fm_load_dataset
Load FileMaker records into a named dataset for fast analytics. Fetch records once, store as pandas DataFrame, then run multiple analyses without extra database round trips.
Instructions
Load FileMaker records into a named dataset for fast analytics.
Fetches records from FM and stores them as a pandas DataFrame in session memory. Load once, then run multiple analyses with fm_analyze — no additional FM round trips needed.
Auto-paginates if more than 10,000 records match. Loading a dataset with an existing name replaces it (refresh).
IMPORTANT: Call fm_get_schema(table) first to discover field names.
Args: name: Your chosen identifier for this dataset (e.g., "inv25", "customers"). table: FM table to query (see fm_list_tables for available tables). filter: OData $filter expression. Use exact field names from get_schema. Example: "ServiceDate ge 2025-01-01 and ServiceDate lt 2026-01-01" select: Comma-separated fields to fetch. Leave empty for all fields. TIP: Select only the fields you need — reduces memory and speeds loading. Example: "Technician,Region,Amount,ServiceDate"
Returns: Summary with row count, columns, and memory usage.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| table | Yes | ||
| filter | No | ||
| select | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |