feat: add legacy and modern data_id calculating

This commit is contained in:
Igor Ilic 2025-11-04 13:01:10 +01:00
parent e3b707a0c2
commit b0f85c9e99
3 changed files with 78 additions and 4 deletions

View file

@ -10,6 +10,7 @@ from .get_authorized_dataset import get_authorized_dataset
from .get_authorized_dataset_by_name import get_authorized_dataset_by_name
from .get_data import get_data
from .get_unique_dataset_id import get_unique_dataset_id
from .get_unique_data_id import get_unique_data_id
from .get_authorized_existing_datasets import get_authorized_existing_datasets
from .get_dataset_ids import get_dataset_ids

View file

@ -0,0 +1,71 @@
from uuid import uuid5, NAMESPACE_OID, UUID
from typing import Optional
from sqlalchemy import select
from cognee.modules.data.models.Data import Data
from cognee.infrastructure.databases.relational import get_relational_engine
from cognee.modules.users.models import User
async def get_unique_data_id(data_identifier: str, user: User, tenant_id: Optional[UUID]) -> UUID:
"""
Function returns a unique UUID for data based on data identifier, user id and tenant id.
If data with legacy ID exists, return that ID to maintain compatibility.
Args:
data_identifier: A way to uniquely identify data (e.g. file hash, data name, etc.)
user: User object adding the data
tenant_id: UUID of the tenant for which data is being added
Returns:
UUID: Unique identifier for the data
"""
def _get_deprecated_unique_data_id(data_identifier: str, user: User) -> UUID:
"""
Deprecated function, returns a unique UUID for data based on data identifier and user id.
Needed to support legacy data without tenant information.
Args:
data_identifier: A way to uniquely identify data (e.g. file hash, data name, etc.)
user: User object adding the data
Returns:
UUID: Unique identifier for the data
"""
# return UUID hash of file contents + owner id + tenant_id
return uuid5(NAMESPACE_OID, f"{data_identifier}{str(user.id)}")
def _get_modern_unique_data_id(data_identifier: str, user: User, tenant_id: UUID) -> UUID:
"""
Function returns a unique UUID for data based on data identifier, user id and tenant id.
Args:
data_identifier: A way to uniquely identify data (e.g. file hash, data name, etc.)
user: User object adding the data
tenant_id: UUID of the tenant for which data is being added
Returns:
UUID: Unique identifier for the data
"""
# return UUID hash of file contents + owner id + tenant_id
return uuid5(NAMESPACE_OID, f"{data_identifier}{str(user.id)}{str(tenant_id)}")
# Get all possible data_id values
data_id = {
"modern_data_id": _get_modern_unique_data_id(
data_identifier=data_identifier, user=user, tenant_id=tenant_id
),
"legacy_data_id": _get_deprecated_unique_data_id(
data_identifier=data_identifier, user=user
),
}
# Check if data item with legacy_data_id exists, if so use that one, else use modern_data_id
db_engine = get_relational_engine()
async with db_engine.get_async_session() as session:
legacy_data_point = (
await session.execute(select(Data).filter(Data.id == data_id["legacy_data_id"]))
).scalar_one_or_none()
if not legacy_data_point:
return data_id["modern_data_id"]
return data_id["legacy_data_id"]

View file

@ -1,11 +1,13 @@
from uuid import uuid5, NAMESPACE_OID
from uuid import UUID
from .data_types import IngestionData
from cognee.modules.users.models import User
from cognee.modules.data.methods import get_unique_data_id
def identify(data: IngestionData, user: User) -> str:
async def identify(data: IngestionData, user: User) -> UUID:
data_content_hash: str = data.get_identifier()
# return UUID hash of file contents + owner id
return uuid5(NAMESPACE_OID, f"{data_content_hash}{user.id}")
return await get_unique_data_id(
data_identifier=data_content_hash, user=user, tenant_id=user.tenant_id
)