Find Duplicate and Stale RAG Documents

Created by

Michael Olmos

Actor

RAG Dataset Quality Auditor

Audit a realistic help-center RAG sample to catch stale content and exact duplicates before indexing.

Try for free

RAG Dataset Quality Auditorgifted_wagon/rag-dataset-quality-auditor

Quality score

Grade

Document ID

Title

+9 fields

Input

Inline documents

Document ID:help-center-101+1

Source URL:https://example.com/help/reset-password+1

Document title:Reset a customer password+1

Document text:Customers can reset a forgotten password from the sign-in screen. Select Forgot password, enter the verified account email, and submit the request. The service sends a single-use reset link that expires after thirty minutes. Open the link, choose a new password that meets the displayed security requirements, and confirm the change. Existing sessions are signed out after the reset completes. If the message does not arrive, check the spam folder, confirm the address, and wait two minutes before requesting another link. Support agents should never ask customers to share passwords or reset links.+1

Updated at:2026-08-01T00:00:00.000Z+1

Minimum useful words:60

Stale after days:365

Near-duplicate similarity:0.92

Include content preview:false

Output fields

Quality score

Grade

Document ID

Title

Source URL

Words

Issues

Critical

High

Exact duplicate of

Near duplicate of

Similarity

Issue codes

How it works

Sign up on Apify or log in

The RAG Dataset Quality Auditor Actor is ready to run with the inputs already set for "Find Duplicate and Stale RAG Documents". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Find Duplicate and Stale RAG Documents" task

The RAG Dataset Quality Auditor Actor will start running based on the input automatically. You can also change all the input fields, like inline documents, minimum useful words, and more, to match your specific use case.

Receive the "Find Duplicate and Stale RAG Documents" 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 quality score, grade, document id, 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 "Find Duplicate and Stale RAG Documents" task via API.