Workspace
Within each workspace, you can create and manage Projects.
The XAI object instance has all the necessary methods to interact with your workspaces. You can use the following functions to create a new workspace, list all existing workspaces and select a particular workspace.
# creating a new workspapce name
workspace = aryaxai.create_workspace('workspace name')
# create a new workspace with custom server configurations
# for avalilable custom server configuration check xai.available_custom_servers()
# workspace = aryaxai.create_workspace('workspace name', "t3.medium")
# creating a new workspapce name
workspace = aryaxai.create_workspace('workspace name')
Create a new workspace with custom server configurations:
# for avalilable custom server configuration check xai.available_custom_servers()
workspace = aryaxai.create_workspace('workspace name', "t3.medium")
NOTE: While anyone can create a workspace, only the Organization admin or owner can view all workspaces within the organization. You can invite users directly to your workspace or project without needing to assign them as the owner or admin of the organization.
To update workspace instance type:
workspace.update_server('t3.medium)
List all workspaces available:
# list all workspaces available
aryaxai.workspaces()
Select a workspace name:
# select a workspace name
workspace = organization.workspace('sdk-testing')
Create a new workspace with dedicated server configurations
# start custom server of workspace
# workspace.start_server()
# stop custom server of workspace
# workspace.stop_server()
# update custom server of workspace
# workspace.update_server('t3.medium')
To fetch available serverless options
aryaxai.available_batch_servers()
Additional functions:
Delete or rename workspace:
# Deleting Workspace
#workspace.delete_workspace()
# rename workspace
# workspace.rename_workspace('new_workspace_name')
Project
A project represents the ML use case you want to solve eg. Loan status prediction, house sale prediction.
AryaXAI supports multiple project types tailored for different data modalities. When creating a new project, users can choose from the following data types based on their specific requirements:
1. Tabular
Tabular data projects focus on structured datasets that are typically stored in spreadsheets or relational databases. These datasets consist of rows and columns containing numerical or categorical data.
2. Image
Image data projects specialize in processing visual information, enabling tasks such as image categorization, segmentation, and image generation.
3. Text
Text data projects process textual information to perform tasks such as text classification, semantic understanding and content generation.
Create Tabular Project
To create a new project, users must specify the data modality during the project creation process:
project=workspace.create_project('Project1',modality='tabular',project_type=
'classification')
# create project in workspace
workspace.create_project('Loan Status Prediction')
# create project name
project = workspace.create_project('project_name')
# create project with custom server
# workspace.create_project('Loan Status Prediction', 't3.medium')
Create project in a workspace:
# create project in workspace
workspace.create_project('Loan Status Prediction')
To create project name, use the following function:
project = workspace.create_project('project_name')
Create project with custom server:
# workspace.create_project('Loan Status Prediction', 't3.medium')
Create Image Project:
Create an image project in workspace:
workspace.create_project('Cifar10',modality='image', project_type='classification')
Create image project with custom server
workspace = organization.create_workspace('Images','t3.medium')
Manage projects:
List of projects:
Select a project name:
project = organization.workspace('workspace_name').project('project_name')
Delete or rename projects:
# delete project
project.delete_project()
# rename project
project.rename_project('new_project_name')
Manage custom server of projects:
Start custom server of a project:
Stop custom server of project:
Update custom server of project:
# project.update_server('t3.medium')
Manage Text projects:
Use the following function to enable the creation of a Text modality project:
project=workspace.create_project('Text Model',modality='text', project_type= 'chat')
To check for available text models
project.get_available_text_models()
To initialize text models
project.initialize_text_model('meta-llama/Llama-3.2-1B')
To generate text case by passing various parameters
project.generate_text_case(model_name= "meta-llama/Llama-3.2-1B-Instruct", model_type= "llm", unique_identifier="682ef0be61e2652db4345747",prompt= "What is the capital of Uganda?", tag="training", explainability_method= ["DLB"], explain_model= False, instance_type="gova-2")
