https://github.com/eniompw/geminiocr

Gemini API for OCR
https://github.com/eniompw/geminiocr

gemini gemini-api gemini-pro-vision llm ocr vercel

Last synced: about 2 months ago
JSON representation

Gemini API for OCR

• Host: GitHub
• URL: https://github.com/eniompw/geminiocr
• Owner: eniompw
• License: mit
• Created: 2024-05-29T09:58:44.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-07-23T07:26:35.000Z (6 months ago)
• Last Synced: 2024-07-23T09:26:30.385Z (6 months ago)
• Topics: gemini, gemini-api, gemini-pro-vision, llm, ocr, vercel
• Language: HTML
• Homepage: https://ocr.eniof.com
• Size: 16.6 KB
• Stars: 1
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Gemini OCR

Simple Demo of using the Gemini API for OCR 

Based on:

* [Gemini API OCR Demo](https://github.com/eniompw/GeminiAPI/blob/main/dev/flask/app-ocr.py)

* [Gemini API](https://github.com/eniompw/GeminiAPI)

* [Gemini File API](https://github.com/google-gemini/cookbook/blob/main/quickstarts/File_API.ipynb)

* [Get API key](https://aistudio.google.com/app/apikey)

## Setup API Key Environment Variable

```

echo 'export GOOGLE_API_KEY=AI...' >> ~/.bashrc

source ~/.bashrc

```

## Install Requirements

` pip install -r requirements.txt `

## Run

` python app.py `