Clean and chunk raw scraped text for LLM/RAG pipelines.

This Actor takes messy output from any scraper and returns clean, overlapping chunks ready for embeddings and vector databases.

• Smart HTML/text cleaning
• Semantic-aware chunking (1000 chars with overlap)
• Metadata preservation
• High-volume ready (microtransactions via PPE)

Connect it after any scraper using Actor-to-Actor webhooks or dataset input.

Input example:

{
  "data": [
    {"text": "Your raw scraped content here..."}
  ]
}

Output: One item per chunk with chunk_text.
Pricing

$0.25 per 1,000 chunks processed (very affordable for high volume)

Perfect for AI agents, RAG systems, and automation pipelines.
Made with ❤️ for the AI gold rush.