📚

Eprashala

book → text → cleaned chunks → RAG-ready json, entirely in your browser

no. 01 · any language · client-side
pdf · image · txt → ocr → chunks

01 — INTAKE

0 files
📚
Drop book files here, or click to browse
PDF · PNG / JPG (scanned pages) · TXT

    02 — METADATA & SETTINGS

    This key is saved exclusively for this RAG utility and will not sync with your main LMS student database.
    chunking & extraction options
    Downloads language packs on first use. "Force OCR" below ignores DRM locks.
    Uses Gemini Vision to read charts/pictures. Takes extra time per page. Requires API key.
    Off = use embedded text layer when present, OCR only pages that look scanned.
    Idle

    03 — LOG

    Waiting for input…
    ✨ AI Chunk Optimizer
    🗂️

    Add a book, paste some text, or drop a few pages — then hit Process. Extracted chunks will appear here as index cards, ready to feed a RAG pipeline.