Data Workbench

Managing Your Analysis Scope

Scope Panel Overview

Click the data workbench button on the chat page, the side panel allows you to control which datasets are included in your analysis. Located on the right side of the interface, this panel provides quick access to your selected datasets and their components.

Key Features:

• Search functionality: Use the search bar to quickly find specific datasets, metrics, or dimensions
• Select all option: Toggle all available datasets at once using the "Select all" button
• Real-time selection: Checkboxes next to each dataset allow you to include or exclude models from your analysis scope

Working with Datasets

Exploring Dataset Contents

Each dataset in your scope can be expanded to reveal detailed information:

1. Click the expand arrow (►) next to any dataset name
2. View three tabs:
   • Metrics: Lists all available quantitative measures (e.g., Total Box Office Gross, Average Movie Score)
   • Dimensions: Shows categorical attributes for analysis (e.g., Genre, Release Date)
   • Questions: Displays system-generated suggested questions for this dataset

Data Marketplace

Accessing the Data Marketplace

Click the "+ Browse Dataset" button at the bottom of the data workbench panel to open the Data Marketplace.

Data Marketplace Structure

The Data Marketplace is organized into two main sections:

Personal Data Tab

• My Dataset: Contains datasets you've created or uploaded
• Dataset Management: Each dataset displays:
  • Dataset name and description
  • Metrics and dimensions count
  • Last updated information
  • Quick action buttons

Public Data Tab

• Premium Datasets: Enterprise-grade datasets with verified data sources

Adding Datasets to Scope

Navigate to the Personal Data or Public Data tab in the Data Marketplace,you can browse your available datasets. Click "Add to scope" on any dataset you want to include, then the dataset will immediately appear in your Scope panel

Smart Semantic Features

Smart Semantic automates the creation of a semantic layer (tables, data models, dimensions, metrics) from your uploaded data files (Excel/CSV) using large language models (LLMs). Once processed, you can instantly query the data using natural language to uncover insights—no manual modeling required.

Accessing Smart Semantic

Click the "Smart Semantic" button in the top-right corner of the interface to access advanced dataset management features.

1. Upload Files

   • Supported Formats: .xlsx, .xls, .csv (max 100MB/file).
   • Requirements:
     • Clear headers (Row 1 must contain column names).
     • Consistent data types per column (e.g., avoid mixing text/numbers in one column).
   • How to Upload:
     • Option 1: Chat Interface Upload. Locate the upload icon in the chat input section, after clicking you can upload files.
     • Option 2: Semantic Studio Module. Navigate to Semantic Studio → Click "Smart Semantics" button and upload files.

   ⚠️ Note: Sensitive data? Use pseudonymization before uploading.

2. Submit for Processing

   • Click Submit after uploading.

   • The system validates file structure (e.g., checks for empty cells, encoding issues).

3. Wait for Results

   • Progress Tracking: You can check the status by hovering on the button "AI Model Creation Progress".

   • What Happens:

     • LLMs analyze headers, sample rows, and relationships.
     • Output includes:
       • Tables & Datasets: Logical groupings (e.g., Orders, Customers).
       • Dimensions: Categorical fields (e.g., Product Category, Region).
       • Metrics: Aggregations (e.g., Total Sales = SUM(Revenue)).

   ⏱️ Processing Time: Scales with file size.

Best Practices

Scope Management

• Start Focused: Begin with 2-3 relevant datasets to maintain query performance
• Use Search: Leverage the search functionality when working with many datasets
• Regular Cleanup: Remove unused datasets from your scope to improve performance

Dataset Discovery

• Explore Questions: Use the suggested questions tab to discover analysis possibilities
• Preview Before Adding: Review metrics and dimensions before adding datasets to scope
• Combine Strategically: Mix personal and public datasets for comprehensive analysis

Performance Optimization

• Monitor Scope Size: Keep your active scope manageable for optimal query performance
• Use Select All Sparingly: Avoid selecting all datasets unless necessary for your analysis
• Regular Scope Review: Periodically review and update your active dataset selection

This integrated approach to data model management ensures you have full control over your analysis scope while maintaining easy access to both personal and enterprise-grade datasets through the Data Marketplace.