Streamlit web app to generate datasets with OpenAI's GPT models
License: MIT License
Interests:
I was the original author and current maintainer of the Book Project and the Books API.
Given this query:
HP quotes
I get back this JSON:
{
" Quote ": {
"1": " \"Happiness can be found, even in the darkest of times, if one only remembers to turn on the light.\" ",
"2": " \"It does not do to dwell on dreams and forget to live.\" ",
"3": " \"It is our choices, Harry, that show what we truly are, far more than our abilities.\" ",
"4": " \"Fear of a name increases fear of the thing itself.\" ",
"5": " \"We are only as strong as we are united, as weak as we are divided.\" ",
"6": " \"It takes a great deal of bravery to stand up to our enemies, but just as much to stand up to our friends.\" ",
"7": " \"It is our choices that show what we truly are, far more than our abilities.\" ",
"8": " \"Happiness can be found even in the darkest of times, if one only remembers to turn on the light.\" ",
"9": " \"It is our choices that show what we truly are, far more than our abilities.\" ",
"10": " \"It is our choices that show what we truly are, far more than our abilities.\" "
},
" Author ": {
"1": " Albus Dumbledore ",
"2": " Albus Dumbledore ",
"3": " Albus Dumbledore ",
"4": " Albus Dumbledore ",
"5": " Albus Dumbledore ",
"6": " Albus Dumbledore ",
"7": " Albus Dumbledore ",
"8": " Albus Dumbledore ",
"9": " Albus Dumbledore ",
"10": " Albus Dumbledore "
}
}Expected result:
Add options to save the exported CSV or JSON directly to AWS S3.
Given this query:
HP quotes
I get back this JSON:
{
"Unnamed: 0": {
"0": null,
"1": null,
"2": null,
"3": null,
"4": null,
"5": null,
"6": null,
"7": null,
"8": null,
"9": null,
"10": null
},
" Quote ": {
"0": "------",
"1": " \"Happiness can be found, even in the darkest of times, if one only remembers to turn on the light.\" ",
"2": " \"It does not do to dwell on dreams and forget to live.\" ",
"3": " \"It is our choices, Harry, that show what we truly are, far more than our abilities.\" ",
"4": " \"We must all face the choice between what is right and what is easy.\" ",
"5": " \"Fear of a name increases fear of the thing itself.\" ",
"6": " \"It is our choices that show what we truly are, far more than our abilities.\" ",
"7": " \"It is our choices that make us who we are, and we can always choose to do what is right.\" ",
"8": " \"Happiness can be found even in the darkest of times, if one only remembers to turn on the light.\" ",
"9": " \"It is our choices that make us who we are, and we can always choose to do what is right.\" ",
"10": " \"It is our choices that show what we truly are, far more than our abilities.\" "
},
" Author ": {
"0": "-------",
"1": " Albus Dumbledore ",
"2": " Albus Dumbledore ",
"3": " Albus Dumbledore ",
"4": " Albus Dumbledore ",
"5": " Albus Dumbledore ",
"6": " Albus Dumbledore ",
"7": " Albus Dumbledore ",
"8": " Albus Dumbledore ",
"9": " Albus Dumbledore ",
"10": " Albus Dumbledore "
}
}Expected result:
The generate button should be disabled (greyed out) until the user enters in text in the input field.
Using docker-compose, create services that run the backend (Flask) and frontend (streamlit).
The backend service should start first as the frontend should depend on the frontend service running.
The semantic release GitHub actions job should run only if the conventional commit job runs successfully.
Add a job that runs precommit on the files changed
If the server is down or not running, the frontend should show an error message.
The radio buttons for models depends on the server running, so this should happen straight away.
Add gpt-3.5-turbo functionality that uses the Chat Completions endpoint
Acceptance criteria:
The logs currently show logs from the OpenAI and standard library. Restrict it to only this app's logs.
The Streamlit downloads buttons are in different columns. The column width should be smaller so that they are closer together.
Trigger semantic release in a GitHub actions job
To save on costs, allow a user to add their own API key.
Acceptance criteria:
Remove the link to the header, ideally with Python code rather than CSS.
Once granted access to Anthropic Claude, add an endpoint that queries and returns a response from Claude.
Add an endpoint that generates images using DALL-E.
The frontend should show a grid of images.
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
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.