Giter Site home page Giter Site logo

urbaninfolab / datapoweredai Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 0.0 17 KB

Data-centric AI training and deployment website developed to make AI more accessible to anyone.

Home Page: https://datapowered.ai

License: GNU General Public License v3.0

ai ai-data data data-ai open custom-ai data-powered data-powered-ai datapoweredai

datapoweredai's Introduction

Making artificial intelligence accessible for everyone

DataPowered AI is a data-centric AI training and deployment website developed to make AI more accessible to anyone. It provides a easy-to-use data upload tool which automatically converts given data to trainable information and trains a custom AI for the user. This website serves to allow anyone access to AI, no matter their time or resources.

Getting Started with DataPowered AI

The website offers an data-centric AI creation and deployment system:

dpai_github_1

To upload files, simply click on "Upload files" or drag and drop your own data. Once finished uploading all data you want to be trained on, click the "Train AI" button and DataPowered Ai will begin training an AI on your data.

Depending on the amount of data, DataPowered AI may take more or less time to train your specific AI. For projects that require more than 1 GB of uploaded files to be trained on, please reach out to us and we will work with you to deploy your AI.

Once your AI is trained, you may edit various options via the Deploy menu before sharing it with the world:

dpai_github_2

You can live test your AI here with the Deploy preview. Try asking questions about your data, adjusting the confidence appropriately along with any other settings, and adjust your model in real-time.

You can adjust your models privacy, confidence threshold, color scheme, and description of the model. Details are provided below.

  • Privacy: When your model is public, anyone is able to access and use your model provided they have the correct URL. When your model is private, your URL will redirect to a login page where the only allowed access user is you. The default value is public, with your accessible URL available on the Share tab.
  • Confidence Threshold: This is a measurement of how accurate the model's responses will be. The lower the confidence, the model will allow answers it is not confident in to pass through. The higher the confidence, the less likely it will be that the answer is wrong. We recommend keeping this value at around 50% for general use.
  • Color Scheme: This is a visual aesthetic for your specific model's endpoint. Customize it to your liking.
  • Description: Other than your AI's name, how will your users to know what your AI is about? You can provide a description of your AI here, what it is trained on, intended questions, etc.

Once you are satisfied with adjusting your AI, you can head over to the Share tab:

dpai_github_3

The share tab provides a live-updating share link to your AI. You can click on the URL to copy it to your clipboard and visit the accessible, conversational front-end of your AI. You can also choose any of the social media options to share it with specific social media platforms.

The share URL will provide a website with your trained AI that looks similar to this:

dpai_github_4

That's it!

It's as simple as that to use. Our goal is to provide accessible AI to anyone, no matter their time or resources, and we hope that you will find this useful. Any data you have questions about is just a query away with DataPowered AI.

Official Examples

Below are some examples created by the DataPowered AI team to showcase a few of the applications it has.

Click any example below to check it out!

Work in Progress

This project is actively being worked on.

Please keep updated by following DataPowered AI's Twitter / LinkedIn, where release announcements will be made.

datapoweredai's People

Contributors

seanhlewis avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.