Python
# -*- coding: utf-8 -*-
"""
Entity store 端到端测试(chroma 后端)。
覆盖:
- entity 抽取(spaCy;模型缺失时 skip);
- chroma entity store:0.95 cosine 合并、search、list、delete;
- index helper:抽取→embed→upsert;
- client.build_entity_store 迁移(旧数据补建)。
"""
import asyncio
import random
import uuid
import pytest
from hy_memory.config import MemoryConfig
from hy_memory.models.memory import MemoryNode, MemoryLayer, MemoryStatus
from hy_memory.pipelines._retrieval.entities import extract_entities, get_nlp_full
def run(coro):
loop = asyncio.new_event_loop()
try:
return loop.run_until_complete(coro)
finally:
loop.close()
def _emb(dims: int = 32):
vec = [random.gauss(0, 1) for _ in range(dims)]
norm = sum(v * v for v in vec) ** 0.5 or 1.0
return [v / norm for v in vec]
_SPACY_OK = get_nlp_full() is not None
_needs_spacy = pytest.mark.skipif(not _SPACY_OK, reason="spaCy en_core_web_sm not installed")
class _FakeEmbed:
"""确定性 fake embedder:同文本 → 同向量(哈希派生),不同文本近正交。"""
def __init__(self, dims=32):
self.dims = dims
self._cache = {}
def _vec(self, text):
if text in self._cache:
return list(self._cache[text])
rnd = random.Random(hash(text) & 0xFFFFFFFF)
v = [rnd.gauss(0, 1) for _ in range(self.dims)]
n = sum(x * x for x in v) ** 0.5 or 1.0
v = [x / n for x in v]
self._cache[text] = v
return list(v)
async def embed_batch(self, texts):
return [self._vec(t) for t in texts]
async def embed(self, text):
return self._vec(text)
async def embed_queued(self, text, use_cache=True):
return self._vec(text)
@pytest.fixture
def config(tmp_path):
return MemoryConfig.from_dict({
"vector_store": {
"provider": "chroma",
"collection_name": f"test_ent_{uuid.uuid4().hex[:8]}",
"persist_directory": str(tmp_path / "chroma_data"),
"embedding_dims": 32,
},
})
@pytest.fixture
def store(config):
from hy_memory.data.vector_store_chroma import ChromaVectorStore
vs = ChromaVectorStore(config)
run(vs.initialize())
yield vs
run(vs.close())
class TestEntityExtraction:
@_needs_spacy
def test_proper_and_compound(self):
ents = extract_entities("User loves Kobe Bryant and machine learning")
texts = {t for (_typ, t) in ents}
assert "Kobe Bryant" in texts
assert any("machine learning" == t for t in texts)
@_needs_spacy
def test_chinese_yields_empty(self):
# 英文 spaCy 模型对中文几乎抽不到 entity(与 mem0 一致)
assert extract_entities("用户喜欢科比,住在北京") == []
def test_empty_input(self):
assert extract_entities("") == []
class TestChromaEntityStore:
def test_merge_search_list_delete(self, store):
e = _emb()
id1 = run(store.upsert_entity(entity_text="Kobe Bryant", entity_type="PROPER",
embedding=list(e), memory_id="m1", user_id="u1", agent_id="a1"))
id2 = run(store.upsert_entity(entity_text="Kobe Bryant", entity_type="PROPER",
embedding=list(e), memory_id="m2", user_id="u1", agent_id="a1"))
assert id1 == id2 # 0.95 cosine 合并
id3 = run(store.upsert_entity(entity_text="Lakers", entity_type="PROPER",
embedding=_emb(), memory_id="m3", user_id="u1", agent_id="a1"))
assert id3 != id1
hits = run(store.search_entities(query_embedding=list(e), user_id="u1", agent_ids=["a1"], top_k=10))
kobe = [h for h in hits if h["data"] == "Kobe Bryant"][0]
assert set(kobe["linked_memory_ids"]) == {"m1", "m2"}
assert kobe["score"] > 0.99
allents = run(store.list_entities(user_id="u1"))
assert len(allents) == 2
aff = run(store.delete_entities_for_memory(memory_id="m1", user_id="u1"))
assert aff == 1
hits2 = run(store.search_entities(query_embedding=list(e), user_id="u1", top_k=10))
kobe2 = [h for h in hits2 if h["data"] == "Kobe Bryant"][0]
assert kobe2["linked_memory_ids"] == ["m2"]
def test_user_isolation(self, store):
e = _emb()
run(store.upsert_entity(entity_text="Kobe", entity_type="PROPER",
embedding=list(e), memory_id="m1", user_id="u1"))
# 不同 user 查不到
hits = run(store.search_entities(query_embedding=list(e), user_id="u2", top_k=10))
assert hits == []
def _qdrant_available() -> bool:
try:
import qdrant_client # noqa: F401
return True
except Exception:
return False
_needs_qdrant = pytest.mark.skipif(not _qdrant_available(), reason="qdrant-client not installed")
@pytest.fixture
def qdrant_store(tmp_path):
cfg = MemoryConfig.from_dict({
"vector_store": {
"provider": "qdrant",
"collection_name": f"test_qent_{uuid.uuid4().hex[:8]}",
"persist_directory": str(tmp_path / "qdrant_data"),
"embedding_dims": 32,
},
})
from hy_memory.data.vector_store_qdrant import QdrantVectorStore
vs = QdrantVectorStore(cfg)
run(vs.initialize())
yield vs
run(vs.close())
class TestQdrantEntityStore:
"""Qdrant 后端 entity store(dev6 漏实现,本类回归保护)。"""
@_needs_qdrant
def test_merge_search_list_delete(self, qdrant_store):
store = qdrant_store
e = _emb()
id1 = run(store.upsert_entity(entity_text="Kobe Bryant", entity_type="PROPER",
embedding=list(e), memory_id="m1", user_id="u1", agent_id="a1"))
id2 = run(store.upsert_entity(entity_text="Kobe Bryant", entity_type="PROPER",
embedding=list(e), memory_id="m2", user_id="u1", agent_id="a1"))
assert id1 == id2 # 0.95 cosine 合并
id3 = run(store.upsert_entity(entity_text="Lakers", entity_type="PROPER",
embedding=_emb(), memory_id="m3", user_id="u1", agent_id="a1"))
assert id3 != id1
hits = run(store.search_entities(query_embedding=list(e), user_id="u1", agent_ids=["a1"], top_k=10))
kobe = [h for h in hits if h["data"] == "Kobe Bryant"][0]
assert set(kobe["linked_memory_ids"]) == {"m1", "m2"}
assert kobe["score"] > 0.99
allents = run(store.list_entities(user_id="u1"))
assert len(allents) == 2
aff = run(store.delete_entities_for_memory(memory_id="m1", user_id="u1"))
assert aff == 1
hits2 = run(store.search_entities(query_embedding=list(e), user_id="u1", top_k=10))
kobe2 = [h for h in hits2 if h["data"] == "Kobe Bryant"][0]
assert kobe2["linked_memory_ids"] == ["m2"]
@_needs_qdrant
def test_user_isolation(self, qdrant_store):
store = qdrant_store
e = _emb()
run(store.upsert_entity(entity_text="Kobe", entity_type="PROPER",
embedding=list(e), memory_id="m1", user_id="u1"))
assert run(store.search_entities(query_embedding=list(e), user_id="u2", top_k=10)) == []
class TestIndexHelper:
@_needs_spacy
def test_index_memory_entities(self, store):
from hy_memory.pipelines._retrieval.entity_store import index_memory_entities
emb = _FakeEmbed()
cnt = run(index_memory_entities(
vector_store=store, embed_service=emb,
memory_id="m1", content="User loves Kobe Bryant and the Lakers",
user_id="u1", agent_id="a1",
))
assert cnt >= 1
ents = run(store.list_entities(user_id="u1"))
datas = {e["data"] for e in ents}
assert any("Kobe" in d for d in datas)
def test_no_entities_noop(self, store):
from hy_memory.pipelines._retrieval.entity_store import index_memory_entities
emb = _FakeEmbed()
# 中文无 entity → 0,且不报错
cnt = run(index_memory_entities(
vector_store=store, embed_service=emb,
memory_id="m1", content="用户喜欢科比", user_id="u1",
))
assert cnt == 0
class TestBuildEntityStoreMigration:
@_needs_spacy
def test_build_from_existing_l2(self, config, store):
# 先种两条旧 L2_FACT(不经 writer,模拟历史数据)
emb = _FakeEmbed()
for mid, content in [("m1", "User loves Kobe Bryant"),
("m2", "User works at Notion as a product lead")]:
n = MemoryNode(node_id=mid, user_id="u1", agent_id="default_agent", session_id="s1",
content=content, layer=MemoryLayer.L2_FACT,
status=MemoryStatus.ACTIVE, is_latest=True)
n.embedding = _emb()
run(store.upsert(n))
# 手动构造一个最小 client 壳,调 async_build_entity_store 的核心逻辑
from hy_memory.pipelines._retrieval.entity_store import index_memory_entities
nodes = run(store.list_by_user(user_id="u1", agent_id="default_agent",
status_filter=[MemoryStatus.ACTIVE],
layers=[MemoryLayer.L2_FACT]))
assert len(nodes) == 2
indexed = 0
for nd in nodes:
indexed += run(index_memory_entities(
vector_store=store, embed_service=emb,
memory_id=nd.node_id, content=nd.content, user_id="u1", agent_id="default_agent",
))
assert indexed >= 2
ents = run(store.list_entities(user_id="u1"))
assert len(ents) >= 2