skitsanos/gemini-ocr
PDF Screenshot OCR Analysis with Google Gemini Pro
This project helps you quickly convert images taken from PDF documents into editable text. It takes screenshots of your PDFs as input and uses Google's advanced AI to extract the text, providing you with a clean text file and a JSON output for further use. This is perfect for anyone needing to get text out of image-based PDFs, like administrative staff, researchers, or data entry specialists.
Use this if you need to automate extracting text from many PDF screenshots for tasks like data analysis, document digitization, or making content accessible.
Not ideal if you need to extract text directly from machine-readable PDFs or if you require highly structured data extraction beyond plain text.
Stars
13
Forks
2
Language
Shell
License
—
Category
Last pushed
Jan 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/skitsanos/gemini-ocr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vsion-x/vizgenie
Turn natural language into Grafana dashboards. Powered by AI, VizGenie auto-generates PromQL...
tanaikech/FileSearchStore-extension
This repository introduces a Gemini CLI extension that integrates File Search feature. This tool...
vojay-dev/gemini-movie-detectives-api
Use Gemini Pro LLM via VertexAI to create an engaging quiz game incorporating TMDB API data
g-hano/Smarty-Gemini
It is a sophisticated agent designed to meet a wide range of user needs through advanced...
ssabrut/gemini-data-analysis
This project leverages Google Gemini Pro, Retrieval-Augmented Generation (RAG), and Streamlit to...