hafnia 0.5.0__py3-none-any.whl → 0.5.2__py3-none-any.whl

hafnia/platform/datasets.py

@@ -1,23 +1,13 @@
-import collections
-import shutil
-from pathlib import Path
 from typing import Any, Dict, List, Optional
 
 import rich
-from packaging.version import Version
 from rich import print as rprint
 
 from hafnia import http, utils
-from hafnia.dataset.dataset_names import DATASET_FILENAMES_REQUIRED, ResourceCredentials
-from hafnia.dataset.dataset_recipe.dataset_recipe import (
-    DatasetRecipe,
-    get_dataset_path_from_recipe,
-)
-from hafnia.dataset.hafnia_dataset import HafniaDataset
 from hafnia.http import fetch, post
 from hafnia.log import user_logger
-from hafnia.platform import s5cmd_utils
 from hafnia.platform.download import get_resource_credentials
+from hafnia.platform.s5cmd_utils import ResourceCredentials
 from hafnia.utils import timed
 from hafnia_cli.config import Config
 
@@ -57,7 +47,6 @@ def get_or_create_dataset(dataset_name: str = "", cfg: Optional[Config] = None)
     """Create a new dataset on the Hafnia platform."""
     cfg = cfg or Config()
     dataset = get_dataset_by_name(dataset_name, cfg)
-
     if dataset is not None:
         user_logger.info(f"Dataset '{dataset_name}' already exists on the Hafnia platform.")
         return dataset
@@ -130,6 +119,31 @@ def get_upload_credentials_by_id(dataset_id: str, cfg: Optional[Config] = None)
     return ResourceCredentials.fix_naming(credentials_response)
 
 
+@timed("Get read access credentials by ID")
+def get_read_credentials_by_id(dataset_id: str, cfg: Optional[Config] = None) -> Optional[ResourceCredentials]:
+    """Get dataset read access credentials by ID from the Hafnia platform."""
+    cfg = cfg or Config()
+    endpoint_dataset = cfg.get_platform_endpoint("datasets")
+    if utils.is_hafnia_cloud_job():
+        credentials_endpoint_suffix = "temporary-credentials-hidden"  # Access to hidden datasets
+    else:
+        credentials_endpoint_suffix = "temporary-credentials"  # Access to sample dataset
+    access_dataset_endpoint = f"{endpoint_dataset}/{dataset_id}/{credentials_endpoint_suffix}"
+    resource_credentials = get_resource_credentials(access_dataset_endpoint, cfg.api_key)
+    return resource_credentials
+
+
+@timed("Get read access credentials by name")
+def get_read_credentials_by_name(dataset_name: str, cfg: Optional[Config] = None) -> Optional[ResourceCredentials]:
+    """Get dataset read access credentials by name from the Hafnia platform."""
+    cfg = cfg or Config()
+    dataset_response = get_dataset_by_name(dataset_name=dataset_name, cfg=cfg)
+    if dataset_response is None:
+        return None
+
+    return get_read_credentials_by_id(dataset_response["id"], cfg=cfg)
+
+
 @timed("Delete dataset by id")
 def delete_dataset_by_id(dataset_id: str, cfg: Optional[Config] = None) -> Dict:
     cfg = cfg or Config()
@@ -152,10 +166,14 @@ def delete_dataset_by_name(dataset_name: str, cfg: Optional[Config] = None) -> D
     return response
 
 
-def delete_dataset_completely_by_name(dataset_name: str, interactive: bool = True) -> None:
+def delete_dataset_completely_by_name(
+    dataset_name: str,
+    interactive: bool = True,
+    cfg: Optional[Config] = None,
+) -> None:
     from hafnia.dataset.operations.dataset_s3_storage import delete_hafnia_dataset_files_on_platform
 
-    cfg = Config()
+    cfg = cfg or Config()
 
     is_deleted = delete_hafnia_dataset_files_on_platform(
         dataset_name=dataset_name,
@@ -180,79 +198,6 @@ def upload_dataset_details(cfg: Config, data: dict, dataset_name: str) -> dict:
     return response  # type: ignore[return-value]
 
 
-def download_or_get_dataset_path(
-    dataset_name: str,
-    cfg: Optional[Config] = None,
-    path_datasets_folder: Optional[str] = None,
-    force_redownload: bool = False,
-    download_files: bool = True,
-) -> Path:
-    """Download or get the path of the dataset."""
-    recipe_explicit = DatasetRecipe.from_implicit_form(dataset_name)
-    path_dataset = get_dataset_path_from_recipe(recipe_explicit, path_datasets=path_datasets_folder)
-
-    is_dataset_valid = HafniaDataset.check_dataset_path(path_dataset, raise_error=False)
-    if is_dataset_valid and not force_redownload:
-        user_logger.info("Dataset found locally. Set 'force=True' or add `--force` flag with cli to re-download")
-        return path_dataset
-
-    cfg = cfg or Config()
-    api_key = cfg.api_key
-
-    shutil.rmtree(path_dataset, ignore_errors=True)
-
-    endpoint_dataset = cfg.get_platform_endpoint("datasets")
-    dataset_res = get_dataset_by_name(dataset_name, cfg)  # Check if dataset exists
-    if dataset_res is None:
-        raise ValueError(f"Dataset '{dataset_name}' not found on the Hafnia platform.")
-
-    dataset_id = dataset_res.get("id")  # type: ignore[union-attr]
-
-    if utils.is_hafnia_cloud_job():
-        credentials_endpoint_suffix = "temporary-credentials-hidden"  # Access to hidden datasets
-    else:
-        credentials_endpoint_suffix = "temporary-credentials"  # Access to sample dataset
-    access_dataset_endpoint = f"{endpoint_dataset}/{dataset_id}/{credentials_endpoint_suffix}"
-
-    download_dataset_from_access_endpoint(
-        endpoint=access_dataset_endpoint,
-        api_key=api_key,
-        path_dataset=path_dataset,
-        download_files=download_files,
-    )
-    return path_dataset
-
-
-def download_dataset_from_access_endpoint(
-    endpoint: str,
-    api_key: str,
-    path_dataset: Path,
-    version: Optional[str] = None,
-    download_files: bool = True,
-) -> None:
-    try:
-        resource_credentials = get_resource_credentials(endpoint, api_key)
-        download_annotation_dataset_from_version(
-            version=version,
-            credentials=resource_credentials,
-            path_dataset=path_dataset,
-        )
-
-    except ValueError as e:
-        user_logger.error(f"Failed to download annotations: {e}")
-        return
-
-    if not download_files:
-        return
-    dataset = HafniaDataset.from_path(path_dataset, check_for_images=False)
-    try:
-        dataset = dataset.download_files_aws(path_dataset, aws_credentials=resource_credentials, force_redownload=True)
-    except ValueError as e:
-        user_logger.error(f"Failed to download images: {e}")
-        return
-    dataset.write_annotations(path_folder=path_dataset)  # Overwrite annotations as files have been re-downloaded
-
-
 TABLE_FIELDS = {
     "ID": "id",
     "Hidden\nSamples": "hidden.samples",
@@ -287,48 +232,3 @@ def extend_dataset_details(datasets: List[Dict[str, Any]]) -> List[Dict[str, Any
             dataset[f"{variant_type}.samples"] = variant["number_of_data_items"]
             dataset[f"{variant_type}.size"] = utils.size_human_readable(variant["size_bytes"])
     return datasets
-
-
-def download_annotation_dataset_from_version(
-    version: Optional[str],
-    credentials: ResourceCredentials,
-    path_dataset: Path,
-) -> list[str]:
-    path_dataset.mkdir(parents=True, exist_ok=True)
-
-    envs = credentials.aws_credentials()
-    bucket_prefix_sample_versions = f"{credentials.s3_uri()}/versions"
-    all_s3_annotation_files = s5cmd_utils.list_bucket(bucket_prefix=bucket_prefix_sample_versions, append_envs=envs)
-    s3_files = _annotation_files_from_version(version=version, all_annotation_files=all_s3_annotation_files)
-
-    local_paths = [(path_dataset / filename.split("/")[-1]).as_posix() for filename in s3_files]
-    s5cmd_utils.fast_copy_files(
-        src_paths=s3_files,
-        dst_paths=local_paths,
-        append_envs=envs,
-        description="Downloading annotation files",
-    )
-    return local_paths
-
-
-def _annotation_files_from_version(version: Optional[str], all_annotation_files: list[str]) -> list[str]:
-    version_files = collections.defaultdict(list)
-    for metadata_file in all_annotation_files:
-        version_str, filename = metadata_file.split("/")[-2:]
-        if filename not in DATASET_FILENAMES_REQUIRED:
-            continue
-        version_files[version_str].append(metadata_file)
-    available_versions = {v for v, files in version_files.items() if len(files) == len(DATASET_FILENAMES_REQUIRED)}
-
-    if len(available_versions) == 0:
-        raise ValueError("No versions were found in the dataset.")
-
-    if version is None:
-        latest_version = max(Version(ver) for ver in available_versions)
-        version = str(latest_version)
-        user_logger.info(f"No version selected. Using latest version: {version}")
-
-    if version not in available_versions:
-        raise ValueError(f"Selected version '{version}' not found in available versions: {available_versions}")
-
-    return version_files[version]

hafnia/platform/download.py

@@ -5,9 +5,9 @@ import boto3
 from botocore.exceptions import ClientError
 from rich.progress import Progress
 
-from hafnia.dataset.dataset_names import ResourceCredentials
 from hafnia.http import fetch
 from hafnia.log import sys_logger, user_logger
+from hafnia.platform.s5cmd_utils import ResourceCredentials
 
 
 def get_resource_credentials(endpoint: str, api_key: str) -> ResourceCredentials:

hafnia/platform/s5cmd_utils.py

@@ -7,6 +7,10 @@ import uuid
 from pathlib import Path
 from typing import Dict, List, Optional
 
+import boto3
+from botocore.exceptions import UnauthorizedSSOTokenError
+from pydantic import BaseModel, field_validator
+
 from hafnia.log import sys_logger, user_logger
 from hafnia.utils import progress_bar
 
@@ -26,7 +30,11 @@ def find_s5cmd() -> Optional[str]:
     if result:
         return result
     python_dir = Path(sys.executable).parent
-    locations = (python_dir / "Scripts" / "s5cmd.exe", python_dir / "bin" / "s5cmd", python_dir / "s5cmd")
+    locations = (
+        python_dir / "Scripts" / "s5cmd.exe",
+        python_dir / "bin" / "s5cmd",
+        python_dir / "s5cmd",
+    )
     for loc in locations:
         if loc.exists():
             return str(loc)
@@ -104,12 +112,17 @@ def delete_bucket_content(
     returns = execute_command(["rm", f"{bucket_prefix}/*"], append_envs=append_envs)
 
     if returns.returncode != 0:
-        bucket_is_already_deleted = "no object found" in returns.stderr.strip()
-        if bucket_is_already_deleted:
+        bucket_content_is_already_deleted = "no object found" in returns.stderr.strip()
+        bucket_is_already_deleted = "NoSuchBucket" in returns.stderr.strip()
+        if bucket_content_is_already_deleted:
             user_logger.info(f"No action was taken. S3 bucket '{bucket_prefix}' is already empty.")
+        elif bucket_is_already_deleted:
+            user_logger.info(f"No action was taken. S3 bucket '{bucket_prefix}' does not exist.")
+            return
         else:
             user_logger.error("Error during s5cmd rm command:")
             user_logger.error(returns.stdout)
+            user_logger.error(returns.stderr)
             raise RuntimeError(f"Failed to delete all files in S3 bucket '{bucket_prefix}'.")
 
     if remove_bucket:
@@ -118,6 +131,7 @@ def delete_bucket_content(
         if returns.returncode != 0:
             user_logger.error("Error during s5cmd rb command:")
             user_logger.error(returns.stdout)
+            user_logger.error(returns.stderr)
             raise RuntimeError(f"Failed to delete S3 bucket '{bucket_prefix}'.")
     user_logger.info(f"S3 bucket '{bucket_prefix}' has been deleted.")
 
@@ -145,3 +159,108 @@ def fast_copy_files(
     cmds = [f"cp {src} {dst}" for src, dst in zip(src_paths, dst_paths)]
     lines = execute_commands(cmds, append_envs=append_envs, description=description)
     return lines
+
+
+ARN_PREFIX = "arn:aws:s3:::"
+
+
+class AwsCredentials(BaseModel):
+    access_key: str
+    secret_key: str
+    session_token: str
+    region: Optional[str]
+
+    def aws_credentials(self) -> Dict[str, str]:
+        """
+        Returns the AWS credentials as a dictionary.
+        """
+        environment_vars = {
+            "AWS_ACCESS_KEY_ID": self.access_key,
+            "AWS_SECRET_ACCESS_KEY": self.secret_key,
+            "AWS_SESSION_TOKEN": self.session_token,
+        }
+        if self.region:
+            environment_vars["AWS_REGION"] = self.region
+
+        return environment_vars
+
+    @staticmethod
+    def from_session(session: boto3.Session) -> "AwsCredentials":
+        """
+        Creates AwsCredentials from a Boto3 session.
+        """
+        try:
+            frozen_credentials = session.get_credentials().get_frozen_credentials()
+        except UnauthorizedSSOTokenError as e:
+            raise RuntimeError(
+                f"Failed to get AWS credentials from the session for profile '{session.profile_name}'.\n"
+                f"Ensure the profile exists in your AWS config in '~/.aws/config' and that you are logged in via AWS SSO.\n"
+                f"\tUse 'aws sso login --profile {session.profile_name}' to log in."
+            ) from e
+        return AwsCredentials(
+            access_key=frozen_credentials.access_key,
+            secret_key=frozen_credentials.secret_key,
+            session_token=frozen_credentials.token,
+            region=session.region_name,
+        )
+
+    def to_resource_credentials(self, bucket_name: str) -> "ResourceCredentials":
+        """
+        Converts AwsCredentials to ResourceCredentials by adding the S3 ARN.
+        """
+        payload = self.model_dump()
+        payload["s3_arn"] = f"{ARN_PREFIX}{bucket_name}"
+        return ResourceCredentials(**payload)
+
+
+class ResourceCredentials(AwsCredentials):
+    s3_arn: str
+
+    @staticmethod
+    def fix_naming(payload: Dict[str, str]) -> "ResourceCredentials":
+        """
+        The endpoint returns a payload with a key called 's3_path', but it
+        is actually an ARN path (starts with arn:aws:s3::). This method renames it to 's3_arn' for consistency.
+        """
+        if "s3_path" in payload and payload["s3_path"].startswith(ARN_PREFIX):
+            payload["s3_arn"] = payload.pop("s3_path")
+
+        if "region" not in payload:
+            payload["region"] = "eu-west-1"
+        return ResourceCredentials(**payload)
+
+    @field_validator("s3_arn")
+    @classmethod
+    def validate_s3_arn(cls, value: str) -> str:
+        """Validate s3_arn to ensure it starts with 'arn:aws:s3:::'"""
+        if not value.startswith("arn:aws:s3:::"):
+            raise ValueError(f"Invalid S3 ARN: {value}. It should start with 'arn:aws:s3:::'")
+        return value
+
+    def s3_path(self) -> str:
+        """
+        Extracts the S3 path from the ARN.
+        Example: arn:aws:s3:::my-bucket/my-prefix -> my-bucket/my-prefix
+        """
+        return self.s3_arn[len(ARN_PREFIX) :]
+
+    def s3_uri(self) -> str:
+        """
+        Converts the S3 ARN to a URI format.
+        Example: arn:aws:s3:::my-bucket/my-prefix -> s3://my-bucket/my-prefix
+        """
+        return f"s3://{self.s3_path()}"
+
+    def bucket_name(self) -> str:
+        """
+        Extracts the bucket name from the S3 ARN.
+        Example: arn:aws:s3:::my-bucket/my-prefix -> my-bucket
+        """
+        return self.s3_path().split("/")[0]
+
+    def object_key(self) -> str:
+        """
+        Extracts the object key from the S3 ARN.
+        Example: arn:aws:s3:::my-bucket/my-prefix -> my-prefix
+        """
+        return "/".join(self.s3_path().split("/")[1:])

{hafnia-0.5.0.dist-info → hafnia-0.5.2.dist-info}/METADATA

@@ -1,16 +1,17 @@
 Metadata-Version: 2.4
 Name: hafnia
-Version: 0.5.0
+Version: 0.5.2
 Summary: Python SDK for communication with Hafnia platform.
 Author-email: Milestone Systems <hafniaplatform@milestone.dk>
 License-File: LICENSE
 Requires-Python: >=3.10
 Requires-Dist: boto3>=1.35.91
 Requires-Dist: click>=8.1.8
+Requires-Dist: docstring-parser>=0.17.0
 Requires-Dist: emoji>=2.14.1
 Requires-Dist: flatten-dict>=0.4.2
 Requires-Dist: keyring>=25.6.0
-Requires-Dist: mcp>=1.16.0
+Requires-Dist: mcp>=1.23.0
 Requires-Dist: mlflow>=3.4.0
 Requires-Dist: more-itertools>=10.7.0
 Requires-Dist: opencv-python-headless>=4.11.0.86

{hafnia-0.5.0.dist-info → hafnia-0.5.2.dist-info}/RECORD

@@ -6,23 +6,23 @@ hafnia/utils.py,sha256=l_awkrb3OttxqSMkPiYcpuP3c_kejkSmiqndSahc1s0,8703
 hafnia/data/__init__.py,sha256=o9QjiGbEcNa6r-qDmwwmxPXf-1UitNl5-WxFNcujqsg,111
 hafnia/data/factory.py,sha256=kHkvOtBUbwaShZBGf1kZzocDJBn_1dHHLrQxnUpJmfY,778
 hafnia/dataset/dataset_details_uploader.py,sha256=H_zz67bBwbgo4StUwBNmH89WlqydIc-tEQbrRnZDwgg,24161
-hafnia/dataset/dataset_helpers.py,sha256=SwQnFy0T0dGVRuBeT7tG_CHsb9WtW8v8mTg9TnQH2k4,4093
-hafnia/dataset/dataset_names.py,sha256=qYbrsqeKiTsu53w7uWDXdw0Y8cHDEHydoalakChKDcY,7413
-hafnia/dataset/hafnia_dataset.py,sha256=YzQjFAY3m5MJvKyHELWdS1mn9UY4xmGmnSRAS8nQRbY,34037
-hafnia/dataset/hafnia_dataset_types.py,sha256=B0yW7wI6Bf0ILw0HS3LeUu_w0NKJyTZhHvKXT_98q_A,21415
+hafnia/dataset/dataset_helpers.py,sha256=N8W_ioDlxP2VvNJXzqXLDbcEqgPKz0WyPNOBakHoBUc,6443
+hafnia/dataset/dataset_names.py,sha256=42_UKrDwcKEW48oTbtBaeyi5qVFVaMAj8vRvDv-mcEI,3616
+hafnia/dataset/hafnia_dataset.py,sha256=OOenIMPm8K23AgxHvmc_y05KCzxIwaZa-gv3uNC50NU,38519
+hafnia/dataset/hafnia_dataset_types.py,sha256=eCLawdjIFoul67AAtQ4xaKjbVSNAFA-mvbJYofiu2Sg,26848
 hafnia/dataset/license_types.py,sha256=b1Jt5e8N89sujIs4T9y39sJEkzpAwCoLDTHDTpkiEOI,2166
-hafnia/dataset/dataset_recipe/dataset_recipe.py,sha256=CkU61k_qaPSu_4Yo-NArr7jHWP417LCmzDKnmzZuDeo,19080
+hafnia/dataset/dataset_recipe/dataset_recipe.py,sha256=Ln49jcpOQ4qzumv-SkWSBCqNgSP1dGQloKSLs7psP90,20991
 hafnia/dataset/dataset_recipe/recipe_transforms.py,sha256=j3Oiytt3LI2rCaJid7Y44oT9MXvlZVqvZanngMebIWg,3088
 hafnia/dataset/dataset_recipe/recipe_types.py,sha256=AcrG6gpRt3Igl-CCJ60uyh-WkfI1NCnQ55M8yClSI9Q,5328
 hafnia/dataset/format_conversions/format_coco.py,sha256=7GjeF016ZBaKxu-VYiqXxuPw8HuuODV1cxc2TbDDZBw,19628
 hafnia/dataset/format_conversions/format_helpers.py,sha256=-lNgn_mrpVM_Xwb3jHH0BlBEPCMKjLqTeYf4PbssbuQ,1144
 hafnia/dataset/format_conversions/format_image_classification_folder.py,sha256=ALVsQfSvBfAkpmUDijznqqd2JBh0Qtnvzq7igxMjMb8,7170
 hafnia/dataset/format_conversions/format_yolo.py,sha256=zvCHo2L_0mPJScMbDtwvZUts9UX2ERKhhYbY31Q6tQA,9912
-hafnia/dataset/format_conversions/torchvision_datasets.py,sha256=1H4AMaOYRe6xAU-Pjv7oB7djpis6W6qmzYdHg_hxwKg,12096
-hafnia/dataset/operations/dataset_s3_storage.py,sha256=kIQBK3yc8AqD1kDjWJi8m-ujOvZ5xvgsT93RHUpuByA,8864
+hafnia/dataset/format_conversions/torchvision_datasets.py,sha256=sC8DgAt10PEaCHFk_Lm-dIzr_0EF-2g24kG9EINYk7c,12096
+hafnia/dataset/operations/dataset_s3_storage.py,sha256=xPC77Og47xTpI0JBFAR1pgb5u7l18byAA6p7IlpnpGE,8971
 hafnia/dataset/operations/dataset_stats.py,sha256=Ltf-V4_o_IB4UXw9WG9bsVoqeX90yGsjivK0CDggriw,11930
 hafnia/dataset/operations/dataset_transformations.py,sha256=qUNno0rAT1A452uzlR-k1WbatyY9VuMp1QJjkMg9GzE,19495
-hafnia/dataset/operations/table_transformations.py,sha256=odcs6e7L-WmkpzkZcF7aRLXIzaXElQX6raFX8FfyZEk,14397
+hafnia/dataset/operations/table_transformations.py,sha256=mdjUE1lSQ7QyONjQapSHDg1MkYuKaflcoVUq1Y6Lkqc,13606
 hafnia/dataset/primitives/__init__.py,sha256=xFLJ3R7gpbuQnNJuFhuu836L3nicwoaY5aHkqk7Bbr8,927
 hafnia/dataset/primitives/bbox.py,sha256=QJJBebltOd9J3idisp3QdX0gCgz6P5xlIlGbth19fG0,6669
 hafnia/dataset/primitives/bitmask.py,sha256=Q7RiNYvMDlcFPkXAWXDJkCIERjnUTCrHu6VeEPX1jEA,7212
@@ -33,14 +33,15 @@ hafnia/dataset/primitives/primitive.py,sha256=Wvby0sCGgYj8ec39PLcHsmip5VKL96ZSCz
 hafnia/dataset/primitives/segmentation.py,sha256=hnXIUklkuDMxYkUaff1bgRTcXI_2b32RIbobxR3ejzk,2017
 hafnia/dataset/primitives/utils.py,sha256=3gT1as-xXEj8CamoIuBb9gQwUN9Ae9qnqtqF_uEe0zo,1993
 hafnia/experiment/__init__.py,sha256=OEFE6HqhO5zcTCLZcPcPVjIg7wMFFnvZ1uOtAVhRz7M,85
+hafnia/experiment/command_builder.py,sha256=9_Of8WsJyyaCSK4C0vJMLVaUU6qEhnVNaIUAEHc80rI,27580
 hafnia/experiment/hafnia_logger.py,sha256=BHIOLAds_3JxT0cev_ikUH0XQVIxBJTkcBSx2Q_SIk0,10894
 hafnia/platform/__init__.py,sha256=L_Q7CNpsJ0HMNPy_rLlLK5RhmuCU7IF4BchxKv6amYc,782
 hafnia/platform/builder.py,sha256=kUEuj5-qtL1uk5v2tUvOCREn5yV-G4Fr6F31haIAb5E,5808
 hafnia/platform/dataset_recipe.py,sha256=ybfSSHVPG0eFUbzg_1McezPSOtMoDZEg7l6rFYndtb4,3857
-hafnia/platform/datasets.py,sha256=gfFHltZ70BJ3XeqxGvDMn06B1hmfhS-9bO149qtJruA,13079
-hafnia/platform/download.py,sha256=A6McEvRw5KmEAn3kx3nNnjxQm1Z8ZSAhn_NFgrM66_8,5020
+hafnia/platform/datasets.py,sha256=nXHg3I14p3tJeDX2woPH9NMiOxn_54zlIOPJXvXFI_w,9448
+hafnia/platform/download.py,sha256=e73Pm0afwRPTHxBvRy0gUZSFfDuePHPnfasyhaZ-KGQ,5019
 hafnia/platform/experiment.py,sha256=SrEH0nuwwBXf1Iu4diB1BEPqL-TxW3aQkZWBbM1-tY0,1846
-hafnia/platform/s5cmd_utils.py,sha256=clI_niKjya0E5d8Jmgvfj86jiuxMD9uK83znWKN6tYY,5335
+hafnia/platform/s5cmd_utils.py,sha256=hHsGPJ1S9_hFIVfCO-efvTF4qbLYreK1nl3VC5caU1w,9491
 hafnia/platform/trainer_package.py,sha256=w6JC7o-279ujcwtNTbUaQ9AnPcYRPPbD8EACa6XyUHA,2206
 hafnia/visualizations/colors.py,sha256=003eAJVnBal4abaYIIpsrT7erIOIjTUHHYVJ1Tj1CDc,5226
 hafnia/visualizations/image_visualizations.py,sha256=rB7c-KK-qq0BsSdkaFxCAHOOCTXTUQx0VMEhib7ig0k,7509
@@ -48,15 +49,15 @@ hafnia_cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hafnia_cli/__main__.py,sha256=CqD_7RfbfwB6MED3WZ8WxclrFxWcRMtZ5A1Snnst3GM,1761
 hafnia_cli/config.py,sha256=X0dJBYH-7mNAFkHgeZvDbawlQqoyCwoY4C-QhlyYCA0,7695
 hafnia_cli/consts.py,sha256=uCpYX44NCu_Zvte0QwChunxOo-qqhcaJRSYDAIsoJ8A,972
-hafnia_cli/dataset_cmds.py,sha256=gxUgTUMzZYEvwUdEDHTuTGFge7pqQPkXPKg20v4GGNU,1948
+hafnia_cli/dataset_cmds.py,sha256=JfSj7Cei1T2oYUXP1bpz63uQopgL3R_dMMYnPGGcuU8,2072
 hafnia_cli/dataset_recipe_cmds.py,sha256=OYSmpKL0Wxo1ZSxIGfH6w7pEWoI7CjUTmfIELJSZjGQ,2894
 hafnia_cli/experiment_cmds.py,sha256=_KxsMhbjlkIno1PIMXJ0Omw_PSJi8qi9hmtCUqwcj1M,7970
 hafnia_cli/keychain.py,sha256=bNyjjULVQu7kV338wUC65UvbCwmSGOmEjKWPLIQjT0k,2555
 hafnia_cli/profile_cmds.py,sha256=yTyOsPsUssLCzFIxURkxbKrFEhYIVDlUC0G2s5Uks-U,3476
-hafnia_cli/runc_cmds.py,sha256=38SGajsizpAydawCWL6gwza9NtLugtHfCdnldllwWJI,5016
+hafnia_cli/runc_cmds.py,sha256=7P5TjF6KA9K4OKPG1qC_0gteXfLJbXlA858WWrosoGQ,5098
 hafnia_cli/trainer_package_cmds.py,sha256=hUBc6gCMV28fcAA0xQdXKL1z-a3aL9lMWcVqjvHO1Uo,2326
-hafnia-0.5.0.dist-info/METADATA,sha256=VRy-2ThTt7kczs4uPFU_qeKgiuye1JZ2Pv8VoN1H1e4,19272
-hafnia-0.5.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-hafnia-0.5.0.dist-info/entry_points.txt,sha256=j2jsj1pqajLAiSOnF7sq66A3d1SVeHPKVTVyIFzipSA,52
-hafnia-0.5.0.dist-info/licenses/LICENSE,sha256=wLZw1B7_mod_CO1H8LXqQgfqlWD6QceJR8--LJYRZGE,1078
-hafnia-0.5.0.dist-info/RECORD,,
+hafnia-0.5.2.dist-info/METADATA,sha256=U8Qy_hlNHR-hfgFqsvAkM8dfzS28v9nRI9ne5oXA87o,19312
+hafnia-0.5.2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+hafnia-0.5.2.dist-info/entry_points.txt,sha256=j2jsj1pqajLAiSOnF7sq66A3d1SVeHPKVTVyIFzipSA,52
+hafnia-0.5.2.dist-info/licenses/LICENSE,sha256=wLZw1B7_mod_CO1H8LXqQgfqlWD6QceJR8--LJYRZGE,1078
+hafnia-0.5.2.dist-info/RECORD,,

hafnia_cli/dataset_cmds.py

@@ -3,8 +3,8 @@ from typing import Optional
 
 import click
 
+import hafnia.dataset.hafnia_dataset
 from hafnia import utils
-from hafnia_cli import consts
 from hafnia_cli.config import Config
 
 
@@ -26,6 +26,13 @@ def cmd_list_datasets(cfg: Config) -> None:
 
 @dataset.command("download")
 @click.argument("dataset_name")
+@click.option(
+    "--version",
+    "-v",
+    default="latest",
+    required=False,
+    help="Dataset version to download e.g. '0.0.1' or '1.0.1'. Defaults to the latest version.",
+)
 @click.option(
     "--destination",
     "-d",
@@ -35,20 +42,18 @@ def cmd_list_datasets(cfg: Config) -> None:
 )
 @click.option("--force", "-f", is_flag=True, default=False, help="Flag to enable force redownload")
 @click.pass_obj
-def cmd_dataset_download(cfg: Config, dataset_name: str, destination: Optional[click.Path], force: bool) -> Path:
+def cmd_dataset_download(
+    cfg: Config, dataset_name: str, version: Optional[str], destination: Optional[click.Path], force: bool
+) -> Path:
     """Download dataset from Hafnia platform"""
 
-    from hafnia.platform import datasets
-
-    try:
-        path_dataset = datasets.download_or_get_dataset_path(
-            dataset_name=dataset_name,
-            cfg=cfg,
-            path_datasets_folder=destination,
-            force_redownload=force,
-        )
-    except Exception:
-        raise click.ClickException(consts.ERROR_GET_RESOURCE)
+    path_dataset = hafnia.dataset.hafnia_dataset.download_or_get_dataset_path(
+        dataset_name=dataset_name,
+        version=version,
+        cfg=cfg,
+        path_datasets_folder=destination,
+        force_redownload=force,
+    )
     return path_dataset
 
 
@@ -67,4 +72,5 @@ def cmd_dataset_delete(cfg: Config, dataset_name: str, interactive: bool) -> Non
     datasets.delete_dataset_completely_by_name(
         dataset_name=dataset_name,
         interactive=interactive,
+        cfg=cfg,
     )

hafnia_cli/runc_cmds.py

@@ -38,7 +38,7 @@ def runc():
 @click.pass_obj
 def launch_local(cfg: Config, exec_cmd: str, dataset: str, image_name: str) -> None:
     """Launch a job within the image."""
-    from hafnia.platform.datasets import download_or_get_dataset_path
+    from hafnia.dataset.hafnia_dataset import download_or_get_dataset_path
 
     is_local_dataset = "/" in dataset
     if is_local_dataset:
@@ -48,7 +48,12 @@ def launch_local(cfg: Config, exec_cmd: str, dataset: str, image_name: str) -> N
             raise click.ClickException(f"Dataset path does not exist: {path_dataset}")
     else:
         click.echo(f"Using Hafnia dataset: {dataset}")
-        path_dataset = download_or_get_dataset_path(dataset_name=dataset, cfg=cfg, force_redownload=False)
+        path_dataset = download_or_get_dataset_path(
+            dataset_name=dataset,
+            version="latest",
+            cfg=cfg,
+            force_redownload=False,
+        )
 
     if image_name is None:
         # Load image name from state.json