Crawl a website and extract structured data from each page (via Firecrawl)
Per-row — runs once for each row.
| name | type | description |
|---|---|---|
| url | VARCHAR | Starting URL or domain |
| schema_json | VARCHAR | JSON Schema for per-page extraction |
| limit(optional) | INTEGER | Max pages to crawl |
| prompt(optional) | VARCHAR | Optional extraction guidance prompt |
Extract specific information from unstructured text (zero-shot NER)
LLM-backed extraction (escape hatch for EXTRACTS)
Extract structured fields from text per a user-supplied schema
Merge multiple timelines into unified chronological sequence
Extract information from text using natural-language instructions
Parse, validate, or transform patterned strings using plain-English instructions
Crawl a website and extract structured data from each page (via Firecrawl)
Per-row — runs once for each row.
| name | type | description |
|---|---|---|
| url | VARCHAR | Starting URL or domain |
| schema_json | VARCHAR | JSON Schema for per-page extraction |
| limit(optional) | INTEGER | Max pages to crawl |
| prompt(optional) | VARCHAR | Optional extraction guidance prompt |
Extract specific information from unstructured text (zero-shot NER)
LLM-backed extraction (escape hatch for EXTRACTS)
Extract structured fields from text per a user-supplied schema
Merge multiple timelines into unified chronological sequence
Extract information from text using natural-language instructions
Parse, validate, or transform patterned strings using plain-English instructions