# Changelog of Image to Text & Scanned PDF OCR to RAG Chunks (`mmdincer/image-ocr-rag`) Actor

- **URL**: https://apify.com/mmdincer/image-ocr-rag/changelog.md
- **Full Actor documentation**: https://apify.com/mmdincer/image-ocr-rag.md

## Changelog

### 1.0.1 (2026-11-04)

- Repeated page headers, footers and page numbers are left out of the text and the chunks when the same short line sits in the margin of at least half the pages. A single page is unchanged. The page is still charged: the OCR ran. No price or event-name change.

### 1.0.0 (2026-11-04)

First release.

- OCR of images (JPEG, PNG, WebP, GIF, BMP, TIFF) and scanned PDFs with Tesseract 5, 37 languages, up to 4 per run.
- Document rows with text, Markdown, token count and confidence; chunk rows with page ranges, token counts and a per-chunk confidence and `lowConfidence` flag.
- Automatic rotation fix, EXIF orientation, contrast clean-up and enlargement of small images.
- Pay per event: `ocr-page` per page with text; blank, unreadable and failed pages are free.
- Reads links from another Apify dataset (`datasetId`).
- Store title and opening lead with the search phrases "image to text" and "scanned PDF OCR".