Text Cleaner For RAG
Pricing
from $3.90 / 1,000 item checkeds
Go to Apify Store
Text Cleaner For RAG
Clean web text for RAG by removing boilerplate, normalizing whitespace, and producing chunk-ready text.
Text Cleaner For RAG
Pricing
from $3.90 / 1,000 item checkeds
Clean web text for RAG by removing boilerplate, normalizing whitespace, and producing chunk-ready text.
Target maximum characters per output chunk.
Approximate character overlap between adjacent chunks.
Minimum useful chunk length unless the document is shorter.
Remove common web boilerplate such as cookie, newsletter, social, and navigation lines.
Drop repeated normalized lines inside each document.
Convert markdown links to visible text.
Keep markdown heading markers for downstream retrieval context.
Maximum documents to process.
Maximum cleaned chunks emitted across all documents.
Maximum UTF-8 bytes cleaned from each document.
Write cleaned markdown, chunks JSON, and summary reports to the key-value store.
Validate input and write a dry-run summary without PPE charges or dataset output.
