Giter VIP home page Giter VIP logo

evidencer's Introduction

Evidencer

Screenshot

A chrome extension that lets you scrape, highlight/underline, and export articles you see online as debate cards. Inspired by Cardr.

Based on this template by @NekitCorp.

Built with

Usage

Simple install

  1. Go to releases and download Evidencer.crx.
  2. Open the Extension Management page by navigating to chrome://extensions.
  3. Drag Evidencer.crx on the page and click Add Extension.
  4. Reload any websites that you want to use with the extension.

Unpacked install

  1. Go to releases and download EvidencerUnpacked.zip, and unzip the file.
  2. Open the Extension Management page by navigating to chrome://extensions.
  3. Enable developer mode by clicking the toggle switch next to Developer mode.
  4. Click the Load unpacked button and select the unzipped EvidencerUnpacked folder.
  5. Reload any websites that you want to use with the extension.

Build from source

  1. Clone the repository and build the extension.
# download repo
git clone https://github.com/Ashwagandhae/evidencer.git
cd evidencer
# install dependencies
npm i
# build files to `/dist` folder
npm run build
  1. Open the Extension Management page by navigating to chrome://extensions.
  2. Enable developer mode by clicking the toggle switch next to Developer mode.
  3. Click the Load unpacked button and select the dist folder.
  4. Reload any websites that you want to use with the extension.

Develop

# download repo
git clone https://github.com/Ashwagandhae/evidencer.git
cd evidencer
# install dependencies
npm i
# build files to `/dist` directory
# vite.build.watch rebuilds when modules have changed on disk
npm run dev

evidencer's People

Contributors

ashwagandhae avatar se-julianbauer avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

devflowinc

evidencer's Issues

feature proposal / RFC: adding auto-cut

Hello,

So I think that you tried out auto-cut already on vault.arguflow.ai. The current version is GPT3 thru OpenAI tuned on ~400 prompts. We are going to be fine-tuning Llama 2 with ~270k prompts this weekend to make a much better auto-cut model.

Imo, that should probably exist in a browser extension for cutting cards.

Do you think that evidencer would be a good project to add the auto-cut features into? We do not have much funding, but also want to make sure that if evidencer is the UI for this we don't just leave you hanging on it. The plan is make this free to use.

We only have one requirement that I think would be a tough ask:

  • auth bc running the model is kinda expensive and we can't just let people abuse it (we put up an embedding endpoint and it got abused w/out even publishing on it ๐Ÿ˜“ )

Beyond that, we have some nice-to-have's if you're cool with them:

  • auto-upload to Vault
  • auto-bookmark into a Vault collection
  • modify-text on screen for inline syntax summarization of arbitrary text (when you do NLP summarization - summary.arguflow.gg - you have to deal with the reality of the model hallucinating sometimes. In contrast, syntax summarization makes it easy to spot when hallucination occurs so it's much less risky. We are thinking that this would be useful for summarizing articles, emails, etc. )

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.