Initial commit: 国土空间规划课程智能体 v1.0

单容器 Docker 架构的国土空间规划课程智能问答系统，集成 FastAPI 后端与 Next.js 前端。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend/src/services/document_service.py

@@ -0,0 +1,127 @@
+"""
+文档处理服务（LangChain 1.0）
+"""
+import os
+import hashlib
+from pathlib import Path
+from typing import List, Dict, Any, Optional
+from sqlalchemy.orm import Session
+from langchain_core.documents import Document as LangChainDocument
+
+from ..models.document import Document, DocumentChunk
+from ..rag.vector_store import get_vector_store
+from ..rag.document_loaders import DocumentLoaderFactory
+from ..rag.text_splitters import get_text_splitter
+
+class DocumentService:
+    """文档处理服务"""
+    
+    def __init__(self, db: Session):
+        self.db = db
+        self.vector_store = get_vector_store()
+    
+    async def process_document(self, document_id: int) -> bool:
+        """处理文档（使用LangChain 1.0）"""
+        try:
+            document = self.db.query(Document).filter(Document.id == document_id).first()
+            if not document:
+                return False
+            
+            # 1. 使用LangChain加载文档
+            documents = DocumentLoaderFactory.load_document(
+                file_path=document.file_path,
+                file_type=document.file_type,
+                metadata={
+                    "document_id": document.id,
+                    "knowledge_base_id": document.knowledge_base_id,
+                    "title": document.title,
+                    "filename": document.filename
+                }
+            )
+            
+            # 2. 使用中文优化的文本分割器
+            text_splitter = get_text_splitter(chunk_size=1000, chunk_overlap=200)
+            splits = text_splitter.split_documents(documents)
+            
+            # 3. 添加到向量存储
+            success = self.vector_store.add_documents(splits)
+            
+            if success:
+                document.is_processed = True
+                self.db.commit()
+                return True
+            
+            return False
+            
+        except Exception as e:
+            print(f"处理文档失败: {str(e)}")
+            self.db.rollback()
+            return False
+    
+    def search_documents(self, query: str, knowledge_base_ids: Optional[List[int]] = None, limit: int = 5) -> List[Dict[str, Any]]:
+        """搜索文档（保留原有接口兼容性）"""
+        try:
+            # 构建过滤条件
+            filter_dict = None
+            if knowledge_base_ids:
+                filter_dict = {"knowledge_base_id": {"$in": knowledge_base_ids}}
+            
+            # 使用LangChain Chroma进行搜索
+            results = self.vector_store.similarity_search_with_score(
+                query=query,
+                k=limit,
+                filter=filter_dict
+            )
+            
+            # 格式化结果
+            search_results = []
+            for doc, distance in results:
+                metadata = doc.metadata if hasattr(doc, 'metadata') else {}
+                score = self._convert_distance_to_score(distance)
+                
+                search_results.append({
+                    "content": doc.page_content,
+                    "metadata": metadata,
+                    "score": score,
+                    "distance": distance
+                })
+            
+            return search_results
+            
+        except Exception as e:
+            print(f"搜索文档失败: {str(e)}")
+            return []
+    
+    def _convert_distance_to_score(self, distance: float) -> float:
+        """将ChromaDB的distance转换为0-1范围的相似度分数"""
+        import math
+        
+        # 内积距离（负值）
+        if distance < 0:
+            return (1 + distance) / 2
+        
+        # 大距离使用对数缩放
+        if distance > 100:
+            return 1 / (1 + math.log(distance))
+        
+        # 标准距离转换
+        return 1 / (1 + distance)
+    
+    def get_document_chunks(self, document_id: int) -> List[DocumentChunk]:
+        """获取文档的所有块"""
+        return self.db.query(DocumentChunk).filter(
+            DocumentChunk.document_id == document_id
+        ).order_by(DocumentChunk.chunk_index).all()
+    
+    def delete_document_chunks(self, document_id: int) -> bool:
+        """删除文档的所有块"""
+        try:
+            self.db.query(DocumentChunk).filter(
+                DocumentChunk.document_id == document_id
+            ).delete()
+            self.db.commit()
+            return True
+        except Exception as e:
+            print(f"删除文档块失败: {str(e)}")
+            self.db.rollback()
+            return False