Audit RAG Chunks Before Vector Database Ingestion

Created by

Michael Olmos

Actor

RAG Dataset Quality Auditor

Find empty, stale, undersized, and duplicate RAG chunks before indexing them in Pinecone, Weaviate, Qdrant, or another vector database.

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:guide-1+3

Source URL:https://example.com/refunds+1

Document title:Refund policy+3

Document text:Customers may request a refund within 30 days of purchase. Requests must include the order number and the email address used at checkout. Approved refunds return to the original payment method within five to ten business days. Digital products that have been substantially consumed may not qualify. Contact support before filing a payment dispute so the team can investigate and document the request.+3

Updated at:2026-08-01T00:00:00.000Z+2

Maximum documents:100

Minimum useful words:50

Maximum useful words:2000

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 "Audit RAG Chunks Before Vector Database Ingestion". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Audit RAG Chunks Before Vector Database Ingestion" 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, maximum documents, and more, to match your specific use case.

Receive the "Audit RAG Chunks Before Vector Database Ingestion" 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 "Audit RAG Chunks Before Vector Database Ingestion" task via API.