直接新建后端把所有逻辑做完了

backend/main.py

@@ -1,79 +1,119 @@
-from fastapi import FastAPI
-from .service import crawler_service
-from .schemas import RegisterRequest, PendingRequest, SaveResultsRequest, AddUrlsRequest, SearchRequest
+# backend/main.py
+from fastapi import FastAPI, APIRouter, BackgroundTasks
+from .service import crawler_sql_service
+from .workflow import workflow
+from .schemas import (
+    RegisterRequest, PendingRequest, SaveResultsRequest, AddUrlsRequest, SearchRequest,
+    AutoMapRequest, AutoProcessRequest, TextSearchRequest
+)
 from .utils import make_response
 
 app = FastAPI(title="Wiki Crawler API")
 
-@app.post("/register")
+# ==========================================
+# V1 Router: 原始的底层接口 (Manual Control)
+# ==========================================
+router_v1 = APIRouter()
+
+@router_v1.post("/register")
 async def register(req: RegisterRequest):
     try:
-        data = crawler_service.register_task(req.url)
+        data = crawler_sql_service.register_task(req.url)
         return make_response(1, "Success", data)
     except Exception as e:
         return make_response(0, str(e))
 
-@app.post("/add_urls")
+@router_v1.post("/add_urls")
 async def add_urls(req: AddUrlsRequest):
     try:
         urls = req.urls_obj["urls"]
-        data = crawler_service.add_urls(req.task_id, urls=urls)
+        data = crawler_sql_service.add_urls(req.task_id, urls=urls)
         return make_response(1, "Success", data)
     except Exception as e:
         return make_response(0, str(e))
 
-@app.post("/pending_urls")
+@router_v1.post("/pending_urls")
 async def pending_urls(req: PendingRequest):
     try:
-        data = crawler_service.get_pending_urls(req.task_id, req.limit)
+        data = crawler_sql_service.get_pending_urls(req.task_id, req.limit)
         msg = "Success" if data["urls"] else "Queue Empty"
         return make_response(1, msg, data)
     except Exception as e:
         return make_response(0, str(e))
 
-@app.post("/save_results")
+@router_v1.post("/save_results")
 async def save_results(req: SaveResultsRequest):
     try:
-        data = crawler_service.save_results(req.task_id, req.results)
+        data = crawler_sql_service.save_results(req.task_id, req.results)
         return make_response(1, "Success", data)
     except Exception as e:
         return make_response(0, str(e))
 
-@app.post("/search")
-async def search(req: SearchRequest):
-    """
-    通用搜索接口：
-    支持基于 task_id 的局部搜索，也支持不传 task_id 的全库搜索。
-    """
+@router_v1.post("/search")
+async def search_v1(req: SearchRequest):
+    """V1 搜索：需要客户端自己传向量"""
     try:
-        # 1. 基础校验：确保向量不为空且维度正确（阿里 v4 模型通常为 1536）
         vector = req.query_embedding['vector']
+        # 注意：这里需要确认你数据库的向量维度。TextEmbedding V3 可能是 1024，V2 是 1536。
+        # 请根据你的 PGVector 设置进行匹配。
+        if not vector:
+            return make_response(2, "Vector is empty", None)
 
-        if not vector or len(vector) != 1536:
-            return make_response(
-                code=2, 
-                msg=f"向量维度错误。期望 1536, 实际收到 {len(req.query_embedding) if req.query_embedding else 0}",
-                data=None
-            )
-
-        # 2. 调用业务类执行搜索
-        data = crawler_service.search_knowledge(
+        data = crawler_sql_service.search_knowledge(
             query_embedding=vector,
             task_id=req.task_id,
             limit=req.limit
         )
-
-        # 3. 统一返回
-        return make_response(
-            code=1, 
-            msg="搜索完成", 
-            data=data
-        )
-
+        return make_response(1, "Search Done", data)
     except Exception as e:
-        # 记录日志并返回失败信息
-        print(f"搜索接口异常: {str(e)}")
-        return make_response(code=0, msg=f"搜索失败: {str(e)}")
+        return make_response(0, str(e))
+
+
+# ==========================================
+# V2 Router: 自动化工作流 (Automated Workflow)
+# ==========================================
+router_v2 = APIRouter()
+
+@router_v2.post("/auto/map")
+async def auto_map(req: AutoMapRequest, background_tasks: BackgroundTasks):
+    """
+    [异步] 输入首页 URL，自动调用 Firecrawl Map 并入库
+    """
+    # 也可以放入 background_tasks，但 map 通常比较快，这里演示同步返回任务ID
+    try:
+        # 为了不阻塞主线程，如果 map 很慢，建议放入 background_tasks
+        # 这里为了能立刻看到 task_id，先同步调用 (Firecrawl Map 比较快)
+        data = workflow.map_and_ingest(req.url)
+        return make_response(1, "Mapping Started", data)
+    except Exception as e:
+        return make_response(0, str(e))
+
+@router_v2.post("/auto/process")
+async def auto_process(req: AutoProcessRequest, background_tasks: BackgroundTasks):
+    """
+    [异步] 触发后台任务：消费队列 -> 抓取 -> Embedding -> 入库
+    """
+    # 将耗时操作放入后台任务
+    background_tasks.add_task(workflow.process_task_queue, req.task_id, req.batch_size)
+    return make_response(1, "Processing started in background", {"task_id": req.task_id})
+
+@router_v2.post("/search")
+async def search_v2(req: TextSearchRequest):
+    """
+    [智能] 输入自然语言文本 -> 后端转向量 -> 搜索
+    """
+    try:
+        data = workflow.search_with_embedding(req.query, req.task_id, req.limit)
+        return make_response(1, "Search Success", data)
+    except Exception as e:
+        return make_response(0, f"Search Failed: {str(e)}")
+
+
+# ==========================================
+# 挂载路由
+# ==========================================
+app.include_router(router_v1, prefix="/api/v1", tags=["V1 Manual API"])
+app.include_router(router_v2, prefix="/api/v2", tags=["V2 Automated Workflow"])
 
 if __name__ == "__main__":
     import uvicorn