Build Source-Linked RAG Chunks from a Sitemap

Created by

Tim Zinin

Actor

RAG Dataset Builder

Convert an authorized public sitemap into bounded text chunks with stable IDs, source evidence, confidence, crawl gaps, and reconciliation.

Try for free

RAG Dataset Builderzinin/sitemap-to-knowledge

Stable chunk ID

Site

Source page

Knowledge text

+24 fields

Input

Domains / websites(required):docs.apify.com

Max concurrency:1

Output fields

Stable chunk ID

Site

Source page

Knowledge text

Content SHA-256

Chunk #

Chars

Approx. tokens

Summary

Confidence basis

Confidence

Confidence band

Confidence risks

Recommended action

Priority

Observed at

Evidence freshness

Data gaps

Negative signals

Partial

Partial reasons

Crawl completeness

Source evidence

Failure type

Retryable

Failure diagnostics

Delivery and billing

Automation safe

How it works

Sign up on Apify or log in

The RAG Dataset Builder Actor is ready to run with the inputs already set for "Build Source-Linked RAG Chunks from a Sitemap". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Build Source-Linked RAG Chunks from a Sitemap" task

The RAG Dataset Builder Actor will start running based on the input automatically. You can also change all the input fields, like domains / websites and max concurrency, to match your specific use case.

Receive the "Build Source-Linked RAG Chunks from a Sitemap" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as stable chunk id, site, source page, and more.

Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Build Source-Linked RAG Chunks from a Sitemap" task via API.