Light

schibsted / sum Goto Github PK

View Code? Open in Web Editor NEW

3.0 6.0 1.0 460 KB

Sum, a powerful tool for enhancing your articles with the help of ChatGPT.

License: Apache License 2.0

JavaScript 1.43% TypeScript 98.23% CSS 0.33%

chatgpt nextjs nrk openai whisper vg tailwindcss

sum's Introduction

Sum

Sum, a powerful tool for enhancing your articles with the help of ChatGPT.

Developed in collaboration with NRK and VG during an innovation day event.

Start Page	Result Page

Getting Started

First, install the dependencies:

npm install

Next, configure the environment variables. Refer to the section below for details.

After setting up the environment variables, run the development server:

npm run dev

Open http://localhost:3000 in your browser to see the result.

Environment Variables

Create a .env file in the root of the project and add the following environment variables:

OPENAI_API_KEY="" # Obtain this from OpenAI
OPENAI_GPT_MODEL="" # Specify the model to use (if not provided, the gpt-3.5-turbo model will be used by default)

Contributing

Contributions are welcome! Jusy submit a pull request with your changes 🚀

If you want to contribute, but don't know how to code, please create an issue with your idea, and we'll see what we can do.

Technologies used

Acknowledgments

Ørjan Hafnor for the design
Johannes Andersen for the initial code
Danielle Chiosso Liu for prompt engineering and investigating ChatGPT performance
NRK and VG for fostering cross-media collaboration

sum's People

Contributors

Stargazers

Watchers

sum's Issues

Compress audio files

Describe the feature you'd like to request

Speech to text have a rather small upload limit of just 25mb
https://platform.openai.com/docs/guides/speech-to-text

Describe the solution you'd like

We should add some sort of WASM or other module to take the uploaded audio file, then compress it and convert it to a supported type

File uploads are currently limited to 25 MB and the following input file types are supported: mp3, mp4, mpeg, mpga, m4a, wav, and webm.

To be experimented with, but maybe mono 32kbit/s mp3?

Implement V3 design

Describe the feature you'd like to request

There are some missing designs from Figma
https://www.figma.com/file/hQHcPmvIvXhAcaYEZawj9k/Untitled?node-id=45-762

Describe the solution you'd like

Here are some of the things needed:

Drag and drop state
Audio preview after upload
Side by side view
Description hover in action select menu

Add streaming support for ChatGPT

Describe the feature you'd like to request

Currently the page is just loading until the entire response is done from ChatGPT

Describe the solution you'd like

ChatGPT API does allow streaming.
We should add streaming support so it has that typing animation we are used to from the official chat.openai.com site

Docs: https://platform.openai.com/docs/api-reference/chat/create

Add better error handling and loading states

Describe the feature you'd like to request

Currently loading is just set on the HTML elements to have a spinning cursor.

Errors are also currently just hidden for the user, and they will be stuck in a infinite loading loop

Describe the solution you'd like

We should add better loading animation

Errors should be correctly shown to the end user

Add multi-language support

Describe the feature you'd like to request

Currently we have a "language select", but it is hardcoded to just be Norwegian

Describe the solution you'd like

Implement the ability to select other languages

The UI should use the selected languages
The action selector should only list prompts available in the selected language (meaning we also need to localize the prompts array)

Store data in a database

Describe the feature you'd like to request

Currently it is all a SPA

This has the downside of not being able to create unique URLs pr summary.
Causing things like refresh or browser crash to louse access to the work done

Describe the solution you'd like

When a user click the "Sum" button on the first page, create a entry in a DB and use that to push ChatGPT actions to
Then redirect the user to a new page. Something like localhost:3000/sum/

Dependency Dashboard

This issue lists Renovate updates and detected dependencies. Read the Dependency Dashboard docs to learn more.

Rate-Limited

These updates are currently rate-limited. Click on a checkbox below to force their creation now.

Open

These updates have all been created already. Click a checkbox below to force a retry/rebase of any.

Detected dependencies

github-actions

.github/workflows/codeql.yml

actions/checkout v3

actions/setup-node v3

github/codeql-action v2

github/codeql-action v2

github/codeql-action v2

.github/workflows/tests.yml

actions/checkout v3

actions/setup-node v3

npm

package.json

@headlessui/react 1.7.13

@heroicons/react 2.0.17

lodash 4.17.21

next 13.3.0

openai 3.2.1

react 18.2.0

react-dom 18.2.0

tmp 0.2.1

zod 3.21.4

@tailwindcss/forms 0.5.3

@types/ffmpeg 1.0.4

@types/lodash 4.14.192

@types/node 18.15.11

@types/react 18.0.33

@types/react-dom 18.0.11

@types/tmp 0.2.3

autoprefixer 10.4.14

eslint 8.37.0

eslint-config-next 13.3.0

postcss 8.4.21

prettier 2.8.7

prettier-plugin-tailwindcss 0.2.7

stylelint 15.4.0

stylelint-config-standard 32.0.0

tailwindcss 3.3.1

typescript 5.0.3

node >=19

npm >=9

nvm

.nvmrc

node v19

Check this box to trigger a request for Renovate to run again on this repository

Recommend Projects

React

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

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

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

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

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.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

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

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.