Remove Bucket driver from nucliadb_datasets (#1757)

* Remove Bucket driver from nucliadb_datasets * WIP on deleting datasets * WIP * Fix * Fix * Fix sort * Fix lint * Update nucliadb_dataset/nucliadb_dataset/settings.py Co-authored-by: Joan Antoni RE <[email protected]> --------- Co-authored-by: Joan Antoni RE <[email protected]>
nuclia · Jan 24, 2024 · 4dc7501 · 4dc7501 · github-actions · Jan 24, 2024
1 parent 8a67587
commit 4dc7501
Show file tree

Hide file tree

Showing 24 changed files with 794 additions and 813 deletions.
diff --git a/nucliadb/nucliadb/train/api/v1/check.py b/nucliadb/nucliadb/train/api/v1/check.py
@@ -21,10 +21,10 @@
 from fastapi import Request
 from fastapi_versioning import version  # type: ignore
 
-from nucliadb.train.api.models import TrainSetPartitions
 from nucliadb.train.api.utils import get_kb_partitions
 from nucliadb.train.api.v1.router import KB_PREFIX, api
 from nucliadb_models.resource import NucliaDBRoles
+from nucliadb_models.trainset import TrainSetPartitions
 from nucliadb_utils.authentication import requires_one
 
 

diff --git a/nucliadb/nucliadb/train/api/v1/trainset.py b/nucliadb/nucliadb/train/api/v1/trainset.py
@@ -23,10 +23,10 @@
 from fastapi import Request
 from fastapi_versioning import version  # type: ignore
 
-from nucliadb.train.api.models import TrainSetPartitions
 from nucliadb.train.api.utils import get_kb_partitions
 from nucliadb.train.api.v1.router import KB_PREFIX, api
 from nucliadb_models.resource import NucliaDBRoles
+from nucliadb_models.trainset import TrainSetPartitions
 from nucliadb_utils.authentication import requires_one
 
 

diff --git a/nucliadb_dataset/nucliadb_dataset/__init__.py b/nucliadb_dataset/nucliadb_dataset/__init__.py
@@ -20,41 +20,24 @@
 from enum import Enum
 from typing import Dict
 
-from nucliadb_dataset.dataset import (
-    NucliaCloudDataset,
-    NucliaDBDataset,
-    Task,
-    download_all_partitions,
-)
+from nucliadb_dataset.dataset import NucliaDBDataset, Task, download_all_partitions
 from nucliadb_dataset.nuclia import NucliaDriver
 
 NUCLIA_GLOBAL: Dict[str, NucliaDriver] = {}
 
 CLIENT_ID = "CLIENT"
 
 
-class DatasetType(str, Enum):
-    FIELD_CLASSIFICATION = "FIELD_CLASSIFICATION"
-    IMAGE_CLASSIFICATION = "IMAGE_CLASSIFICATION"
-    PARAGRAPH_CLASSIFICATION = "PARAGRAPH_CLASSIFICATION"
-    PARAGRAPH_STREAMING = "PARAGRAPH_STREAMING"
-    QUESTION_ANSWER_STREAMING = "QUESTION_ANSWER_STREAMING"
-    SENTENCE_CLASSIFICATION = "SENTENCE_CLASSIFICATION"
-    TOKEN_CLASSIFICATION = "TOKEN_CLASSIFICATION"
-
-
 class ExportType(str, Enum):
     DATASETS = "DATASETS"
     FILESYSTEM = "FILESYSTEM"
 
 
 __all__ = (
     "NucliaDBDataset",
-    "NucliaCloudDataset",
     "Task",
     "download_all_partitions",
     "NUCLIA_GLOBAL",
     "CLIENT_ID",
-    "DatasetType",
     "ExportType",
 )