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
This commit is contained in:
2026-07-29 21:24:40 +08:00
commit 51dc8dc4f6
83 changed files with 10794 additions and 0 deletions
+74
View File
@@ -0,0 +1,74 @@
"""文档入库 API 测试(任务管理器为 FakeManager,不真实联网)"""
from collections.abc import Iterator
import pytest
from fastapi.testclient import TestClient
from app.api.v1 import document as document_module
from app.main import app
from app.models.document import DocumentInput
from app.services.qdrant import QdrantService
class FakeManager:
"""假入库任务管理器:记录 submit 调用并返回固定 task_id"""
def __init__(self, task_id: str = "task-1") -> None:
self.task_id = task_id
self.submitted: list[DocumentInput] = []
async def submit(self, doc: DocumentInput) -> str:
self.submitted.append(doc)
return self.task_id
@pytest.fixture
def client(monkeypatch: pytest.MonkeyPatch) -> Iterator[TestClient]:
"""TestClientlifespan 中的 Qdrant 集合初始化替换为空操作"""
async def _noop_ensure_collections(self: QdrantService) -> None:
return None
monkeypatch.setattr(QdrantService, "ensure_collections", _noop_ensure_collections)
with TestClient(app) as test_client:
yield test_client
def test_ingest_submit_accepted(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""正常提交:HTTP 202code=0data 含 task_id 与 status=pending,文档已登记给管理器"""
fake = FakeManager(task_id="task-abc")
monkeypatch.setattr(document_module, "_get_task_manager", lambda: fake)
resp = client.post("/api/v1/documents", json={"text": "正文内容", "title": "标题"})
assert resp.status_code == 202
body = resp.json()
assert body["code"] == 0
data = body["data"]
assert data["task_id"] == "task-abc"
assert data["status"] == "pending"
assert [d.title for d in fake.submitted] == ["标题"]
def test_ingest_empty_text(client: TestClient) -> None:
"""空 text:路由内校验,返回 code=1001"""
resp = client.post("/api/v1/documents", json={"text": ""})
body = resp.json()
assert body["code"] == 1001
assert body["message"] == "文档内容不能为空"
assert body["data"] is None
def test_ingest_no_sync_ingestion_error(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""任务模式下同步路径不再返回 2000:提交即 202,入库失败体现在任务状态中"""
fake = FakeManager()
monkeypatch.setattr(document_module, "_get_task_manager", lambda: fake)
resp = client.post("/api/v1/documents", json={"text": "正文内容"})
assert resp.status_code == 202
body = resp.json()
assert body["code"] == 0
assert body["data"]["status"] == "pending"