Recued
Menu
← Back to recipes

Crawl a small website section with Tavily

by recued-core v1 10 views

Use “Crawl a small website section with Tavily” in Recued. Read a deliberately limited section of one website with Tavily and return clean page content. Defaults are conservative: one level, ten links per level, at most 20 pages, basic extraction, no images, and no external domains.

How it works 6 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (6 steps)
url trim
Trim whitespace from setting url
crawl ?
pages default
Apply default
page_count count
Count items in pages
page_table to_table
Format results as a data table
summary to_summary
Format results as a summary card
Settings 10 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

url setting =
limit setting = 20
format setting = markdown
tavily setting =
max depth setting = 1
max breadth setting = 10
select paths setting =
exclude paths setting =
extract depth setting = basic
timeout seconds setting = 120

Trust & control

What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.

Permissions it requires

Read your Tavily connection
Declared by the recipe — Recued grants these at install, where you review them before approving.

About

Tags

tavily tavilycrawlwebsiteextractionragpack:tavily

Details

6 steps 10 configurable settings recipe_id: crawl-site-tavily