llm_aided_ocr

llm_aided_ocr is a local-AI tool - Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs.

Overview

The LLM-Aided OCR Project is an advanced system designed to significantly enhance the quality of Optical Character Recognition (OCR) output. By leveraging cutting-edge natural language processing techniques and large language models (LLMs), this project transforms raw OCR text into highly accurate, well-formatted, and readable documents.

1. PDF to Image Conversion - Function: 'convert_pdf_to_images()' - Uses 'pdf2image' library to convert PDF pages into images - Supports processing a subset of pages with 'max_pages' and 'skip_first_n_pages' parameters

2. OCR Processing - Function: 'ocr_image()' - Utilizes 'pytesseract' for text extraction - Includes image preprocessing with 'preprocess_image()' function: - Converts image to grayscale - Applies binary thresholding using Otsu's method - Performs dilation to enhance text clarity

3. Chunk Creation - The 'process_document()' function splits the full text into manageable chunks - Uses sentence boundaries for natural splits - Implements an overlap between chunks to maintain context

4. Error Correction and Formatting - Core function: 'process_chunk()' - Two-step process: a. OCR Correction: - Uses LLM to fix OCR-induced errors - Maintains original structure and content b. Markdown Formatting (optional): - Converts text to proper markdown format - Handles headings, lists, emphasis, and more

5. Duplicate Content Removal - Implemented within the markdown formatting step - Identifies and removes exact or near-exact repeated paragraphs - Preserves unique content and ensures text flow

llm_aided_ocr is open-source, written primarily in Python, with 2,928 GitHub stars under the Other license. It was last updated on 2026-03-22.

Key capabilities

From the project's documentation:

• PDF to image conversion
• Advanced error correction using LLMs (local or API-based)
• Smart text chunking for efficient processing
• Header and page number suppression (optional)
• Quality assessment of the final output
• Support for both local LLMs and cloud-based API providers (OpenAI, Anthropic)

Install

A quick way to get started (always check the official docs for the latest):

pip install --upgrade pip

How it fits a local-AI stack

llm_aided_ocr runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related local-AI tools in the directory:

• Continue
• Mem0

Sources

• Source code & docs: Dicklesworthstone/llm_aided_ocr

Stats from GitHub, 2026-06-08.