Dicklesworthstone/llm_aided_ocr
Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs
Processes PDFs through a multi-stage pipeline: PDF-to-image conversion, Tesseract OCR, intelligent sentence-boundary chunking with context overlap, then parallel LLM correction via OpenAI/Anthropic APIs or local GGUF models with `llama_cpp`. Includes token management with dynamic adjustment, duplicate paragraph removal, optional header/footer suppression, and built-in quality assessment comparing original OCR against final output.
2,885 stars. Actively maintained with 2 commits in the last 30 days.
Stars
2,885
Forks
206
Language
Python
License
—
Category
Last pushed
Mar 03, 2026
Commits (30d)
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Dicklesworthstone/llm_aided_ocr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
NanoNets/docstrange
Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple...
hashangit/Extract2MD
Extract2MD is a powerful and versatile AI-enabled client-side JavaScript library for extracting...
th1nhhdk/local_ai_ocr
An local, offline (after initial setup), portable OCR software that can process images and PDF...
emcf/thepipe
Get clean data from tricky documents, powered by vision-language models ⚡
langstruct-ai/langstruct
Extract structured data from any content using LLMs.