131 lines
4.8 KiB
Python
131 lines
4.8 KiB
Python
# backend/main.py
|
||
from fastapi import FastAPI, APIRouter, BackgroundTasks
|
||
# 确保导入路径与你的文件名一致，如果文件名是 workflow.py 则用 workflow
|
||
from .services.crawler_sql_service import crawler_sql_service
|
||
from .services.automated_crawler import workflow
|
||
from .schemas import (
|
||
RegisterRequest, PendingRequest, SaveResultsRequest, AddUrlsRequest, SearchRequest,
|
||
AutoMapRequest, AutoProcessRequest, TextSearchRequest
|
||
)
|
||
from .utils import make_response
|
||
|
||
app = FastAPI(title="Wiki Crawler API")
|
||
|
||
# ==========================================
|
||
# 工具函数
|
||
# ==========================================
|
||
|
||
|
||
# ==========================================
|
||
# V1 Router: 原始的底层接口 (Manual Control)
|
||
# ==========================================
|
||
router_v1 = APIRouter()
|
||
|
||
@router_v1.post("/register")
|
||
async def register(req: RegisterRequest):
|
||
try:
|
||
# Service 返回: {'task_id': 1, 'is_new_task': True, 'msg': '...'}
|
||
res = crawler_sql_service.register_task(req.url)
|
||
# 使用 pop 将 msg 提取出来作为响应的 msg，剩下的作为 data
|
||
return make_response(1, res.pop("msg", "Success"), res)
|
||
except Exception as e:
|
||
return make_response(0, str(e))
|
||
|
||
@router_v1.post("/add_urls")
|
||
async def add_urls(req: AddUrlsRequest):
|
||
try:
|
||
urls = req.urls_obj["urls"]
|
||
res = crawler_sql_service.add_urls(req.task_id, urls=urls)
|
||
return make_response(1, res.pop("msg", "Success"), res)
|
||
except Exception as e:
|
||
return make_response(0, str(e))
|
||
|
||
@router_v1.post("/pending_urls")
|
||
async def pending_urls(req: PendingRequest):
|
||
try:
|
||
res = crawler_sql_service.get_pending_urls(req.task_id, req.limit)
|
||
# 即使队列为空，Service 也会返回 msg="Queue is empty"
|
||
return make_response(1, res.pop("msg", "Success"), res)
|
||
except Exception as e:
|
||
return make_response(0, str(e))
|
||
|
||
@router_v1.post("/save_results")
|
||
async def save_results(req: SaveResultsRequest):
|
||
try:
|
||
res = crawler_sql_service.save_results(req.task_id, req.results)
|
||
return make_response(1, res.pop("msg", "Success"), res)
|
||
except Exception as e:
|
||
return make_response(0, str(e))
|
||
|
||
@router_v1.post("/search")
|
||
async def search_v1(req: SearchRequest):
|
||
"""V1 搜索：客户端手动传向量"""
|
||
try:
|
||
vector = req.query_embedding['vector']
|
||
if not vector:
|
||
return make_response(2, "Vector is empty", None)
|
||
|
||
# Service 现在返回 {'results': [...], 'msg': 'Found ...'}
|
||
res = crawler_sql_service.search_knowledge(
|
||
query_embedding=vector,
|
||
task_id=req.task_id,
|
||
limit=req.limit
|
||
)
|
||
return make_response(1, res.pop("msg", "Search Done"), res)
|
||
except Exception as 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):
|
||
"""
|
||
[同步] 输入首页 URL，自动调用 Firecrawl Map 并入库
|
||
"""
|
||
try:
|
||
# Workflow 返回: {'task_id':..., 'msg': 'Task mapped...', ...}
|
||
res = workflow.map_and_ingest(req.url)
|
||
return make_response(1, res.pop("msg", "Mapping Started"), res)
|
||
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
|
||
"""
|
||
try:
|
||
# 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)
|
||
|
||
# 因为是后台任务，无法立即获取 Service 的返回值 msg，只能返回通用消息
|
||
return make_response(1, "Background processing started", {"task_id": req.task_id})
|
||
except Exception as e:
|
||
return make_response(0, str(e))
|
||
|
||
@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:
|
||
# Workflow 返回 {'results': [...], 'msg': '...'}
|
||
res = workflow.search_with_embedding(req.query, req.task_id, req.limit)
|
||
return make_response(1, res.pop("msg", "Search Success"), res)
|
||
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
|
||
uvicorn.run(app, host="0.0.0.0", port=8000, reload=True) |