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
+171
View File
@@ -0,0 +1,171 @@
"""文档管理 API 测试(QdrantService 为 mock,不真实联网)"""
from collections.abc import Iterator
from typing import Any
import pytest
from fastapi.testclient import TestClient
from app.api.v1 import document as document_module
from app.main import app
from app.services.qdrant import QdrantService
class FakeQdrant:
"""假 QdrantService:返回固定数据或抛出固定异常"""
def __init__(
self,
scroll_result: tuple[list[dict[str, Any]], str | None] | None = None,
detail: dict[str, Any] | None = None,
deleted: dict[str, int] | None = None,
error: Exception | None = None,
) -> None:
self.scroll_result = scroll_result if scroll_result is not None else ([], None)
self.detail = detail
self.deleted = deleted if deleted is not None else {}
self.error = error
async def scroll_l1(self, limit: int = 20, offset: str | None = None) -> tuple[list[dict[str, Any]], str | None]:
if self.error is not None:
raise self.error
return self.scroll_result
async def get_doc_detail(self, doc_id: str) -> dict[str, Any] | None:
if self.error is not None:
raise self.error
return self.detail
async def delete_by_doc_id(self, doc_id: str) -> dict[str, int]:
if self.error is not None:
raise self.error
return self.deleted
@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 _install_fake(monkeypatch: pytest.MonkeyPatch, fake: FakeQdrant) -> None:
"""将 _get_qdrant 单例替换为假服务"""
monkeypatch.setattr(document_module, "_get_qdrant", lambda: fake)
def _make_item(doc_id: str = "doc-1") -> dict[str, Any]:
"""构造固定的 L1 列表项"""
return {
"doc_id": doc_id,
"title": "标题",
"category": "技术文档",
"tags": ["API"],
"summary": "一句话总结",
}
def test_list_documents_success(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""列表:正常返回 items 与 next_offset"""
fake = FakeQdrant(scroll_result=([_make_item()], "cursor-2"))
_install_fake(monkeypatch, fake)
resp = client.get("/api/v1/documents", params={"limit": 10, "offset": "cursor-1"})
assert resp.status_code == 200
body = resp.json()
assert body["code"] == 0
data = body["data"]
assert data["items"] == [_make_item()]
assert data["next_offset"] == "cursor-2"
def test_list_documents_empty(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""列表:空库返回 items=[]、next_offset=None"""
fake = FakeQdrant(scroll_result=([], None))
_install_fake(monkeypatch, fake)
resp = client.get("/api/v1/documents")
body = resp.json()
assert body["code"] == 0
assert body["data"] == {"items": [], "next_offset": None}
def test_get_document_detail(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""详情:存在返回 l1/l2_nodes/l3_nodes/chunks_count"""
detail = {
"l1": {"doc_id": "doc-1", "title": "标题", "text": "一句话总结"},
"l2_nodes": [{"doc_id": "doc-1", "section_path": "1", "text": "大纲节点"}],
"l3_nodes": [],
"chunks_count": 3,
}
fake = FakeQdrant(detail=detail)
_install_fake(monkeypatch, fake)
resp = client.get("/api/v1/documents/doc-1")
body = resp.json()
assert body["code"] == 0
assert body["data"] == detail
def test_get_document_not_found(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""详情:不存在返回 code=1004"""
fake = FakeQdrant(detail=None)
_install_fake(monkeypatch, fake)
resp = client.get("/api/v1/documents/missing")
body = resp.json()
assert body["code"] == 1004
assert body["message"] == "文档不存在"
assert body["data"] is None
def test_delete_document_success(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""删除:返回各集合删除数与 deleted_total"""
deleted = {"doc_l1": 1, "doc_l2": 2, "doc_l3": 4, "chunks": 6}
fake = FakeQdrant(deleted=deleted)
_install_fake(monkeypatch, fake)
resp = client.delete("/api/v1/documents/doc-1")
body = resp.json()
assert body["code"] == 0
data = body["data"]
assert data["doc_id"] == "doc-1"
assert data["deleted"] == deleted
assert data["deleted_total"] == 13
def test_delete_document_not_found_idempotent(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""删除:不存在 doc_id 仍 code=0,各集合删除数全 0、deleted_total=0(幂等)"""
deleted = {"doc_l1": 0, "doc_l2": 0, "doc_l3": 0, "chunks": 0}
fake = FakeQdrant(deleted=deleted)
_install_fake(monkeypatch, fake)
resp = client.delete("/api/v1/documents/missing")
body = resp.json()
assert body["code"] == 0
data = body["data"]
assert data["deleted"] == deleted
assert data["deleted_total"] == 0
def test_list_documents_service_error(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
"""列表:scroll 抛错返回 code=2000"""
fake = FakeQdrant(error=RuntimeError("boom"))
_install_fake(monkeypatch, fake)
resp = client.get("/api/v1/documents")
body = resp.json()
assert body["code"] == 2000
assert body["data"] is None