Skip to content

Extracting text from images (jpg, png as well as pdf) using AI (Gemini & Llava)

Notifications You must be signed in to change notification settings

pbreedt/ai-text-extract

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ai-text-extract

A package to wrap services from different cloud providers in a common, simplified interface

General info

The main purpose of this package was to explore the SDK's of different AI providers.
There are many other possibile tools to also perform this task, like these

Technologies

  • Go - version 1.22

SDK's currently covered:

Setup

Like with all Go modules, you can simply "go get" it.
go get github.com/pbreedt/ai-text-extract

This package is not very flexible like taking CLI params (mainly because it is just a simple proof-of-concept and the incompatible model names between SDK's)

Google generative AI

  1. Next step creates a new key and project in your Google Cloud account
  2. Obtain an API key, see this link
  3. export GOOGLE_AI_API_KEY=your_api_key

Google Vertex AI

  1. Login to GCP console
  2. Create service account
  3. Create service account key (storing key in /path/to/sa-json.json file)
  4. export GOOGLE_APPLICATION_CREDENTIALS=/path/to/sa-json.json
  5. export GOOGLE_PROJECT_ID=your_project_id
  6. export GOOGLE_REGION=google_region

Ollama

  1. Download and install from the Ollama website
  2. Run command 'ollama run llava'

Status

Project is: in progress

Credits

Thanks to ritaly for a quick readme template

Contact

Created by @pbreedt

About

Extracting text from images (jpg, png as well as pdf) using AI (Gemini & Llava)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages