Files
QMDSearch/app/api/v1/document.py
T
kplam 51dc8dc4f6 Initial commit: QMDSearch 分层信息检索服务
- FastAPI + Qdrant + Redis + Ollama 技术栈
- L1→L2→L3→chunk 四层分层检索(dense + sparse RRF 融合)
- 文档三级总结与 2.5 级回退
- query 解析路由与分类
- /admin 管理页面
2026-07-29 21:24:40 +08:00

112 lines
4.1 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""文档 APIPOST /api/v1/documents 异步入库 + 任务查询 + 文档管理(列表/详情/删除)"""
from typing import Any
import structlog
from fastapi import APIRouter, Query
from fastapi.responses import JSONResponse
from app.api.response import ApiError, ok
from app.config import Settings
from app.core.ingest_tasks import IngestTaskManager
from app.core.ingestion import Ingester
from app.models.document import DocumentInput
from app.services.qdrant import QdrantService
from app.services.redis import RedisCache, get_cache
logger = structlog.get_logger()
router = APIRouter(prefix="/api/v1", tags=["document"])
# 模块级懒加载单例,避免每请求重建 Ingester 及其下游依赖
_ingester: Ingester | None = None
_qdrant: QdrantService | None = None
_task_manager: IngestTaskManager | None = None
def _get_ingester() -> Ingester:
global _ingester
if _ingester is None:
_ingester = Ingester()
return _ingester
def _get_qdrant() -> QdrantService:
global _qdrant
if _qdrant is None:
_qdrant = QdrantService()
return _qdrant
def _get_task_manager() -> IngestTaskManager:
"""入库任务管理器懒加载单例
Redis 沿用全局缓存单例(RedisCache 读写全容错,不可用时镜像写失败仅告警);
获取缓存实例异常时传 None,退化为纯内存模式。
"""
global _task_manager
if _task_manager is None:
try:
redis: RedisCache | None = get_cache()
except Exception:
logger.warning("Redis 缓存不可用,入库任务状态仅保留在内存", exc_info=True)
redis = None
_task_manager = IngestTaskManager(ingester=_get_ingester(), redis=redis, settings=Settings())
return _task_manager
@router.post("/documents")
async def ingest_document(doc: DocumentInput) -> JSONResponse:
"""文档入库入口:登记异步任务并返回 202 + task_id,入库结果经任务查询端点获取"""
if not doc.text.strip():
raise ApiError(1001, "文档内容不能为空")
task_id = await _get_task_manager().submit(doc)
return JSONResponse(status_code=202, content=ok({"task_id": task_id, "status": "pending"}))
@router.get("/documents/tasks/{task_id}")
async def get_ingest_task(task_id: str) -> dict[str, Any]:
"""查询入库任务状态:含 task_id/status/created_at/updated_atdone 附 resultfailed 附 error"""
task = await _get_task_manager().get(task_id)
if task is None:
raise ApiError(1004, "任务不存在")
return ok(task)
@router.get("/documents")
async def list_documents(
limit: int = Query(default=20, ge=1, le=100),
offset: str | None = None,
) -> dict[str, Any]:
"""分页列出文档(L1 摘要),返回 items 与下一页游标 next_offset"""
try:
items, next_offset = await _get_qdrant().scroll_l1(limit=limit, offset=offset)
except Exception as exc:
logger.error("文档列表查询失败", error=str(exc))
raise ApiError(2000, f"文档列表查询失败: {exc}") from exc
return ok({"items": items, "next_offset": next_offset})
@router.get("/documents/{doc_id}")
async def get_document(doc_id: str) -> dict[str, Any]:
"""获取文档详情:L1 记录 + L2/L3 节点 + chunks 数量"""
try:
detail = await _get_qdrant().get_doc_detail(doc_id)
except Exception as exc:
logger.error("文档详情查询失败", doc_id=doc_id, error=str(exc))
raise ApiError(2000, f"文档详情查询失败: {exc}") from exc
if detail is None:
raise ApiError(1004, "文档不存在")
return ok(detail)
@router.delete("/documents/{doc_id}")
async def delete_document(doc_id: str) -> dict[str, Any]:
"""删除文档:四层集合中该 doc_id 的所有点;幂等,不存在也返回成功(删除数全 0)"""
try:
deleted = await _get_qdrant().delete_by_doc_id(doc_id)
except Exception as exc:
logger.error("文档删除失败", doc_id=doc_id, error=str(exc))
raise ApiError(2000, f"文档删除失败: {exc}") from exc
return ok({"doc_id": doc_id, "deleted": deleted, "deleted_total": sum(deleted.values())})