Detect duplicate embedding spend

Find exact duplicate RAG chunks and excessive overlap, estimate wasted embedding tokens, and stop redundant vectors before indexing.

Try for free
RAG Dataset Linter
RAG Dataset Lintersebastian-actors/rag-dataset-linter
Gate
Action
Source type
Source ID
+9 fields
Text
Number
Boolean
List
Object

Input

Minimum tokens:5
Maximum tokens:2000
Near-duplicate similarity:0.95
Maximum adjacent overlap ratio:0.35
Inline records
chunkId:pricing-0+2
documentId:pricing+2
sourceUrl:https://example.com/pricing+2
chunkIndex:0+2
title:Pricing+2
headingPath
chunkText:Embedding duplicate chunks wastes tokens and creates redundant vectors that can crowd retrieval results.+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 Apify01

Create your Apify account to access the RAG Dataset Linter.

Start the run02

The Actor will start running based on the input automatically.

Receive the output03

Monitor the progress in real-time. You will be notified as soon as your dataset is complete and ready for review.

Integrate into your workflow04

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow.

Image

Integrate Actor directly into your workflow

Choose from one of 100+ integration options we provide or integrate via API

Webhook

Webhook

n8n

n8n

Make

Make

Zapier

Zapier

Airbyte

Airbyte

Keboola

Keboola

IFTTT

IFTTT

Hubspot

Hubspot

GDrive

GDrive

Gmail

Gmail

Apify MCP

Apify MCP

GitHub

GitHub

Slack

Slack

LangChain

LangChain

LlamaIndex

LlamaIndex

Flowise

Flowise

Pinecone

Pinecone

OpenAI

OpenAI

Mastra

Mastra

Clay

Clay