[docs]def create_dataset(body):
"""
Create a new dataset with the specified name, description, and other details.
:table:Input parameters summary:
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| Field | Input | Type | Description |
+=========================+=======+=======+===============================================================================+
| dataset_name | body | str |The name of the new dataset to create |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| dataset_description | body | str | A description for the new dataset |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| dataset_type | body | str | The type of the new dataset (e.g. Image, Text, Audio, etc.). |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| item_format | body | str |The format of the dataset items (e.g. image/jpeg, text/plain, audio/mpeg, etc.)|
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| metadata | body | dict | A dictionary of metadata to associate with the new dataset. |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| s3IntermediateUrl | body | str | The S3 URL where the dataset items are processed |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| aws_credentials_enabled | body | bool | Whether AWS credentials are enabled for the dataset |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| aws_credentials | body | dict | A dictionary containing AWS credentials for the dataset |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
Sample Request Body
.. code-block:: python
from pprint import pprint
from tensoract.client import Tensoract
# Initialize Tensoract client
dataset_client = Tensoract(api_url="YOUR_API_URL",api_key="YOUR_API_KEY")
body={
"dataset_name": "Test-Dataset-API",
"dataset_description": "This is a test Dataset",
"dataset_type": "Image",
"item_format": "image/tiff",
"metadata": {
"Dataset": "Image Dataset"
},
"s3IntermediateUrl": "s3://************************************",
"aws_credentials_enabled": true,
"aws_credentials": {
"awsKey": "***********",
"awsSecret": "**************",
"awsRegion": "***********",
"awsType": "key"
}
}
pprint(dataset_client.create_dataset(body))
:table:Response summary:
+------------+-----------------+-----------------------------------------------+
| Field | Type | Instructions |
+============+=================+===============================================+
| dataset_id | str | Id of the dataset. |
+------------+-----------------+-----------------------------------------------+
| value | str | Description or message indicating the result. |
+------------+-----------------+-----------------------------------------------+
| status | str | The status of the operation |
+------------+-----------------+-----------------------------------------------+
Sample Response
.. code-block:: python
{
"dataset_id": "e20859abab70f7df3fb0b7c7",
"value": "Dataset updated",
"status": "success"
}
"""
[docs]def get_dataset(dataset_id):
"""
Get a dataset by ID.
:table:Input parameters summary:
+--------------+----------+-------+--------------------------------------------------+
| Field | Input | Type | Description |
+==============+==========+=======+==================================================+
| dataset_id | body | str | The Id of the dataset to retrieve |
+--------------+----------+-------+--------------------------------------------------+
.. code-block:: python
from pprint import pprint
from tensoract.client import Tensoract
# Initialize Tensoract client
dataset_client = Tensoract(api_url="YOUR_API_URL",api_key="YOUR_API_KEY")
# Invoke get_project method
response = dataset_client.get_dataset(dataset_id="9373f3f9d3f1400cfba6ac6a")
pprint(response)
:table:Response summary:
+-------------------------+-------+------------------------------------------------------------------------------+
| Field | Type | Description |
+=========================+=======+==============================================================================+
| dataset_id | str |The Id of the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| dataset_name | str |The name of the new dataset to create |
+-------------------------+-------+------------------------------------------------------------------------------+
| dataset_description | str | A description for the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| dataset_type | str | The type of the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| dataset_versions | list | A list of dictionaries containing version information for the dataset. |
+-------------------------+-------+------------------------------------------------------------------------------+
| item_format | str |The format of the dataset items |
+-------------------------+-------+------------------------------------------------------------------------------+
| metadata | dict | A dictionary containing metadata for the dataset. |
+-------------------------+-------+------------------------------------------------------------------------------+
| aws_credentials_enabled | bool | Whether AWS credentials are enabled for the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| aws_credentials | dict | A dictionary containing AWS credentials for the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| s3IntermediateUrl | str | The S3 URL for intermediate data |
+-------------------------+-------+------------------------------------------------------------------------------+
Sample Response
.. code-block:: python
{
"dataset_id": "9373f3f9d3f1400cfba6ac6a",
"dataset_name": "Test-Dataset-Recipes",
"dataset_type": "PDFOCR",
"dataset_versions": [
{
"id": 0,
"items": 29,
"name": "V.1",
"locked": false,
"created": 1690173205,
"modified": 1690173205
}
],
"dataset_items": 29,
"metadata": {
"Dataset": "Recipes"
},
"company": "60f38299446de8dabe9207e5",
"company_name": "Objectways",
"aws_credentials_enabled": true,
"aws_credentials": {
"awsType": "key",
"awsKey": "********************",
"awsSecret": "****************************************",
"awsRegion": "*********"
},
"s3IntermediateUrl": "*******************************"
}
"""
[docs]def update_dataset(dataset_id,body):
"""
Update Dataset.
:table:Input parameters summary:
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| Field | Input | Type | Description |
+=========================+=======+=======+===============================================================================+
| dataset_id | body | str |The Id of the dataset |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| dataset_name | body | str |The name of the new dataset to create |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| dataset_description | body | str | A description for the dataset |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| dataset_type | body | str | The type of the dataset |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| dataset_versions | body | list | A list of dictionaries containing version information for the dataset. |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| item_format | body | str |The format of the dataset items |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| metadata | body | dict | A dictionary containing metadata for the dataset. |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| aws_credentials_enabled | body | bool | Whether AWS credentials are enabled for the dataset |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| aws_credentials | body | dict | A dictionary containing AWS credentials for the dataset |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
| s3IntermediateUrl | body | str | The S3 URL for intermediate data |
+-------------------------+-------+-------+-------------------------------------------------------------------------------+
Sample Request Body
.. code-block:: python
from pprint import pprint
from tensoract.client import Tensoract
# Initialize Tensoract client
dataset_client = Tensoract(api_url="YOUR_API_URL",api_key="YOUR_API_KEY")
body={
"dataset_name": "Test-Dataset-API",
"dataset_description": "Update dataset",
"dataset_type": "Image",
"item_format": "image/tiff",
"metadata": {
"Dataset": "Image Dataset"
},
"s3IntermediateUrl": "s3://************************************",
"aws_credentials_enabled": true,
"aws_credentials": {
"awsKey": "***********",
"awsSecret": "**************",
"awsRegion": "***********",
"awsType": "key"
}
}
response = dataset_client.update_dataset(dataset_id="85bfac4fb66d935312a373ec",body=body)
pprint(response)
:table:Response summary:
+-------------------------+-------+------------------------------------------------------------------------------+
| Field | Type | Description |
+=========================+=======+==============================================================================+
| dataset_id | str |The ID of the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| dataset_name | str |The name of the new dataset to create |
+-------------------------+-------+------------------------------------------------------------------------------+
| dataset_description | str | A description for the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| dataset_type | str | The type of the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| dataset_versions | list | A list of dictionaries containing version information for the dataset. |
+-------------------------+-------+------------------------------------------------------------------------------+
| item_format | str |The format of the dataset items |
+-------------------------+-------+------------------------------------------------------------------------------+
| metadata | dict | A dictionary containing metadata for the dataset. |
+-------------------------+-------+------------------------------------------------------------------------------+
| aws_credentials_enabled | bool | Whether AWS credentials are enabled for the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| aws_credentials | dict | A dictionary containing AWS credentials for the dataset |
+-------------------------+-------+------------------------------------------------------------------------------+
| s3IntermediateUrl | str | The S3 URL for intermediate data |
+-------------------------+-------+------------------------------------------------------------------------------+
Sample Response
.. code-block:: python
{
"dataset_id": "85bfac4fb66d935312a373ec",
"dataset_name": "Test-Dataset-API",
"dataset_type": "Image",
"dataset_description": "Update Dataset",
"dataset_versions": [
{
"id": 0,
"items": 0,
"name": "V.1",
"locked": false,
"created": 1678442477,
"modified": 1678442477
}
],
"item_format": "image/tiff",
"metadata": {
"Dataset": "Image Dataset"
},
"company": "60f38299446de8dabe9207e5",
"aws_credentials_enabled": true,
"aws_credentials": {
"awsKey": "********************",
"awsSecret": "****************************************",
"awsRegion": "*********",
"awsType": "key"
},
"s3IntermediateUrl": "s3://************************************",
}
"""
[docs]def delete_dataset(dataset_id):
"""
Delete Dataset.
:table:Input parameters summary:
+--------------+----------+-------+--------------------------------------------------+
| Field | Input | Type | Description |
+==============+==========+=======+==================================================+
| dataset_id | body | str | The Id of the dataset to delete |
+--------------+----------+-------+--------------------------------------------------+
.. code-block:: python
from pprint import pprint
from tensoract.client import Tensoract
# Initialize Tensoract client
dataset_client = Tensoract(api_url="YOUR_API_URL",api_key="YOUR_API_KEY")
# Invoke delete_dataset method
response = dataset_client.delete_dataset(dataset_id="8bc05ec26ab161e218a0e842")
pprint(response)
:table:Response summary:
+------------+------------------+---------------------------------------------------------------+
| Field | Type | Description |
+============+==================+===============================================================+
| status | str | The status of the operation |
+------------+------------------+---------------------------------------------------------------+
| value | str | The result or value of the operation |
+------------+------------------+---------------------------------------------------------------+
Sample Response
.. code-block:: python
{
"status": "success",
"value": "dataset deleted"
}
"""
[docs]def list_datasets(dataset_id,dataset_name,active):
"""
List datasets.
:table:Input parameters summary:
+----------------+-------+-------+-----------------------------------------------+
| Field | Input | Type | Description |
+================+=======+=======+===============================================+
| dataset_id | body | str |The Id of the dataset |
+----------------+-------+-------+-----------------------------------------------+
| dataset_name | body | str |The name of the dataset |
+----------------+-------+-------+-----------------------------------------------+
| active | body | bool |Whether to filter datasets by active status |
+----------------+-------+-------+-----------------------------------------------+
Sample Request Body
.. code-block:: python
{
from pprint import pprint
from tensoract.client import Tensoract
# Initialize Tensoract client
dataset_client = Tensoract(api_url="YOUR_API_URL",api_key="YOUR_API_KEY")
# Invoke list_datasets method
response = dataset_client.list_datasets(dataset_id=None,dataset_name=None,active=True)
pprint(response)
}
:table:Response summary:
+-------------------------+------+-------------------------------------------------------------------------------+
| Field | Type | Description |
+=========================+======+===============================================================================+
| dataset_id | str | The Id of the dataset |
+-------------------------+------+-------------------------------------------------------------------------------+
| dataset_name | str | The name of the dataset |
+-------------------------+------+-------------------------------------------------------------------------------+
| dataset_description | str | A description for the dataset |
+-------------------------+------+-------------------------------------------------------------------------------+
| dataset_type | str | The type of the dataset |
+-------------------------+------+-------------------------------------------------------------------------------+
| dataset_versions | list| A list of dictionaries containing version information for the dataset. |
+-------------------------+------+-------------------------------------------------------------------------------+
| company | str | The Id of the company associated with the item. |
+-------------------------+------+-------------------------------------------------------------------------------+
| company_name | str | The name of the company associated with the item. |
+-------------------------+------+-------------------------------------------------------------------------------+
Sample Response
.. code-block:: python
[
{
"dataset_id": "c8a04fbf7c8f95ef8912338f",
"dataset_name": "Test Dataset",
"dataset_type": "Image",
"dataset_versions": [
{
"id": 0,
"items": 1,
"name": "Base version",
"locked": true,
"created": 1657526913,
"modified": 1657526913
},
{
"id": 1,
"items": 59,
"name": "Version 2",
"locked": true,
"created": 1657527052,
"modified": 1657527052
}
],
"company": "60f38299446de8dabe9207e5",
"company_name": "Objectways"
},
{
"dataset_id": "bd35da16cd39283f119454cc",
"dataset_name": "Test Dataset 3",
"dataset_type": "Image",
"dataset_versions": [
{
"id": 0,
"items": 1,
"name": "V.1",
"locked": true,
"created": 1657708086,
"modified": 1657708086
},
{
"id": 1,
"items": 5,
"name": "V.2",
"locked": true,
"created": 1657709319,
"modified": 1657709319
},
],
"company": "60f38299446de8dabe9207e5",
"company_name": "Objectways"
}
]
"""