Developed by Muhammad Qasim Aziz | HITS Web SEO Write

Free Standalone Offline Document, PDF & Image OCR Search Engine (Smart Caching)

Index local folders containing PDFs, Word documents, text files, and images with built-in Tesseract OCR. Features intelligent incremental caching for lightning-fast sub-second loading on subsequent runs.

📥 Download Free .exe for Windows

Why Smart Incremental Caching Matters

Scanning thousands of documents and performing OCR on images can take time on the initial run. Our smart incremental caching engine saves your processed index locally, allowing future directory queries to load in milliseconds while automatically detecting and updating only modified or new files.

  • Lightning-Fast Subsequent Loads: Instantly bypasses redundant text extraction and OCR steps for unchanged files.
  • Smart Delta Updates: Automatically scans modification timestamps (`mtime`) and only processes newly added or edited files.
  • Built-in Tesseract OCR & Vector Search: Scans text inside PDFs, Word docs, and raster images (.jpg, .png, .gif) offline with high precision.

Key Features of Our Tool

  • 100% Offline & Private: Keep confidential client data and business documents secure on your machine without cloud exposure.
  • Portable Tesseract Engine: Includes a fully integrated OCR binary structure so it runs smoothly on any Windows PC without external setups.
  • Ranked Excerpt Display: Shows match confidence percentages, exact file paths, and context text previews.

Step-by-Step Usage Manual

Follow this quick guide to search your local repositories:

Step 1: Download the Application

Click the download button above to retrieve rag_search_engine.exe from our GitHub repository.

Step 2: Select Document & Image Folder

Click "📁 Select Folder to Index" and choose any directory containing your documents or image files.

Step 3: Load / Update Index

Click "⚡ Load / Update Index". The app loads cached data instantly in seconds, scanning only modified files.

Step 4: Search Wording or Filenames

Type keywords or natural language queries into the input bar and click "🔍 Search Repository" to instantly find matching files!

Frequently Asked Questions (FAQ)

How does the smart caching system work?

The app saves a hidden `.index_cache.pkl` file inside your selected folder. On future runs, it checks file modification timestamps to load pre-extracted text and OCR results instantly.


Do I need an internet connection or external software?

No. The application is 100% self-contained and operates entirely offline on Windows.