: column;
+            background: #0a0a0a;
+        }
+        .kb-panel.show {
+            display: flex;
+        }
+        .kb-header {
+            padding: 16px 20px;
+            background: #141414;
+            border-bottom: 1px solid #222;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+        }
+        .kb-stats {
+            display: flex;
+            gap: 24px;
+        }
+        .kb-stat {
+            text-align: center;
+        }
+        .kb-stat-value {
+            font-size: 1.5rem;
+            font-weight: 600;
+            color: #00d4ff;
+        }
+        .kb-stat-label {
+            font-size: 0.75rem;
+            color: #666;
+        }
+        .kb-content {
+            flex: 1;
+            display: flex;
+            overflow: hidden;
+        }
+        .kb-sidebar {
+            width: 200px;
+            background: #111;
+            border-right: 1px solid #222;
+            padding: 16px 0;
+        }
+        .kb-nav-item {
+            padding: 12px 20px;
+            cursor: pointer;
+            color: #888;
+            border-left: 3px solid transparent;
+        }
+        .kb-nav-item:hover {
+            background: #1a1a1a;
+            color: #e0e0e0;
+        }
+        .kb-nav-item.active {
+            background: #1a1a1a;
+            color: #00d4ff;
+            border-left-color: #00d4ff;
+        }
+        .kb-main {
+            flex: 1;
+            padding: 20px;
+            overflow-y: auto;
+        }
+        .kb-section {
+            display: none;
+        }
+        .kb-section.active {
+            display: block;
+        }
+        .kb-entity-grid {
+            display: grid;
+            grid-template-columns: repeat(auto-fill, minmax(280px, 1fr));
+            gap: 16px;
+        }
+        .kb-entity-card {
+            background: #141414;
+            border: 1px solid #222;
+            border-radius: 8px;
+            padding: 16px;
+            cursor: pointer;
+            transition: all 0.2s;
+        }
+        .kb-entity-card:hover {
+            border-color: #00d4ff;
+        }
+        .kb-entity-name {
+            font-weight: 600;
+            margin-bottom: 4px;
+        }
+        .kb-entity-def {
+            font-size: 0.85rem;
+            color: #888;
+            margin-bottom: 8px;
+        }
+        .kb-entity-meta {
+            font-size: 0.75rem;
+            color: #666;
+        }
+        .kb-glossary-item {
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            padding: 12px 16px;
+            background: #141414;
+            border-radius: 6px;
+            margin-bottom: 8px;
+        }
+        .kb-transcript-item {
+            padding: 12px 16px;
+            background: #141414;
+            border-radius: 6px;
+            margin-bottom: 8px;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+        }
+        .file-type-icon {
+            padding: 4px 8px;
+            border-radius: 4px;
+            font-size: 0.7rem;
+            font-weight: 600;
+        }
+        .type-audio { background: #7b2cbf; }
+        .type-document { background: #00d4ff; color: #000; }
+        /* Transcript selector */
+        .transcript-selector {
+            position: relative;
+        }
+        .transcript-dropdown {
+            position: absolute;
+            top: 100%;
+            right: 0;
+            background: #1a1a1a;
+            border: 1px solid #333;
+            border-radius: 8px;
+            min-width: 200px;
+            max-height: 300px;
+            overflow-y: auto;
+            display: none;
+            z-index: 100;
+        }
+        .transcript-dropdown.show {
+            display: block;
+        }
+        .transcript-option {
+            padding: 10px 16px;
+            cursor: pointer;
+            border-bottom: 1px solid #222;
+        }
+        .transcript-option:hover {
+            background: #2a2a2a;
+        }
+        .transcript-option.active {
+            background: #00d4ff22;
+        }
     </style>
 </head>
 <body>
@@ -198,19 +592,40 @@
             <a href="/" class="back-link">← 返回项目列表</a>
             <span class="project-name" id="projectName">加载中...</span>
         </div>
-        <button class="btn btn-small" onclick="showUpload()">+ 上传音频</button>
+        <div class="header-actions">
+            <button class="btn btn-small" onclick="showUpload()">+ 上传文件</button>
+        </div>
     </div>
     
     <div class="main">
+        <!-- Sidebar -->
+        <div class="sidebar">
+            <button class="sidebar-btn active" onclick="switchView('workbench')" title="工作台">📝</button>
+            <button class="sidebar-btn" onclick="switchView('knowledge-base')" title="知识库">📚</button>
+        </div>
+        
+        <!-- Content Area -->
+        <div class="content-area">
+            <!-- Workbench View -->
+            <div id="workbenchView" class="workbench-view" style="display: flex; width: 100%;">
                 <div class="editor-panel">
                     <div class="panel-header">
+                        <div style="display: flex; align-items: center; gap: 12px;">
                             <span>📄 转录文本</span>
-                <span style="font-size:0.8rem;color:#666;">点击实体高亮</span>
+                            <div class="transcript-selector">
+                                <button class="btn-icon" onclick="toggleTranscriptDropdown()">📁 选择文件</button>
+                                <div class="transcript-dropdown" id="transcriptDropdown"></div>
+                            </div>
+                        </div>
+                        <div class="panel-actions">
+                            <button class="btn-icon" onclick="toggleEditMode()" id="editBtn">✏️ 编辑</button>
+                            <button class="btn-icon" onclick="saveTranscript()" id="saveBtn" style="display:none;">💾 保存</button>
+                        </div>
                     </div>
                     <div class="transcript-content" id="transcriptContent">
                         <div class="empty-state">
                             <p style="color:#666;">暂无转录内容</p>
-                    <button class="btn" onclick="showUpload()">上传音频</button>
+                            <button class="btn" onclick="showUpload()">上传音频或文档</button>
                         </div>
                     </div>
                 </div>
@@ -218,7 +633,7 @@
                 <div class="graph-panel">
                     <div class="panel-header">
                         <span>🔗 知识图谱</span>
-                <span style="font-size:0.8rem;color:#666;">拖拽节点查看关系</span>
+                        <span style="font-size:0.8rem;color:#666;">右键节点编辑 | 拖拽建立关系</span>
                     </div>
                     <svg id="graph-svg"></svg>
                     <div class="entity-list" id="entityList">
@@ -228,15 +643,203 @@
                 </div>
             </div>
             
+            <!-- Knowledge Base View -->
+            <div id="knowledgeBaseView" class="kb-panel">
+                <div class="kb-header">
+                    <h2>📚 项目知识库</h2>
+                    <div class="kb-stats">
+                        <div class="kb-stat">
+                            <div class="kb-stat-value" id="kbEntityCount">0</div>
+                            <div class="kb-stat-label">实体</div>
+                        </div>
+                        <div class="kb-stat">
+                            <div class="kb-stat-value" id="kbRelationCount">0</div>
+                            <div class="kb-stat-label">关系</div>
+                        </div>
+                        <div class="kb-stat">
+                            <div class="kb-stat-value" id="kbTranscriptCount">0</div>
+                            <div class="kb-stat-label">文件</div>
+                        </div>
+                        <div class="kb-stat">
+                            <div class="kb-stat-value" id="kbGlossaryCount">0</div>
+                            <div class="kb-stat-label">术语</div>
+                        </div>
+                    </div>
+                </div>
+                <div class="kb-content">
+                    <div class="kb-sidebar">
+                        <div class="kb-nav-item active" onclick="switchKBTab('entities')">🏷️ 实体</div>
+                        <div class="kb-nav-item" onclick="switchKBTab('relations')">🔗 关系</div>
+                        <div class="kb-nav-item" onclick="switchKBTab('glossary')">📖 术语表</div>
+                        <div class="kb-nav-item" onclick="switchKBTab('transcripts')">📁 文件</div>
+                    </div>
+                    <div class="kb-main">
+                        <!-- Entities Section -->
+                        <div class="kb-section active" id="kbEntitiesSection">
+                            <h3 style="margin-bottom:16px;">所有实体</h3>
+                            <div class="kb-entity-grid" id="kbEntityGrid"></div>
+                        </div>
+                        <!-- Relations Section -->
+                        <div class="kb-section" id="kbRelationsSection">
+                            <h3 style="margin-bottom:16px;">所有关系</h3>
+                            <div id="kbRelationsList"></div>
+                        </div>
+                        <!-- Glossary Section -->
+                        <div class="kb-section" id="kbGlossarySection">
+                            <div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:16px;">
+                                <h3>术语表</h3>
+                                <button class="btn btn-small" onclick="showAddTermModal()">+ 添加术语</button>
+                            </div>
+                            <div id="kbGlossaryList"></div>
+                        </div>
+                        <!-- Transcripts Section -->
+                        <div class="kb-section" id="kbTranscriptsSection">
+                            <h3 style="margin-bottom:16px;">所有文件</h3>
+                            <div id="kbTranscriptsList"></div>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </div>
+    </div>
+    
+    <!-- Upload Modal -->
     <div class="upload-overlay" id="uploadOverlay">
         <div class="upload-box">
-            <h2 style="margin-bottom:10px;">上传音频分析</h2>
+            <h2 style="margin-bottom:10px;">上传文件</h2>
-            <p style="color:#666;">支持 MP3, WAV, M4A (最大 500MB)</p>
+            <div class="upload-tabs">
-            <input type="file" id="fileInput" accept="audio/*" hidden>
+                <div class="upload-tab active" onclick="switchUploadTab('audio')">🎵 音频</div>
-            <button class="btn" onclick="document.getElementById('fileInput').click()">选择文件</button>
+                <div class="upload-tab" onclick="switchUploadTab('document')">📄 文档</div>
-            <br><br>
-            <button class="btn" style="background:#333;" onclick="hideUpload()">取消</button>
             </div>
+            <p style="color:#666;" id="uploadHint">支持 MP3, WAV, M4A (最大 500MB)</p>
+            <input type="file" id="fileInput" accept="audio/*" hidden>
+            <input type="file" id="docInput" accept=".pdf,.docx,.doc,.txt,.md" hidden>
+            <button class="btn" onclick="triggerFileSelect()">选择文件</button>
+            <br><br>
+            <button class="btn btn-secondary" onclick="hideUpload()">取消</button>
+        </div>
+    </div>
+    
+    <!-- Entity Editor Modal -->
+    <div class="modal-overlay" id="entityModal">
+        <div class="modal">
+            <h3 class="modal-header">编辑实体</h3>
+            <div class="form-group">
+                <label>实体名称</label>
+                <input type="text" id="entityName" placeholder="实体名称">
+            </div>
+            <div class="form-group">
+                <label>实体类型</label>
+                <select id="entityType">
+                    <option value="PROJECT">项目 (PROJECT)</option>
+                    <option value="TECH">技术 (TECH)</option>
+                    <option value="PERSON">人物 (PERSON)</option>
+                    <option value="ORG">组织 (ORG)</option>
+                    <option value="OTHER">其他 (OTHER)</option>
+                </select>
+            </div>
+            <div class="form-group">
+                <label>定义描述</label>
+                <textarea id="entityDefinition" placeholder="一句话描述这个实体..."></textarea>
+            </div>
+            <div class="form-group">
+                <label>别名 (用逗号分隔)</label>
+                <input type="text" id="entityAliases" placeholder="别名1, 别名2, 别名3">
+            </div>
+            <div class="relation-editor" id="relationEditor" style="display:none;">
+                <h4 style="color:#888;font-size:0.9rem;margin-bottom:12px;">实体关系</h4>
+                <div id="relationList"></div>
+                <button class="btn-icon" onclick="showAddRelation()" style="margin-top:8px;">+ 添加关系</button>
+            </div>
+            <div class="modal-actions">
+                <button class="btn btn-danger" onclick="deleteEntity()" id="deleteEntityBtn">删除</button>
+                <button class="btn btn-secondary" onclick="hideEntityModal()">取消</button>
+                <button class="btn" onclick="saveEntity()">保存</button>
+            </div>
+        </div>
+    </div>
+    
+    <!-- Add Relation Modal -->
+    <div class="modal-overlay" id="relationModal">
+        <div class="modal">
+            <h3 class="modal-header">添加关系</h3>
+            <div class="form-group">
+                <label>目标实体</label>
+                <select id="relationTarget"></select>
+            </div>
+            <div class="form-group">
+                <label>关系类型</label>
+                <select id="relationType">
+                    <option value="belongs_to">属于 (belongs_to)</option>
+                    <option value="works_with">合作 (works_with)</option>
+                    <option value="depends_on">依赖 (depends_on)</option>
+                    <option value="mentions">提及 (mentions)</option>
+                    <option value="related">相关 (related)</option>
+                </select>
+            </div>
+            <div class="form-group">
+                <label>关系证据/说明</label>
+                <textarea id="relationEvidence" placeholder="描述这个关系的依据..."></textarea>
+            </div>
+            <div class="modal-actions">
+                <button class="btn btn-secondary" onclick="hideRelationModal()">取消</button>
+                <button class="btn" onclick="saveRelation()">添加</button>
+            </div>
+        </div>
+    </div>
+    
+    <!-- Merge Entities Modal -->
+    <div class="modal-overlay" id="mergeModal">
+        <div class="modal">
+            <h3 class="modal-header">合并实体</h3>
+            <p style="color:#888;margin-bottom:16px;font-size:0.9rem;">将选中的实体合并到目标实体中</p>
+            <div class="form-group">
+                <label>源实体</label>
+                <input type="text" id="mergeSource" disabled>
+            </div>
+            <div class="form-group">
+                <label>目标实体 (保留)</label>
+                <select id="mergeTarget"></select>
+            </div>
+            <div class="modal-actions">
+                <button class="btn btn-secondary" onclick="hideMergeModal()">取消</button>
+                <button class="btn" onclick="confirmMerge()">合并</button>
+            </div>
+        </div>
+    </div>
+    
+    <!-- Add Glossary Term Modal -->
+    <div class="modal-overlay" id="glossaryModal">
+        <div class="modal">
+            <h3 class="modal-header">添加术语</h3>
+            <div class="form-group">
+                <label>术语</label>
+                <input type="text" id="glossaryTerm" placeholder="术语名称">
+            </div>
+            <div class="form-group">
+                <label>发音提示 (可选)</label>
+                <input type="text" id="glossaryPronunciation" placeholder="如: K8s 发音为 Kubernetes">
+            </div>
+            <div class="modal-actions">
+                <button class="btn btn-secondary" onclick="hideGlossaryModal()">取消</button>
+                <button class="btn" onclick="saveGlossaryTerm()">添加</button>
+            </div>
+        </div>
+    </div>
+    
+    <!-- Context Menu -->
+    <div class="context-menu" id="contextMenu">
+        <div class="context-menu-item" onclick="editEntity()">✏️ 编辑实体</div>
+        <div class="context-menu-item" onclick="showMergeModal()">🔄 合并实体</div>
+        <div class="context-menu-divider"></div>
+        <div class="context-menu-item" onclick="createEntityFromSelection()">➕ 标记为实体</div>
+    </div>
+    
+    <!-- Selection Toolbar -->
+    <div class="selection-toolbar" id="selectionToolbar">
+        <span style="color:#888;font-size:0.85rem;">选中文本:</span>
+        <button class="btn-icon" onclick="createEntityFromSelection()">标记为实体</button>
+        <button class="btn-icon" onclick="hideSelectionToolbar()">取消</button>
     </div>
     
     <script src="app.js"></script>