Skip to content

LynxGeekNYC/AI-Tools

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI-Tools

Various AI tools that I use for ChatGPT / OpenAI.

PDF-JSON.PY

Script that extracts data from PDF files in order to be used for OpenAI / ChatGPT Analyzation and Processing.

Was this script helpful to you? Please donate:

I put a lot of work into these scripts so please donate if you can. Even $1 helps!

C++ OCR to JSON for Law (/ocr/law/2025)

C++ Framework for Law Practice that analyzes all data (Transcripts, Medical Records, Police Reportd, etc), efficiently exports all data to a JSON to be able to submit to OpenAI or any other LLM for Analysis, etc. This script is designed to be efficient to minimize token usage, rather than uploading entire PDF's, etc.

C++ OCR to JSON

Instructions

Install Dependencies:

Install Tesseract and Leptonica: sudo apt install tesseract-ocr libtesseract-dev libleptonica-dev Install Poppler: sudo apt install libpoppler-dev

Install nlohmann/json header file via package manager or manually.

Build the Script:

bash g++ -o ocr_extractor ocr_extractor.cpp -ltesseract -llept -lpoppler-cpp -std=c++17 Run the Script:

bash ./ocr_extractor output.json file1.pdf file2.jpg file3.png

Output:

Extracted data will be saved in output.json.

PayPal: [email protected]

CashApp / Venmo: LynxGeekNYC

BitCoin: bc1q8sthd96c7chhq5kr3u80xrxs26jna9d8c0mjh7

About

Various AI tools that I use for ChatGPT / OpenAI.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published