数据集相关

更新时间：2025-11-26

获取数据集列表

使用以下代码可以获取数据集列表。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量（可选，推荐使用）
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息和服务端点
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'  # 百舸AIHC服务地址
AK = os.getenv('AK') or 'your-access-key-id'                # 您的Access Key ID
SK = os.getenv('SK') or 'your-secret-access-key'            # 您的Secret Access Key

# 创建BCE客户端配置
config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)

# 创建 aihc client
aihc_client = AihcClient(config)

# 查询数据集列表
try:
    __logger.info('--------------------DescribeDatasets start--------------------')
    response = aihc_client.dataset.DescribeDatasets()
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为获取数据集列表

获取数据集详情

使用以下代码可以获取数据集详情。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'
AK = os.getenv('AK') or 'your-access-key-id'
SK = os.getenv('SK') or 'your-secret-access-key'

config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)
aihc_client = AihcClient(config)

# 查询数据集详情
try:
    __logger.info('--------------------DescribeDataset start--------------------')
    dataset_id = "d-xxx" # 替换为实际的数据集ID
    response = aihc_client.dataset.DescribeDataset(datasetId=dataset_id)
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为获取数据集详情

获取数据集版本列表

使用以下代码可以获取数据集版本列表。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'
AK = os.getenv('AK') or 'your-access-key-id'
SK = os.getenv('SK') or 'your-secret-access-key'

config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)
aihc_client = AihcClient(config)

# 获取数据集版本列表
try:
    __logger.info('--------------------DescribeDatasetVersions start--------------------')
    dataset_id = "d-xxx" # 替换为实际的数据集ID
    response = aihc_client.dataset.DescribeDatasetVersions(datasetId=dataset_id)
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为获取数据集版本列表

获取数据集版本详情

使用以下代码可以获取数据集版本详情。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'
AK = os.getenv('AK') or 'your-access-key-id'
SK = os.getenv('SK') or 'your-secret-access-key'

config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)
aihc_client = AihcClient(config)

# 获取数据集版本详情
try:
    __logger.info('--------------------DescribeDatasetVersion start--------------------')
    dataset_id = "d-xxx" # 替换为实际的数据集ID
    version_id = "v-xxx" # 替换为实际的数据集版本ID
    response = aihc_client.dataset.DescribeDatasetVersion(datasetId=dataset_id, versionId=version_id)
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为获取数据集版本详情

修改数据集

使用以下代码可以修改数据集。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'
AK = os.getenv('AK') or 'your-access-key-id'
SK = os.getenv('SK') or 'your-secret-access-key'

config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)
aihc_client = AihcClient(config)

# 修改数据集
try:
    __logger.info('--------------------ModifyDataset start--------------------')
    dataset_id = "d-xxx" # 替换为实际的数据集ID
    response = aihc_client.dataset.ModifyDataset(datasetId=dataset_id, name='test-dataset-xxx')
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为修改数据集

删除数据集

使用以下代码可以删除数据集。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'
AK = os.getenv('AK') or 'your-access-key-id'
SK = os.getenv('SK') or 'your-secret-access-key'

config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)
aihc_client = AihcClient(config)

# 删除数据集
try:
    __logger.info('--------------------DeleteDataset start--------------------')
    dataset_id = "d-xxx" # 替换为实际的数据集ID
    response = aihc_client.dataset.DeleteDataset(datasetId=dataset_id)
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为删除数据集

创建数据集

使用以下代码可以创建数据集。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.services.aihc.modules.dataset.dataset_model import DatasetVersionEntry
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'
AK = os.getenv('AK') or 'your-access-key-id'
SK = os.getenv('SK') or 'your-secret-access-key'

config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)
aihc_client = AihcClient(config)

# 创建数据集
try:
    __logger.info('--------------------CreateDataset start--------------------')
    response = aihc_client.dataset.CreateDataset(
        name='sdk-test-dataset-xxx-xxx',
        storageType='PFS',
        storageInstance='pfs-xxx',
        importFormat='FOLDER',
        visibilityScope='ALL_PEOPLE',
        initVersionEntry=DatasetVersionEntry(
            storagePath='/',
            mountPath='/xx'
        )
    )
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为创建数据集

创建数据集版本

使用以下代码可以创建数据集版本。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'
AK = os.getenv('AK') or 'your-access-key-id'
SK = os.getenv('SK') or 'your-secret-access-key'

config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)
aihc_client = AihcClient(config)

# 创建数据集版本
try:
    __logger.info('--------------------CreateDatasetVersion start--------------------')
    dataset_id = "d-xxx" # 替换为实际的数据集ID
    response = aihc_client.dataset.CreateDatasetVersion(
        datasetId=dataset_id, storagePath='/xxx-xxx',
        mountPath='/xxx/xxx', description='Test dataset version'
    )
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为创建数据集版本

删除数据集版本

使用以下代码可以删除数据集版本。

                Python
                
            

                import logging
import os

import dotenv

from baidubce.bce_client_configuration import BceClientConfiguration
from baidubce.auth.bce_credentials import BceCredentials
from baidubce.services.aihc.aihc_client import AihcClient
from baidubce.exception import BceHttpClientError, BceServerError

# 加载环境变量
dotenv.load_dotenv()

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', force=True)
logging.getLogger().setLevel(logging.INFO)
logging.getLogger("baidubce").setLevel(logging.INFO)
__logger = logging.getLogger(__name__)
__logger.setLevel(logging.INFO)

# 配置认证信息
HOST = os.getenv('HOST') or 'https://aihc.bj.baidubce.com'
AK = os.getenv('AK') or 'your-access-key-id'
SK = os.getenv('SK') or 'your-secret-access-key'

config = BceClientConfiguration(credentials=BceCredentials(AK, SK), endpoint=HOST)
aihc_client = AihcClient(config)

# 删除数据集版本
try:
    __logger.info('--------------------DeleteDatasetVersion start--------------------')
    dataset_id = "d-xxx" # 替换为实际的数据集ID
    version_id = "v-xxx" # 替换为实际的数据集版本ID
    response = aihc_client.dataset.DeleteDatasetVersion(datasetId=dataset_id, versionId=version_id)
    print(response)
except BceHttpClientError as e:
    if isinstance(e.last_error, BceServerError):
        __logger.error('send request failed. Response %s, code: %s, msg: %s'
                        % (e.last_error.status_code, e.last_error.code, str(e.last_error)))
    else:
        __logger.error('send request failed. Unknown exception: %s' % e)
            

注意: 根据接口文档去填写具体的访问参数，接口链接为删除数据集版本

在线服务部署相关

常用工具

百度智能云

百度百舸 · AI计算平台

百度百舸 · AI计算平台

数据集相关

获取数据集列表

获取数据集详情

获取数据集版本列表

获取数据集版本详情

修改数据集

删除数据集

创建数据集

创建数据集版本

删除数据集版本