process_csv
Process CSV files with filtering, aggregation, and pagination to handle large datasets while optimizing token usage for data analysis workflows.
Instructions
Process CSV files efficiently with filters, groupby aggregation, and pagination. Use offset for large files (>10K rows) to achieve 99% token savings.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to CSV file | |
| filter_expr | No | Filter expression (e.g., "price > 100") | |
| columns | No | Columns to select | |
| limit | No | Maximum rows to return | |
| offset | No | Skip first N rows before returning results (pagination) | |
| aggregate_by | No | Column to aggregate by | |
| agg_func | No | Aggregation function | |
| response_format | No | summary = stats + 5 sample rows (for humans), full = all rows in data array (for processing) | summary |