airbyte

import airbyte as ab import os # Configure a source (e.g., source-faker for demo purposes) # For real connectors, replace 'source-faker' with the actual connector name # and 'config' with your credentials/connection details. # Use os.environ.get for sensitive information. source = ab.get_source( "source-faker", config={ "count": 1000, # Number of records to generate "seed": 42 # Seed for reproducible data generation }, install_if_missing=True # Automatically install the connector if not found ) # Verify configuration and connection check_result = source.check() if check_result.status == "succeeded": print("Source connection successful!\n") else: print(f"Source connection failed: {check_result.message}\n") exit() # Select all available streams from the source source.select_all_streams() # Read data from the source into PyAirbyte's internal cache (DuckDB by default) read_result = source.read() # Access a specific stream and convert it to a Pandas DataFrame # Replace 'users' with the actual stream name from your source users_df = read_result["users"].to_pandas() print("First 5 records from 'users' stream:") print(users_df.head())