109 lines
4.0 KiB
Python
109 lines
4.0 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""
|
||
clone_user 在 BM25 sparse qdrant 集合上的回归。
|
||
|
||
0.1.6.4 起 qdrant 启用 fastembed BM25 后，scroll/retrieve 返回的 point.vector
|
||
是命名多向量 dict（{"": dense, "bm25": SparseVector}）。clone 走 list_by_user
|
||
读 src 节点，旧代码把整个 dict 赋给 node.embedding；clone 复制后再 upsert，
|
||
_build_vector_field 把 dict 当 List[float] 又包一层 → 非法嵌套 → PointStruct
|
||
ValidationError → rollback → cloned_count=0。
|
||
|
||
本测试在带 sparse 的 qdrant 集合上：
|
||
1. list_by_user 返回的 embedding 必须是 List[float]（不是 dict）；
|
||
2. clone_user 成功，cloned_count == src 节点数；
|
||
3. dst 可被 list_by_user 读回，数量一致。
|
||
"""
|
||
|
||
import asyncio
|
||
import uuid
|
||
|
||
import pytest
|
||
|
||
from hy_memory.config import MemoryConfig
|
||
from hy_memory.models.memory import MemoryNode, MemoryLayer, MemoryStatus
|
||
|
||
|
||
def run(coro):
|
||
loop = asyncio.new_event_loop()
|
||
try:
|
||
return loop.run_until_complete(coro)
|
||
finally:
|
||
loop.close()
|
||
|
||
|
||
def _emb(dims=32):
|
||
import random
|
||
v = [random.gauss(0, 1) for _ in range(dims)]
|
||
n = sum(x * x for x in v) ** 0.5 or 1.0
|
||
return [x / n for x in v]
|
||
|
||
|
||
def _qdrant_sparse_ok():
|
||
try:
|
||
import qdrant_client # noqa
|
||
from hy_memory.pipelines._retrieval import bm25_fastembed
|
||
return bm25_fastembed.is_available()
|
||
except Exception:
|
||
return False
|
||
|
||
|
||
def _mk(node_id, content, uid="src_u", aid="a1"):
|
||
n = MemoryNode(
|
||
node_id=node_id, user_id=uid, agent_id=aid, session_id="s1",
|
||
content=content, layer=MemoryLayer.L2_FACT,
|
||
status=MemoryStatus.ACTIVE, is_latest=True,
|
||
)
|
||
n.embedding = _emb()
|
||
return n
|
||
|
||
|
||
@pytest.mark.skipif(not _qdrant_sparse_ok(),
|
||
reason="qdrant-client + fastembed (BM25 sparse) required")
|
||
class TestCloneQdrantSparse:
|
||
def test_clone_on_bm25_sparse_collection(self, tmp_path):
|
||
from hy_memory.data.vector_store_qdrant import QdrantVectorStore
|
||
|
||
cfg = MemoryConfig.from_dict({"vector_store": {
|
||
"provider": "qdrant",
|
||
"collection_name": f"t_clone_{uuid.uuid4().hex[:8]}",
|
||
"persist_directory": str(tmp_path / "qdrant"),
|
||
"embedding_dims": 32,
|
||
}})
|
||
vs = QdrantVectorStore(cfg)
|
||
run(vs.initialize())
|
||
try:
|
||
# 该集合应启用 BM25 sparse（否则测不到回归）
|
||
assert vs._supports_fulltext, "expected BM25 sparse collection"
|
||
|
||
src_uid = "src_user_clone"
|
||
nodes = [_mk(f"n{i}", f"用户喜欢运动项目{i}", uid=src_uid) for i in range(5)]
|
||
run(vs.upsert_batch(nodes))
|
||
|
||
# 1) list_by_user 的 embedding 必须是 List[float]，不能是多向量 dict
|
||
listed = run(vs.list_by_user(src_uid, agent_id="a1"))
|
||
assert len(listed) == 5
|
||
for nd in listed:
|
||
assert isinstance(nd.embedding, list), \
|
||
f"embedding 应为 List[float]，实际 {type(nd.embedding)}"
|
||
assert nd.embedding and not isinstance(nd.embedding[0], dict)
|
||
|
||
# 2) 模拟 clone：复制 list_by_user 读到的节点到新 user 再 upsert
|
||
# （等价于 async_clone_user 的核心数据流，复现「读→复制→写」）
|
||
cloned = []
|
||
for nd in listed:
|
||
c = MemoryNode(
|
||
node_id=str(uuid.uuid4()), user_id="dst_user_clone",
|
||
agent_id="a1", session_id="s1", content=nd.content,
|
||
layer=nd.layer, status=MemoryStatus.ACTIVE, is_latest=True,
|
||
)
|
||
c.embedding = nd.embedding # 复制读路径的 embedding
|
||
cloned.append(c)
|
||
written = run(vs.upsert_batch(cloned))
|
||
assert len(written) == 5, f"clone upsert 应写入 5 条，实际 {len(written)}"
|
||
|
||
# 3) dst 可读回，数量一致
|
||
dst = run(vs.list_by_user("dst_user_clone", agent_id="a1"))
|
||
assert len(dst) == 5
|
||
finally:
|
||
run(vs.close())
|