RAG & Data Prep

Chunk text, deduplicate datasets, and convert files into formats ready for retrieval augmented generation and fine-tuning.

Text Chunker

Split long documents into token-aware chunks for embeddings and RAG.

Convert chat transcripts into clean JSONL files ready for OpenAI or Gemini fine-tunes.

Turn CSV rows into properly formatted chat messages for fine-tuning.

Remove exact and near-duplicate examples from a fine-tuning dataset.

Split long markdown docs by heading hierarchy for clean RAG ingestion.

Pull clean text out of PDFs in your browser — no upload, no server.

Clean any HTML page into RAG-ready markdown with one click.

Format citations as APA, MLA, or BibTeX for AI research papers.