SPB Git forge

spb/ai-atlas

Public
41commits 1branches 0releases
4.6 MBsize
maindefault branch
12 days agolast push
HTML 77.2% TypeScript 10.5% Python 9.6% JavaScript 2.5%
1.1 KB · 33 lines python
Raw Blame History
1"""Deterministic extraction (Stage 1): DOM, metadata, JSON-LD, embedded JSON, feeds, sitemaps, markdown, tables, numbers, dates.2Always run before any LLM."""3from aiatlas.sdk.extract.dates import parse_date, parse_datetime4from aiatlas.sdk.extract.feeds import FeedItem, parse_feed5from aiatlas.sdk.extract.html import HtmlDoc, parse_html6from aiatlas.sdk.extract.markdown import MarkdownDoc, parse_front_matter, parse_markdown7from aiatlas.sdk.extract.numbers import (8           parse_context_length,9           parse_money_per_mtok,10           parse_param_count,11           parse_percent,12           parse_tokens,13)14from aiatlas.sdk.extract.sitemap import parse_sitemap1516__all__ = [17           "FeedItem",18           "HtmlDoc",19           "MarkdownDoc",20           "parse_context_length",21           "parse_date",22           "parse_datetime",23           "parse_feed",24           "parse_front_matter",25           "parse_html",26           "parse_markdown",27           "parse_money_per_mtok",28           "parse_param_count",29           "parse_percent",30           "parse_sitemap",31           "parse_tokens",32]33