2026-09-12 10:45:40 +08:00
|
|
|
|
"""幂等创建长期记忆画像向量集合 `user_long_term_memory_v1`。
|
|
|
|
|
|
|
|
|
|
|
|
写入侧是 `app/infrastructure/milvus_profile_projection.py`,字段必须与之一致。
|
|
|
|
|
|
|
|
|
|
|
|
用法:
|
|
|
|
|
|
.\\.venv\\Scripts\\python.exe tools\\setup_milvus_profile_collection.py
|
|
|
|
|
|
|
|
|
|
|
|
安全口径(与 `setup_milvus_knowledge_collections.py` 相同:这是**共享** Milvus 实例,
|
|
|
|
|
|
里面还有别的项目在用的集合):
|
|
|
|
|
|
- 只碰 `user_long_term_memory_v1` 这一个集合,绝不 list 后批量删除;
|
|
|
|
|
|
- 集合已存在时**只做结构比对并报告**,不覆盖、不删重建;
|
|
|
|
|
|
- 结构不一致时明确报错退出,由人决定怎么处理,避免静默丢数据。
|
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
|
|
import asyncio
|
|
|
|
|
|
import sys
|
2026-09-20 14:33:30 +08:00
|
|
|
|
from pathlib import Path
|
2026-09-12 10:45:40 +08:00
|
|
|
|
from typing import Any
|
|
|
|
|
|
|
2026-09-20 14:33:30 +08:00
|
|
|
|
# 与 setup_milvus_knowledge_collections.py 同一条引导:脚本必须能直接在仓库根目录用
|
|
|
|
|
|
# 项目解释器执行(见模块 docstring 的用法)。缺这一行会在根目录直接报
|
|
|
|
|
|
# ModuleNotFoundError: No module named app(2026-09-19 S-7 实测)。
|
|
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
|
|
|
|
|
|
2026-09-12 10:45:40 +08:00
|
|
|
|
COLLECTION = "user_long_term_memory_v1"
|
|
|
|
|
|
VECTOR_FIELD = "embedding"
|
|
|
|
|
|
VECTOR_DIM = 1024
|
|
|
|
|
|
PRIMARY_FIELD = "memory_uuid"
|
|
|
|
|
|
|
|
|
|
|
|
#: (字段名, 最大长度)。`memory_uuid` 是主键(UUID 字符串)。
|
|
|
|
|
|
VARCHAR_FIELDS: tuple[tuple[str, int], ...] = (
|
|
|
|
|
|
("memory_uuid", 64),
|
|
|
|
|
|
("content", 2048),
|
|
|
|
|
|
("memory_type", 32),
|
|
|
|
|
|
("memory_key", 64),
|
|
|
|
|
|
("status", 16),
|
|
|
|
|
|
)
|
|
|
|
|
|
#: INT64 字段;可空,因为 `valid_until_ts` 对永久记忆为空。
|
|
|
|
|
|
INT64_FIELDS: tuple[str, ...] = (
|
|
|
|
|
|
"customer_id",
|
|
|
|
|
|
"version",
|
|
|
|
|
|
"valid_until_ts",
|
|
|
|
|
|
"updated_at_ts",
|
|
|
|
|
|
)
|
|
|
|
|
|
FLOAT_FIELDS: tuple[str, ...] = ("confidence",)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _build_schema() -> Any:
|
|
|
|
|
|
from pymilvus import DataType, MilvusClient # type: ignore[import-untyped]
|
|
|
|
|
|
|
|
|
|
|
|
schema = MilvusClient.create_schema(auto_id=False, enable_dynamic_field=False)
|
|
|
|
|
|
for name, max_length in VARCHAR_FIELDS:
|
|
|
|
|
|
schema.add_field(
|
|
|
|
|
|
field_name=name,
|
|
|
|
|
|
datatype=DataType.VARCHAR,
|
|
|
|
|
|
max_length=max_length,
|
|
|
|
|
|
is_primary=(name == PRIMARY_FIELD),
|
|
|
|
|
|
nullable=False,
|
|
|
|
|
|
)
|
|
|
|
|
|
for name in INT64_FIELDS:
|
|
|
|
|
|
# 可空:`valid_until_ts` 对永久记忆必须能不写。
|
|
|
|
|
|
schema.add_field(
|
|
|
|
|
|
field_name=name, datatype=DataType.INT64, nullable=name != "customer_id"
|
|
|
|
|
|
)
|
|
|
|
|
|
for name in FLOAT_FIELDS:
|
|
|
|
|
|
schema.add_field(field_name=name, datatype=DataType.DOUBLE, nullable=False)
|
|
|
|
|
|
schema.add_field(
|
|
|
|
|
|
field_name=VECTOR_FIELD, datatype=DataType.FLOAT_VECTOR, dim=VECTOR_DIM
|
|
|
|
|
|
)
|
|
|
|
|
|
return schema
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _build_index_params() -> Any:
|
|
|
|
|
|
from pymilvus import MilvusClient # type: ignore[import-untyped]
|
|
|
|
|
|
|
|
|
|
|
|
index_params = MilvusClient.prepare_index_params()
|
|
|
|
|
|
index_params.add_index(
|
|
|
|
|
|
field_name=VECTOR_FIELD,
|
|
|
|
|
|
index_name="profile_vector_index",
|
|
|
|
|
|
index_type="AUTOINDEX",
|
|
|
|
|
|
metric_type="COSINE",
|
|
|
|
|
|
)
|
|
|
|
|
|
return index_params
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def describe_mismatch(described: dict[str, Any]) -> list[str]:
|
|
|
|
|
|
"""比对已存在集合与期望结构,返回差异列表(一致时为空)。"""
|
|
|
|
|
|
problems: list[str] = []
|
|
|
|
|
|
actual = {field["name"]: field for field in described.get("fields", [])}
|
|
|
|
|
|
expected_names = (
|
|
|
|
|
|
[name for name, _ in VARCHAR_FIELDS] + list(INT64_FIELDS)
|
|
|
|
|
|
+ list(FLOAT_FIELDS) + [VECTOR_FIELD]
|
|
|
|
|
|
)
|
|
|
|
|
|
for name in expected_names:
|
|
|
|
|
|
if name not in actual:
|
|
|
|
|
|
problems.append(f"缺少字段 {name}")
|
|
|
|
|
|
for name, _ in VARCHAR_FIELDS:
|
|
|
|
|
|
if name in actual and not actual[name].get("is_primary") and name == PRIMARY_FIELD:
|
|
|
|
|
|
problems.append(f"{name} 不是主键")
|
|
|
|
|
|
vector = actual.get(VECTOR_FIELD)
|
|
|
|
|
|
if vector is not None:
|
|
|
|
|
|
params = vector.get("params") or {}
|
|
|
|
|
|
dim = params.get("dim")
|
|
|
|
|
|
if dim is not None and int(dim) != VECTOR_DIM:
|
|
|
|
|
|
problems.append(f"{VECTOR_FIELD} 维度是 {dim},期望 {VECTOR_DIM}")
|
|
|
|
|
|
return problems
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def ensure_collection(uri: str, token: str = "") -> str:
|
|
|
|
|
|
"""返回 `created` / `exists` / `conflict:<原因>`。"""
|
|
|
|
|
|
from pymilvus import AsyncMilvusClient # type: ignore[import-untyped]
|
|
|
|
|
|
|
|
|
|
|
|
client = AsyncMilvusClient(uri=uri, token=token or None)
|
|
|
|
|
|
try:
|
|
|
|
|
|
if await client.has_collection(COLLECTION):
|
|
|
|
|
|
described = await client.describe_collection(COLLECTION)
|
|
|
|
|
|
problems = describe_mismatch(described)
|
|
|
|
|
|
if problems:
|
|
|
|
|
|
return "conflict:" + "; ".join(problems)
|
|
|
|
|
|
return "exists"
|
|
|
|
|
|
await client.create_collection(
|
|
|
|
|
|
collection_name=COLLECTION,
|
|
|
|
|
|
schema=_build_schema(),
|
|
|
|
|
|
index_params=_build_index_params(),
|
|
|
|
|
|
)
|
|
|
|
|
|
return "created"
|
|
|
|
|
|
finally:
|
|
|
|
|
|
close = getattr(client, "close", None)
|
|
|
|
|
|
if close is not None:
|
|
|
|
|
|
await close()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def main() -> int:
|
|
|
|
|
|
from app.core.config import get_settings
|
|
|
|
|
|
|
|
|
|
|
|
settings = get_settings()
|
|
|
|
|
|
uri = settings.milvus_uri
|
|
|
|
|
|
if not uri:
|
|
|
|
|
|
print("未配置 milvus_uri,无法创建集合")
|
|
|
|
|
|
return 1
|
|
|
|
|
|
outcome = await ensure_collection(uri, settings.milvus_token or "")
|
|
|
|
|
|
print(f"{COLLECTION}: {outcome}")
|
|
|
|
|
|
if outcome.startswith("conflict:"):
|
|
|
|
|
|
print("结构不一致,未做任何修改。请人工确认后再处理。")
|
|
|
|
|
|
return 2
|
|
|
|
|
|
return 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
|
|
sys.exit(asyncio.run(main()))
|