Data
Data Layer
Data
Data Layer
Understanding the core data management components of PandaAI
Release v3 is currently in beta. This documentation reflects the features and functionality in progress and may change before the final release.
The Data Layer is built around a powerful Semantic Layer that handles data processing and representation, enhancing the comprehension of tabular data from various data sources:
- CSV and Excel files
- SQL databases (PostgreSQL, MySQL)
- Cloud data warehouses (BigQuery, Databricks, Snowflake)
This semantic layer processes your data into one of two formats:
- Materialized DataFrames: Complete datasets loaded into memory for direct manipulation and analysis
- Virtualized DataFrames: Virtual representations of your data that maintain source connections
Both virtualized and materialized dataframes have a .chat() method that allows to interact with them using natural language. The dataframes can also be shared with your team using our Data Platform.
Was this page helpful?