surface↓extraction↓parse_date_llm
Extractionscalar · returns json

PARSE_DATE_LLM

LLM-backed date parsing (escape hatch for PARSE_DATE)

Per-row — runs once for each row.

extractionllmllm-escape-hatchdate

Syntax

PARSE_DATE_LLM({{ date_text }})
PARSE_DATE_LLM({{ date_text }}, '{{ prefer_format }}')

Arguments

nametypedescription
date_textVARCHAR—
prefer_format(optional)VARCHAR—

About

LLM-backed escape hatch for date parsing. Use when the canonical `dateutil` + `dateparser` path (PARSE_DATE) misses a format — typically very unusual or domain-specific date representations, non-Western calendars, or heavily ambiguous text where the LLM's world knowledge helps. For standard formats (ISO, US, EU, natural language in Western languages), prefer PARSE_DATE — it is orders of magnitude faster, fully deterministic, and covers 99% of real-world date strings.

Examples

LLM escape hatch parses written dates

SELECT
  parse_date_llm ('March 15th, 2024')

Nearby rabbit holes

same domain
scalar

CRAWL_BATCH

Crawl a website and extract structured data from each page (via Firecrawl)

extractionexternal-apiurl
scalar

EXTRACT

Extract specific information from unstructured text (zero-shot NER)

extractionnlispecialist-zootext
scalar

EXTRACT_LLM

LLM-backed extraction (escape hatch for EXTRACTS)

extractionllmllm-escape-hatchtext
scalar

EXTRACT_STRUCTURED

Extract structured fields from text per a user-supplied schema

extractionllmtext
aggregate

MERGE_TIMELINES

Merge multiple timelines into unified chronological sequence

extractionllmjson
scalar

PARSE

Extract information from text using natural-language instructions

extractionllmtext
Climb back to The Looking Glass