Admin and Configuration Guide
This article explains how administrators configure and manage askEdgi. It describes role-based access control, system settings, API key management, Marketplace administration, workspace data download controls, purge policies, and data reload capabilities.
The article also explains how administrators secure and maintain the askEdgi environment by configuring user access, managing operational settings, controlling data downloads, optimizing workspace storage, and ensuring reliable system performance.
Role Configuration and Access Control
askEdgi integrates with OvalEdge role based access control.
Enabling askEdgi Access
Configuration Steps
Navigate to System Settings.
Search for askedgi.metadata.analytics.role
Select the appropriate role.
Enable askEdgi access.
Save configuration.
Recommended Role Assignments
Metadata Analytics
Governance and discovery teams
Data Analytics
Business analysts and data scientists
Public Edition
Enabled by default via subscription
System Settings Overview
askEdgi includes multiple system-level configurations. These settings control behavior related to AI usage, Marketplace access, usage limits, and operational thresholds. Detailed configuration options are documented separately under askEdgi System Settings and Configurations.
API Key Management for Enterprise SaaS
OvalEdge Provided API Key
Monthly Quota
$100
Alert Threshold
80 %
Hard Stop
100 %
Admin Configuration
Not required
Customer Provided API Key
Configuration Steps
Generate an OpenAI API key
Navigate to AI settings
Select customer provided key
Paste the key for encrypted storage
Save configuration
Administrative Responsibilities
Monitor usage and spend
Rotate keys periodically
Manage budgets
API Key Security Controls
Encryption
Encrypted at rest
Logging
Never logged or displayed
Isolation
Tenant isolated OpenAI projects
Marketplace Management in Public Edition
Recipe Review Workflow
Workflow Sequence
User submits a recipe
Admin notification is generated
Documentation is reviewed
Policy compliance is validated
Execution behavior is verified
Recipe is approved or rejected
Approved recipes are published
Revoking Marketplace Recipes
Recipes may be revoked to:
Remove public visibility
Block new subscriptions
Preserve existing executions
Scheduled Jobs and Automation
Background Jobs
Trial Reminder
Daily
Spend Limit Check
Hourly
Billing Reset
Monthly
Subscription Validation
Daily
Cleanup Service
Daily
Workspace State Management
Connected
Workspace active
Restarting
Workspace reloading
Disconnected
Workspace unavailable
Administrative Recovery Actions
Review workspace logs
Restart workspace
Monitor CPU and memory usage
Upgrade workspace container
Workspace Container Sizes
Standard
Default
Medium
2 times compute and memory
Large
4 times compute and memory
Troubleshooting Operational Issues
Cannot add catalog objects
Verify connector and permissions
Recipe execution failure
Validate datasets and edition compatibility
Slow workspace
Restart workspace, reduce dataset size, upgrade container
Budget exceeded
Review usage, increase quota, switch API key
Security Hardening Controls
Administrators must enforce:
SSO and MFA
Audit log retention and export
Data masking policies
Network segmentation
API key rotation
Encrypted connector credentials
Backup and Disaster Recovery
Catalog Metadata
OvalEdge database backups
Workspace Artifacts
Ephemeral by design
Recipes
Stored and backed up with metadata
Audit Logs
Export before retention expiry
Workspace Data Download Control
askEdgi supports controlled data download across all workspace objects. This capability enables users to download datasets generated or accessed within the workspace while ensuring enforcement of role-based access control and consistent behavior across all interaction points.
Download Availability Across Workspace
Data download is supported for all types of workspace objects, irrespective of their origin. This includes:
Catalog tables
Non-catalog tables
AI-generated datasets
Uploaded files
Derived or transformed datasets created during analysis
Download functionality is consistently available across the following views:
Workspace object list
Analysis results (tabular outputs)
Chat / askEdgi responses where data is rendered
Recipe execution outputs
This ensures a uniform experience for users working across different analysis and interaction modes within askEdgi.
Role-Based Access Control
askEdgi provides controlled access to data download within the workspace using a role-based configuration. This ensures that only authorized users can download data while maintaining consistent behavior across all areas where data is displayed, including analysis outputs, chat responses, and recipe results.
Role Evaluation and Access Control
The system evaluates the roles assigned to the logged-in user before enabling the download capability.
A configurable list of roles is maintained at the system level.
During runtime, the user’s assigned roles are compared against this configured list.
If the user has at least one matching role:
Download functionality is enabled
If the user does not have any matching role:
Download functionality is restricted
This evaluation is performed dynamically for every relevant data view to ensure that access is always aligned with the latest role configuration.
Consistency Across askEdgi Views
The download control is applied uniformly across all areas where data is rendered within askEdgi. This ensures a consistent and predictable user experience.
The same access logic is enforced for:
Workspace object list (tables, files, datasets)
Analysis result tables generated from queries or prompts
Chat / askEdgi responses where tabular data is displayed
Outputs generated from recipe execution
Regardless of how the data is generated (catalog, non-catalog, or AI-generated), the download behavior remains consistent.
User Interface
The visibility and state of the download option are dynamically controlled based on the user’s access.
For users with download permission:
The download option is visible in the UI
The option is enabled and actionable
Users can initiate a download through:
Context menu (three-dot menu), or
Action icons (where applicable in the workspace)
For users without download permission:
The download option is not exposed in the UI (preferred behavior), or
It is displayed in a disabled state with a tooltip indicating restricted access
This ensures that unauthorized users are clearly restricted without ambiguity.
Configuration
Download access is controlled through a system configuration.
Module Group
OVALEDGE_APP
Configuration Type
SECURITY
Key
askEdgi.workspace.download.allowed.roles
Value
<role_list>
Description
Configure which roles are allowed to download data from the askEdgi workspace, including analysis and chat outputs
The configuration defines which roles are authorized to download data from askEdgi, including all analysis outputs and chat-based results.
Purge Policy
When datasets are imported into the workspace from the Data Catalog, Recipes execution, manual upload, or other supported sources. Over time, these datasets can consume significant storage even when they are no longer actively used.
To optimize workspace storage, askEdgi automatically removes inactive data after a configurable retention period. When data is purged, only the physical dataset stored in the workspace is removed. Metadata, catalog references, and chat history remain available.
Retention Configuration
Administrators can configure retention periods using the following system settings:
askedgi.workspace.data.retention_days
Retention period for workspace datasets
30 days
askedgi.workspace.results.retention_days
Retention period for temporary analysis results
5 days
These values can be adjusted to align with organizational standards and governance requirements.
How Purging Works
When a dataset is added to the workspace, the retention timer starts.
The retention period is refreshed when:
The dataset is imported again.
A Recipe execution refreshes the dataset.
The dataset is reloaded from its source.
When the retention period expires:
The dataset is automatically purged from workspace storage.
The object remains visible in the workspace.
A Purged indicator is displayed on the object.
Users cannot perform new analysis on the purged data until it is reloaded.
No notifications are generated when data is purged. Instead, users can identify purged objects through the status indicatordisplayed in the workspace.
Example
A sales table is imported into the workspace on January 1.
The workspace retention period is set to 30 days.
If the table is not refreshed or re-imported, askEdgi automatically removes the physical dataset from workspace storage on January 31.
The Sales Orders object remains visible in the workspace and a Purged indicator appears next to it.
Users must reload the dataset before using it for analysis again.
Data Reload
Data Reload allows users to restore or refresh existing datasets directly from their original catalog source without manually adding them again. When a catalog-sourced dataset is purged, users can click the Reload icon displayed next to the object. askEdgi retrieves the latest available data from the source system and restores it to the workspace.
Reload can also be used to refresh existing datasets when new data becomes available in the source system.
Upon clicking on the Data Reload icon , it displays:
Dataset status
Source connection details
Last imported timestamp
Reload availability
Example:
A user imports the OE Column dataset into the workspace.
Later, new metadata is crawled into the source system. Instead of removing and importing the dataset again, the user clicks Reload.
askEdgi refreshes the dataset using the latest source data, and subsequent analyses use the updated information.
Objects Excluded from Purging and Reload
The following object types are not automatically purged or reloaded:
Local file uploads (CSV, XLSX, JSON, and similar files)
AI-generated outputs
Recipe-generated outputs
Live connection datasets
These objects are not linked to a catalog source and therefore cannot be restored automatically. If they become unavailable, they must be recreated or uploaded again.
Copyright © 2026, OvalEdge LLC, Peachtree Corners, GA USA
Was this helpful?