Go to example tasks
Extract image-only PDF text for AI search
Created by
Dakota Myers
Actor
OCR Citation Chunker
Extract image-only PDF text for AI search. Reusable page-aware JSON example for RAG, search, and agent workflows.
OCR Citation Chunkerskilled_glee/ocr-citation-chunker
Document index
Document title
Page start
Page end
+11 fieldsTextNumberBooleanListObject
Input
Single PDF URL:https://raw.githubusercontent.com/EchoEmpireUtility-bot/ocr-benchmark-fixtures/main/ocr-test-scan.pdf
Chunk size:3000
Chunk overlap:300
Output fields
Document index
Document title
Page start
Page end
Chunk index
Page chunk index
Chunk ID
OCR confidence
OCR quality score
OCR quality tier
OCR quality flags
Character count
Estimated tokens
OCR text
Source URL
Sign up on Apify01
Create your Apify account to access the OCR Citation Chunker.
Start the run02
The Actor will start running based on the input automatically.
Receive the output03
Monitor the progress in real-time. You will be notified as soon as your dataset is complete and ready for review.
Integrate into your workflow04
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow.
