feat: 添加文件向量化状态检查

exam_pkg/manager.py

@@ -61,6 +61,113 @@ QUESTION_BANK_DIR = "./题库"
 DRAFT_DIR = "./题库/草稿"
 
 
+# ==================== 文件状态检查 ====================
+
+def check_file_indexed(file_path: str, collection: str) -> Dict:
+    """
+    检查文件是否已向量化
+
+    Args:
+        file_path: 文件路径
+        collection: 向量库名称
+
+    Returns:
+        {
+            "indexed": True/False,      # 是否已索引
+            "chunk_count": 0,           # 切片数量
+            "status": "ready/not_found/indexing/error",
+            "message": "状态说明"
+        }
+    """
+    if not file_path or not collection:
+        return {
+            "indexed": False,
+            "chunk_count": 0,
+            "status": "error",
+            "message": "缺少文件路径或向量库名称"
+        }
+
+    try:
+        from core.engine import get_engine
+        engine = get_engine()
+
+        if not engine:
+            return {
+                "indexed": False,
+                "chunk_count": 0,
+                "status": "error",
+                "message": "RAG 引擎未初始化"
+            }
+
+        # 提取文件名
+        filename = os.path.basename(file_path)
+
+        # 查询向量库
+        collections = [collection] if isinstance(collection, str) else list(collection) if collection else []
+
+        if not collections:
+            return {
+                "indexed": False,
+                "chunk_count": 0,
+                "status": "error",
+                "message": "未指定向量库"
+            }
+
+        # 尝试检索文件切片
+        total_chunks = 0
+        found_collection = None
+
+        for coll in collections:
+            try:
+                # 使用简单 query 查询文件
+                results = engine.search_knowledge(
+                    query="document",
+                    collections=[coll],
+                    source_filter=filename,
+                    top_k=1
+                )
+
+                if results and results.get('documents') and results['documents'][0]:
+                    # 获取该文件的切片总数
+                    collection_obj = engine.kb_manager.get_collection(coll)
+                    if collection_obj:
+                        all_results = collection_obj.get(
+                            where={"source": filename}
+                        )
+                        if all_results and all_results.get('ids'):
+                            total_chunks = len(all_results['ids'])
+                            found_collection = coll
+                            break
+            except Exception as e:
+                logger.warning(f"检查向量库 {coll} 失败: {e}")
+                continue
+
+        if total_chunks > 0:
+            return {
+                "indexed": True,
+                "chunk_count": total_chunks,
+                "status": "ready",
+                "message": f"文件已索引，共 {total_chunks} 个切片",
+                "collection": found_collection
+            }
+        else:
+            return {
+                "indexed": False,
+                "chunk_count": 0,
+                "status": "not_found",
+                "message": f"文件 {filename} 未在向量库中找到，可能正在向量化或未上传"
+            }
+
+    except Exception as e:
+        logger.error(f"检查文件索引状态失败: {e}")
+        return {
+            "indexed": False,
+            "chunk_count": 0,
+            "status": "error",
+            "message": f"检查状态异常: {str(e)}"
+        }
+
+
 # ==================== 新版出题接口 ====================
 
 def generate_questions_from_file(
@@ -102,6 +209,28 @@ def generate_questions_from_file(
     """
     options = options or {}
 
+    # 🔥 新增：检查文件向量化状态
+    file_status = check_file_indexed(file_path, collection)
+
+    if not file_status["indexed"]:
+        # 文件未索引，返回明确的错误信息
+        error_messages = {
+            "not_found": f"文件未向量化: {file_status['message']}",
+            "error": f"检查文件状态失败: {file_status['message']}",
+        }
+
+        return {
+            "success": False,
+            "request_id": request_id,
+            "error_code": "FILE_NOT_INDEXED" if file_status["status"] == "not_found" else "STATUS_CHECK_ERROR",
+            "message": error_messages.get(file_status["status"], file_status["message"]),
+            "file_status": file_status["status"],
+            "chunk_count": file_status["chunk_count"],
+            "questions": [],
+            "total": 0,
+            "source_chunks_used": 0
+        }
+
     # 1. 检索文件的所有切片
     chunks = retrieve_file_chunks(
         file_path=file_path,