sarvcrawl

n8n community node for SarvCrawl — crawl sites, parse documents, and run keyword or hybrid semantic search over your knowledge bases

Package Information

Released: 1 mo ago
Downloads: 0 weekly / 0 monthly
Latest Version: 1.0.1
Author: Sarv Webs Pvt. Ltd.

Available Nodes

Documentation generating…

SarvCrawl icon
SarvCrawl
Interact with SarvCrawl — manage knowledge bases, scrape URLs, crawl sites, upload documents and search

Documentation

n8n-nodes-sarvcrawl

Crawl the web and search your own knowledge bases, from an n8n workflow.

An n8n community node for SarvCrawl —
scrape a page, crawl a site, then query it by keyword or by meaning, with no code
in between.

npm
License
n8n

Install · Credentials · Operations · Example

📦 Install

In n8n (self-hosted): Settings → Community Nodes → Install, then
enter:

n8n-nodes-sarvcrawl

Manually:

npm install n8n-nodes-sarvcrawl

Restart n8n, and SarvCrawl appears in the node panel.

[!NOTE]
Community nodes run on self-hosted n8n. On n8n Cloud they are available on
plans that permit them — check your plan before installing.

🔑 Credentials

Create a SarvCrawl API credential:

Field Value
API Key Your key from crawl.sarv.com — 1 billion free tokens on sign-up, no card
Base URL https://crawl.sarv.com — the default; set your own host to self-host

[!IMPORTANT]
Base URL is the origin, not the API prefix. The REST API lives at /api/…
and the node adds that itself, so a value ending in /api makes every call
404.

🧰 Operations

Three resources, thirteen operations.

Resource Operations
Knowledge Base Create · Get · Get All · Delete
Job Scrape URL · Crawl Website · Get Status · Get All Jobs · Cancel
Search Search (BM25 keyword) · Semantic Search (hybrid embedding + BM25)

Semantic Search is what you want for questions phrased in natural language;
Search for exact terms, identifiers and error codes.

Crawl takes the bounds you would expect — max depth, page limit and a path
exclude list — so a run cannot wander off across a whole domain.

🔁 Example

A workflow that keeps a knowledge base current and answers questions from it:

Schedule Trigger (daily)
  → SarvCrawl: Job → Crawl Website     (kb_id, url, max depth 2, limit 50)
  → Wait                                (crawling is asynchronous)
  → SarvCrawl: Job → Get Status         (poll until completed)
  → SarvCrawl: Search → Semantic Search (your question)
  → Slack / Email / AI Agent

Ingest is asynchronous: Scrape URL and Crawl Website return a job id
immediately, so poll Get Status before you search. Search operations return
straight away.

📄 License

Apache-2.0. The full text ships in the package as LICENSE, and is also at
apache.org/licenses/LICENSE-2.0.

Discussion