Validate a RAG dataset before re-indexing

Created by

Sebastián S

Actor

RAG Dataset Linter

Catch broken chunk sequences, missing provenance, duplicates, and overlap before a scheduled RAG re-index replaces your production vectors.

Try for free

RAG Dataset Lintersebastian-actors/rag-dataset-linter

Gate

Action

Source type

Source ID

+9 fields

Input

Minimum tokens:10

Maximum tokens:2000

Near-duplicate similarity:0.95

Maximum adjacent overlap ratio:0.35

Inline records

chunkId:release-0+2

documentId:release-notes+1

sourceUrl:https://example.com/releases+1

chunkIndex:0+2

title:Release notes+2

headingPath

chunkText:Create a repeatable quality gate before each scheduled re-index. Stable chunk identifiers and ordered indexes make regressions visible across ingestion runs.+2

Maximum chunks:1000

Output fields

Gate

Action

Source type

Source ID

Audited

Findings

Errors

Warnings

Exact duplicate rate

Near duplicate rate

Estimated wasted tokens

Truncated

Finished

How it works

Sign up on Apify or log in

The RAG Dataset Linter Actor is ready to run with the inputs already set for "Validate a RAG dataset before re-indexing". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Validate a RAG dataset before re-indexing" task

The RAG Dataset Linter Actor will start running based on the input automatically. You can also change all the input fields, like minimum tokens, maximum tokens, and more, to match your specific use case.

Receive the "Validate a RAG dataset before re-indexing" 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 gate, action, source type, 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 "Validate a RAG dataset before re-indexing" task via API.