Intelligent Media Management:Creating a metadata index

API

L'exemple suivant indexe tous les fichiers du bucket test-bucket et stocke l'index dans le jeu de données test-dataset au sein du projet test-project.

1. Appelez l'opération CreateBinding pour créer une liaison entre le jeu de données et le bucket OSS.

   • Exemple de requête

     {
         "ProjectName": "test-project",
         "URI": "oss://test-bucket",
         "DatasetName": "test-dataset"
     }

   • Exemple de réponse

     {
         "Binding": {
             "Phase": "",
             "ProjectName": "test-project",
             "DatasetName": "test-dataset",
             "State": "Ready",
             "CreateTime": "2022-07-06T07:03:28.054762739+08:00",
             "UpdateTime": "2022-07-06T07:03:28.054762739+08:00",
             "URI": "oss://test-bucket"
         },
         "RequestId": "090D2AC5-8450-0AA8-A1B1-****"
     }

   • Exemple de code (SDK Python)

     # -*- coding: utf-8 -*-
     import os
     from alibabacloud_imm20200930.client import Client as imm20200930Client
     from alibabacloud_tea_openapi import models as open_api_models
     from alibabacloud_imm20200930 import models as imm_20200930_models
     from alibabacloud_tea_util import models as util_models
     from alibabacloud_tea_util.client import Client as UtilClient
     class Sample:
         def __init__(self):
             pass
         @staticmethod
         def create_client(
             access_key_id: str,
             access_key_secret: str,
         ) -> imm20200930Client:
             """
             Use an AccessKey ID and AccessKey secret to initialize a client.
             @param access_key_id:
             @param access_key_secret:
             @return: Client
             @throws Exception
             """
             config = open_api_models.Config(
                 access_key_id=access_key_id,
                 access_key_secret=access_key_secret
             )
             # Specify the endpoint.
             config.endpoint = f'imm.cn-beijing.aliyuncs.com'
             return imm20200930Client(config)
         @staticmethod
         def main() -> None:
             # The AccessKey pair of an Alibaba Cloud account grants full access to all APIs. For better security, we recommend that you use a RAM user for API calls and daily operations.
             # To prevent security risks, do not hard-code your AccessKey ID and AccessKey secret in your project code.
             # This example shows how to read the AccessKey pair from environment variables for authentication. For more information about how to configure environment variables, see https://www.alibabacloud.com/help/document_detail/2361894.html.
             imm_access_key_id = os.getenv("AccessKeyId")
             imm_access_key_secret = os.getenv("AccessKeySecret")
             client = Sample.create_client(imm_access_key_id, imm_access_key_secret)
             create_binding_request = imm_20200930_models.CreateBindingRequest(
                 # Specify the name of the IMM project.
                 project_name='test-project',
                 # Specify the name of the IMM dataset.
                 dataset_name='test-dataset',
                 # Specify the URI of the OSS bucket to bind.
                 uri='oss://test-bucket'
             )
             runtime = util_models.RuntimeOptions()
             try:
                 # Print the API response.
                 response = client.create_binding_with_options(create_binding_request, runtime)
                 print(response.body.to_map())
             except Exception as error:
                 # If an error occurs, print the error message.
                 UtilClient.assert_as_string(error.message)
                 print(error)
     if __name__ == '__main__':
         Sample.main()

2. Facultatif : Appelez l'opération GetBinding pour interroger l'état de la liaison.

   • Exemple de requête

     {
         "ProjectName": "test-project",
         "URI": "oss://test-bucket",
         "DatasetName": "test-dataset"
     }

   • Exemple de réponse

     {
         "Binding": {
             "Phase": "IncrementalScanning",
             "ProjectName": "test-project",
             "DatasetName": "test-dataset",
             "State": "Running",
             "CreateTime": "2022-07-06T07:04:05.105182822+08:00",
             "UpdateTime": "2022-07-06T07:04:13.302084076+08:00",
             "URI": "oss://test-bucket"
         },
         "RequestId": "B5A9F54B-6C54-03C9-B011-****"
     }

     Remarque

     • Si la valeur du paramètre Phase est IncrementalScanning, cela signifie qu'IMM a terminé l'indexation des données existantes dans le bucket OSS et qu'il analyse désormais de manière incrémentielle les nouveaux fichiers.

     • Si la valeur du paramètre State est Running, la liaison est active.

   • Exemple de code (SDK Python 1.27.3)

     # -*- coding: utf-8 -*-
     import os
     from alibabacloud_imm20200930.client import Client as imm20200930Client
     from alibabacloud_tea_openapi import models as open_api_models
     from alibabacloud_imm20200930 import models as imm_20200930_models
     from alibabacloud_tea_util import models as util_models
     from alibabacloud_tea_util.client import Client as UtilClient
     class Sample:
         def __init__(self):
             pass
         @staticmethod
         def create_client(
             access_key_id: str,
             access_key_secret: str,
         ) -> imm20200930Client:
             """
             Use an AccessKey ID and AccessKey secret to initialize a client.
             @param access_key_id:
             @param access_key_id:
             @param access_key_secret:
             @return: Client
             @throws Exception
             """
             config = open_api_models.Config(
                 access_key_id=access_key_id,
                 access_key_secret=access_key_secret
             )
             # Specify the endpoint.
             config.endpoint = f'imm.cn-beijing.aliyuncs.com'
             return imm20200930Client(config)
         @staticmethod
         def main() -> None:
             # The AccessKey pair of an Alibaba Cloud account grants full access to all APIs. For better security, we recommend that you use a RAM user for API calls and daily operations.
             # To prevent security risks, do not hard-code your AccessKey ID and AccessKey secret in your project code.
             # This example shows how to read the AccessKey pair from environment variables for authentication. For more information about how to configure environment variables, see https://www.alibabacloud.com/help/document_detail/2361894.html.
             imm_access_key_id = os.getenv("AccessKeyId")
             imm_access_key_secret = os.getenv("AccessKeySecret")
             client = Sample.create_client(imm_access_key_id, imm_access_key_secret)
             get_binding_request = imm_20200930_models.GetBindingRequest(
                 # Specify the name of the IMM project.
                 project_name='test-project',
                 # Specify the name of the IMM dataset.
                 dataset_name='test-dataset',
                 # Specify the URI of the bound OSS bucket.
                 uri='oss://test-bucket'
             )
             runtime = util_models.RuntimeOptions()
             try:
                 # Print the API response.
                 response = client.get_binding_with_options(get_binding_request, runtime)
                 print(response.body.to_map())
             except Exception as error:
                 # If an error occurs, print the error message.
                 UtilClient.assert_as_string(error.message)
                 print(error)
     if __name__ == '__main__':
         Sample.main()

Ajouter une source de données

2. Cliquez sur le jeu de données test-dataset, sélectionnez l'onglet Data access, puis cliquez sur New Data Source.

3. Sélectionnez le bucket que vous souhaitez lier, puis cliquez sur OK.

   Remarque

   Après l'ajout d'une source de données, IMM crée d'abord des tâches d'extraction de métadonnées pour les fichiers existants dans le bucket. Ensuite, IMM surveille en continu la source de données pour détecter les événements et crée de nouvelles tâches en conséquence. Ces tâches entraînent des frais. Pour plus d'informations, consultez la rubrique Présentation de la facturation. Nous vous recommandons de tester cette fonctionnalité avec un bucket contenant peu de données.

API

Pour indexer manuellement des fichiers spécifiques dans un bucket OSS ou sur PDS, appelez l'opération BatchIndexFileMeta ou IndexFileMeta.

• Appel de l'opération BatchIndexFileMeta

  L'exemple suivant indexe les fichiers OSS oss://test-bucket/test-object1.jpg et oss://test-bucket/test-object2.jpg dans le jeu de données test-dataset au sein du projet test-project.

  • Exemple de requête

    {
      "ProjectName": "test-project",
      "DatasetName": "test-dataset",
      "Files": [
        {
          "URI": "oss://test-bucket/test-object1.jpg",
          "CustomLabels": {
            "category": "People"
          }
        },
        {
          "URI": "oss://test-bucket/test-object2.jpg",
          "CustomLabels": {
            "category": "Pets"
          }
        }
      ],
      "Notification": {
        "MNS": {
          "TopicName": "test-topic"
        }
      }
    }

  • Exemple de réponse

    {
        "RequestId": "0D4CB096-EB44-02D6-A4E9-****",
        "EventId": "16C-1KoeYbdckkiOObpyzc****"
    }

  • Message Simple Message Queue (MNS). Le résultat est renvoyé dans un message MNS. Pour plus d'informations sur le SDK MNS, consultez la rubrique Étape 4 : Recevoir et supprimer des messages.

    {
        "ProjectName": "test-project",
        "DatasetName": "test-dataset",
        "RequestId": "658FFD57-B495-07C0-B24B-B64CC52993CB",
        "StartTime": "2022-07-06T07:18:18.664770352+08:00",
        "EndTime": "2022-07-06T07:18:20.762465221+08:00",
        "Success": true,
        "Message": "",
        "Files": [
            {
                "URI": "oss://test-bucket/test-object1.jpg",
                "CustomLabels": {
                    "category": "People"
                },
                "Error": ""
            },
            {
                "URI": "oss://test-bucket/test-object2.jpg",
                "CustomLabels": {
                    "category": "Pets"
                },
                "Error": ""
            }
        ]
    }

    Remarque

    • Si la valeur du paramètre Success est true, la tâche d'indexation des métadonnées a réussi.

    • Le tableau Files renvoie l'URI et les informations d'erreur pour chaque fichier. Si le champ Error est vide, les métadonnées du fichier ont été indexées avec succès.

  • Exemple de code (SDK Python)

    # -*- coding: utf-8 -*-
    # This file is auto-generated, don't edit it. Thanks.
    import sys
    import os
    from typing import List
    from alibabacloud_imm20200930.client import Client as imm20200930Client
    from alibabacloud_tea_openapi import models as open_api_models
    from alibabacloud_imm20200930 import models as imm_20200930_models
    from alibabacloud_tea_util import models as util_models
    from alibabacloud_tea_util.client import Client as UtilClient
    class Sample:
        def __init__(self):
            pass
        @staticmethod
        def create_client(
            access_key_id: str,
            access_key_secret: str,
        ) -> imm20200930Client:
            """
            Use an AccessKey ID and AccessKey secret to initialize a client.
            @param access_key_id:
            @param access_key_secret:
            @return: Client
            @throws Exception
            """
            config = open_api_models.Config(
                access_key_id=access_key_id,
                access_key_secret=access_key_secret
            )
            # Specify the endpoint.
            config.endpoint = f'imm.cn-beijing.aliyuncs.com'
            return imm20200930Client(config)
        @staticmethod
        def main(
            args: List[str],
        ) -> None:
            # The AccessKey pair of an Alibaba Cloud account grants full access to all APIs. For better security, we recommend that you use a RAM user for API calls and daily operations.
            # To prevent security risks, do not hard-code your AccessKey ID and AccessKey secret in your project code.
            # This example shows how to read the AccessKey pair from environment variables for authentication. For more information about how to configure environment variables, see https://www.alibabacloud.com/help/document_detail/2361894.html.
            imm_access_key_id = os.getenv("AccessKeyId")
            imm_access_key_secret = os.getenv("AccessKeySecret")
            client = Sample.create_client(imm_access_key_id, imm_access_key_secret)
            notification_mns = imm_20200930_models.MNS(
                topic_name='test-topic'
            )
            notification = imm_20200930_models.Notification(
                mns=notification_mns
            )
            input_file_0custom_labels = {
                'category': 'People'
            }
            input_file_0 = imm_20200930_models.InputFile(
                uri='oss://test-bucket/test-object1.jpg',
                custom_labels=input_file_0custom_labels
            )
            input_file_1custom_labels = {
                'category': 'Pets'
            }
            input_file_1 = imm_20200930_models.InputFile(
                uri='oss://test-bucket/test-object2.jpg',
                custom_labels=input_file_1custom_labels
            )
            batch_index_file_meta_request = imm_20200930_models.BatchIndexFileMetaRequest(
                project_name='test-project',
                dataset_name='test-dataset',
                files=[
                    input_file_0,
                    input_file_1
                ],
                notification=notification
            )
            runtime = util_models.RuntimeOptions()
            try:
                # Send the request to start the asynchronous indexing task.
                client.batch_index_file_meta_with_options(batch_index_file_meta_request, runtime)
            except Exception as error:
                # If an error occurs, print the error message.
                UtilClient.assert_as_string(error.message)
        @staticmethod
        async def main_async(
            args: List[str],
        ) -> None:
            # The AccessKey pair of an Alibaba Cloud account grants full access to all APIs. For better security, we recommend that you use a RAM user for API calls and daily operations.
            # To prevent security risks, do not hard-code your AccessKey ID and AccessKey secret in your project code.
            # This example shows how to read the AccessKey pair from environment variables for authentication. For more information about how to configure environment variables, see https://www.alibabacloud.com/help/document_detail/2361894.html.
            imm_access_key_id = os.getenv("AccessKeyId")
            imm_access_key_secret = os.getenv("AccessKeySecret")
            client = Sample.create_client(imm_access_key_id, imm_access_key_secret)
            notification_mns = imm_20200930_models.MNS(
                topic_name='test-topic'
            )
            notification = imm_20200930_models.Notification(
                mns=notification_mns
            )
            input_file_0custom_labels = {
                'category': 'People'
            }
            input_file_0 = imm_20200930_models.InputFile(
                uri='oss://test-bucket/test-object1.jpg',
                custom_labels=input_file_0custom_labels
            )
            input_file_1custom_labels = {
                'category': 'Pets'
            }
            input_file_1 = imm_20200930_models.InputFile(
                uri='oss://test-bucket/test-object2.jpg',
                custom_labels=input_file_1custom_labels
            )
            batch_index_file_meta_request = imm_20200930_models.BatchIndexFileMetaRequest(
                project_name='test-project',
                dataset_name='test-dataset',
                files=[
                    input_file_0,
                    input_file_1
                ],
                notification=notification
            )
            runtime = util_models.RuntimeOptions()
            try:
                # When you run the code, print the API response.
                await client.batch_index_file_meta_with_options_async(batch_index_file_meta_request, runtime)
            except Exception as error:
                # If an error occurs, print the error message.
                UtilClient.assert_as_string(error.message)
    if __name__ == '__main__':
        Sample.main(sys.argv[1:])

• Appel de l'opération IndexFileMeta

  L'exemple suivant indexe le fichier OSS oss://test-bucket/test-object1.jpg dans le jeu de données test-dataset au sein du projet test-project.

  • Exemple de requête

    {
      "ProjectName": "test-project",
      "DatasetName": "test-dataset",
      "File": {
        "URI": "oss://test-bucket/test-object1.jpg",
        "CustomLabels": {
          "category": "People"
        }
      },
      "Notification": {
        "MNS": {
          "TopicName": "test-topic"
        }
      }
    }

  • Exemple de réponse

    {
        "RequestId": "5AA694AD-3D10-0B6A-85B2-****",
        "EventId": "17C-1Kofq1mlJxRYF7vAGF****"
    }

  • Message Simple Message Queue (MNS). Le résultat est renvoyé dans un message MNS. Pour plus d'informations sur le SDK MNS, consultez la rubrique Étape 4 : Recevoir et supprimer des messages.

    {
        "ProjectName": "test-project",
        "DatasetName": "test-dataset",
        "RequestId": "658FFD57-B495-07C0-B24B-B64CC52993CB",
        "StartTime": "2022-07-06T07:18:18.664770352+08:00",
        "EndTime": "2022-07-06T07:18:20.762465221+08:00",
        "Success": true,
        "Message": "",
        "Files": [
            {
                "URI": "oss://test-bucket/test-object1.jpg",
                "CustomLabels": {
                    "category": "People"
                },
                "Error": ""
            }
        ]
    }

    Remarque

    • Si la valeur du paramètre Success est true, la tâche d'indexation des métadonnées a réussi.

    • Le tableau Files renvoie l'URI et les informations d'erreur pour le fichier. Si le champ Error est vide, les métadonnées du fichier ont été indexées avec succès.

  • Exemple de code (SDK Python)

    # -*- coding: utf-8 -*-
    # This file is auto-generated, don't edit it. Thanks.
    import sys
    import os
    from typing import List
    from alibabacloud_imm20200930.client import Client as imm20200930Client
    from alibabacloud_tea_openapi import models as open_api_models
    from alibabacloud_imm20200930 import models as imm_20200930_models
    from alibabacloud_tea_util import models as util_models
    from alibabacloud_tea_util.client import Client as UtilClient
    class Sample:
        def __init__(self):
            pass
        @staticmethod
        def create_client(
            access_key_id: str,
            access_key_secret: str,
        ) -> imm20200930Client:
            """
            Use an AccessKey ID and AccessKey secret to initialize a client.
            @param access_key_id:
            @param access_key_secret:
            @return: Client
            @throws Exception
            """
            config = open_api_models.Config(
                access_key_id=access_key_id,
                access_key_secret=access_key_secret
            )
            # Specify the endpoint.
            config.endpoint = f'imm.cn-beijing.aliyuncs.com'
            return imm20200930Client(config)
        @staticmethod
        def main(
            args: List[str],
        ) -> None:
            # The AccessKey pair of an Alibaba Cloud account grants full access to all APIs. For better security, we recommend that you use a RAM user for API calls and daily operations.
            # To prevent security risks, do not hard-code your AccessKey ID and AccessKey secret in your project code.
            # This example shows how to read the AccessKey pair from environment variables for authentication. For more information about how to configure environment variables, see https://www.alibabacloud.com/help/document_detail/2361894.html.
            imm_access_key_id = os.getenv("AccessKeyId")
            imm_access_key_secret = os.getenv("AccessKeySecret")
            client = Sample.create_client(imm_access_key_id, imm_access_key_secret)
            notification_mns = imm_20200930_models.MNS(
                topic_name='test-topic'
            )
            notification = imm_20200930_models.Notification(
                mns=notification_mns
            )
            input_file_custom_labels = {
                'category': 'People'
            }
            input_file = imm_20200930_models.InputFile(
                uri='oss://test-bucket/test-object1.jpg',
                custom_labels=input_file_custom_labels
            )
            index_file_meta_request = imm_20200930_models.IndexFileMetaRequest(
                project_name='test-project',
                dataset_name='test-dataset',
                file=input_file,
                notification=notification
            )
            runtime = util_models.RuntimeOptions()
            try:
                # When you run the code, print the API response.
                client.index_file_meta_with_options(index_file_meta_request, runtime)
            except Exception as error:
                # If an error occurs, print the error message.
                UtilClient.assert_as_string(error.message)
        @staticmethod
        async def main_async(
            args: List[str],
        ) -> None:
            # The AccessKey pair of an Alibaba Cloud account grants full access to all APIs. For better security, we recommend that you use a RAM user for API calls and daily operations.
            # To prevent security risks, do not hard-code your AccessKey ID and AccessKey secret in your project code.
            # This example shows how to read the AccessKey pair from environment variables for authentication. For more information about how to configure environment variables, see https://www.alibabacloud.com/help/document_detail/2361894.html.
            imm_access_key_id = os.getenv("AccessKeyId")
            imm_access_key_secret = os.getenv("AccessKeySecret")
            client = Sample.create_client(imm_access_key_id, imm_access_key_secret)
            notification_mns = imm_20200930_models.MNS(
                topic_name='test-topic'
            )
            notification = imm_20200930_models.Notification(
                mns=notification_mns
            )
            input_file_custom_labels = {
                'category': 'People'
            }
            input_file = imm_20200930_models.InputFile(
                uri='oss://test-bucket/test-object1.jpg',
                custom_labels=input_file_custom_labels
            )
            index_file_meta_request = imm_20200930_models.IndexFileMetaRequest(
                project_name='test-project',
                dataset_name='test-dataset',
                file=input_file,
                notification=notification
            )
            runtime = util_models.RuntimeOptions()
            try:
                # When you run the code, print the API response.
                await client.index_file_meta_with_options_async(index_file_meta_request, runtime)
            except Exception as error:
                # If an error occurs, print the error message.
                UtilClient.assert_as_string(error.message)
    if __name__ == '__main__':
        Sample.main(sys.argv[1:])

Ajout par lot