Pricing

from $1.20 / 1,000 useful ocr page processeds

Try for free

Go to Apify Store

OCR Citation Chunker

Try for free

Extract text from scanned or image-only PDFs into page-aware JSON chunks for RAG and vector database ingestion, with OCR confidence, page citations, provenance, and stable chunk IDs.

Pricing

from $1.20 / 1,000 useful ocr page processeds

Rating

0.0

(0)

Developer

Dakota Myers

Actor stats

Bookmarked

Total users

Monthly active users

an hour ago

Last modified

Categories

Developer tools

Automation

Source URL

sourceUrl

Required

Original public PDF URL submitted to the Actor.

Type:string

Resolved URL

resolvedUrl

Required

Final PDF URL after HTTP redirects.

Type:string

Source byte size

sourceByteSize

Required

Downloaded PDF size in bytes.

Type:integer

Minimum:0

Document SHA-256

documentSha256

Required

SHA-256 digest of the downloaded PDF bytes.

Type:string

Document ID

documentId

Required

Stable document identifier in the format sha256:.

Type:string

Document index

documentIndex

Required

One-based position of this PDF in the submitted batch.

Type:integer

Minimum:1

Document title

documentTitle

Required

PDF metadata title or a title derived from the source filename.

Type:string

Page start

pageStart

Required

First physical PDF page represented by this chunk.

Type:integer

Minimum:1

Page end

pageEnd

Required

Last physical PDF page represented by this chunk.

Type:integer

Minimum:1

Chunk index

chunkIndex

Required

One-based chunk number within the document.

Type:integer

Minimum:1

Page chunk index

pageChunkIndex

Required

One-based chunk number within the source page.

Type:integer

Minimum:1

Chunk ID

chunkId

Required

Stable SHA-256-based identifier for document, page-local chunk, content hash, and chunking configuration.

Type:string

OCR text

text

Required

Normalized OCR text in this citation-ready chunk.

Type:string

Character count

characterCount

Required

Number of characters in the chunk text.

Type:integer

Minimum:0

Estimated tokens

estimatedTokens

Required

Approximate token count calculated from character length.

Type:integer

Minimum:0

Text SHA-256

sha256

Required

SHA-256 digest of the exact chunk text.

Type:string

Extraction method

extractionMethod

Required

OCR engine used to recover the text.

Type:string

Options:

tesseract-ocr

OCR confidence

ocrConfidence

Required

Mean Tesseract confidence for recognized words on the source page.

Type:number

Minimum:0

Maximum:100

OCR language

ocrLanguage

Required

Tesseract language code used for OCR.

Type:string

OCR DPI

ocrDpi

Required

Rasterization resolution used before OCR.

Type:integer

Minimum:1

OCR word count

ocrWordCount

Required

Recognized word count on the source page.

Type:integer

Minimum:0

OCR quality score

ocrQualityScore

Required

Actor quality score for the source page.

Type:number

Minimum:0

Maximum:100

OCR quality tier

ocrQualityTier

Required

Quality classification derived from OCR diagnostics.

Type:string

Options:

highusablelow

OCR quality flags

ocrQualityFlags

Required

Quality warnings raised for the source page; empty when no flags apply.

Type:string[]

Processed at

processedAt

Required

UTC timestamp when this chunk was written.

Type:string

PDF Citation Chunker

skilled_glee/pdf-citation-chunker

Convert embedded-text PDF reports into page-aware JSON chunks for RAG, semantic search, and vector databases. Preserve page citations, provenance, SHA-256 hashes and stable chunk IDs for idempotent ingestion.

Dakota Myers

PDF OCR Tool — Scanned PDF Text Extraction

junipr/pdf-ocr-tool

Run OCR on scanned PDFs and image-based documents. Extract text by page with language options, confidence scores, and searchable text exports.

junipr

Image to Text OCR - Photos, Screenshots & Scanned PDFs

kantolabs/image-to-text-ocr

Extract text from images, screenshots, photos and scanned PDFs in bulk, with line bounding boxes and confidence scores. Open-source OCR engine - no Google, no API key. $3 per 1,000 pages; failed files are free.

Kanto Labs

PDF to Markdown: Tables, OCR & RAG Chunks

plainfeed/pdf-to-markdown

Convert PDFs from URLs into clean Markdown or text with headings, lists and tables. OCR for scanned pages in 12 languages, and output per document, per page, or as chunks ready for embeddings and RAG.

Plainfeed

PDF OCR Extractor — scanned PDFs to text (Arabic + English)

amanatools/pdf-ocr-extractor

Turn scanned or image-only PDFs into structured text that keeps its reading order: per-block bounding boxes, per-block OCR confidence, column-aware ordering, and a spatial plain-text rendering. Arabic and English OCR built in. Pay per document plus per page.

Dos

Tender RAG Chunker — Text Chunks for LLM

adobeflex/tender-rag-chunker

Chunk tender text for RAG/embeddings with stable ids and metadata.

Yahor

Image OCR Scraper

muhammadafzal/image-ocr-scraper

Extract text from public image URLs with local OCR. Process screenshots, receipts, menus, labels, and scanned documents into structured text and confidence scores.

Muhammad Afzal

Image to Text OCR — Extract Text from Images

junipr/image-to-text

Extract text from images with OCR, confidence scores, language options, page/image metadata, and automation-ready text exports.

junipr

Any URL OCR

caleno/any-url-ocr

Extract text from any image or PDF by URL using Tesseract OCR. Multi-language, PDF page-by-page, no paid OCR API.

Caleno

Subtitle RAG Chunker

skilled_glee/subtitle-rag-chunker

Convert SRT and WebVTT subtitles into timestamped JSON chunks for video transcript RAG, semantic search and vector databases. Preserve cue timestamps, source provenance, stable chunk IDs and SHA-256 hashes.

Dakota Myers