DataChazGPT (not a bot) Profile picture
Developer Advocate @Streamlit (acq. @SnowflakeDB) | prev. Samsung β€’ 𝕏 about LLMs, AI, Python, Data Sci, Web Apps & SEO β€’ My heart is open source β€’ Views mine!

Jul 26, 2021, 10 tweets

πŸ₯ New @streamlit app! 🎈

WTFaq leverages the power of @huggingface Transformers & @Google T5 to generate quality question & answer pairs from URLs!

Select your best Q&As on the fly & export them to CSV!

🎲App bit.ly/3zzS4us
πŸ“¬Post bit.ly/3kUz59O

#SEO

β†“πŸ§΅

First things first, pick a URL!

The app will crawl the URL's content & retrieve it back in the app.

Server side only for now. I'm planning to add the ability to crawl client-side rendered URLs soon, stay tuned! πŸ€—

2/10

Once a URL is crawled, you can check its scraped content in the toggleable section (see belowπŸ‘‡)

As we're still in beta and want to monitor memory spikes closely, built Q&A pairs are based on the first thousand scraped characters only.

We will increase that limit soon!πŸ˜‰

3/10

Wait a few seconds for the results to be populated.

Results will be displayed in a matrix of 5 to 20 question & answers pairs.

You can select your favourite Q&A pairs on the fly simply by ticking them, as shown on the video below πŸ‘‡

4/10

Final step!

Your selected Q&A pairs will be displayed in the bottom table.

If you wish to download them, click that download button - VoilΓ !

5/10

Many cool content & #SEO use cases! πŸ”₯

βœ“ Use it for content generation purposes
βœ“ Map-out Q&A pairs with your product, service or brand
βœ“ Research any topic and get Q&A pairs from that seed topic
βœ“ Differentiate your pages!

6/10

🧰 The stack is 100% #Python! 🐍πŸ”₯

βœ“ Web framework: @streamlit! 🎈
βœ“ Scraping tasks: Requests
βœ“ @Google T5 via @huggingface Pipelines - huggingface.co/transformers/m…
βœ“ Not to forget @thiago's mighty Component for coloured labels! github.com/tvst/st-annota… πŸ™Œ

7/10

πŸ› οΈ Still To-Do’s:

βœ“ Optimise code to increase speed ⚑
βœ“ Increase RAM capacity to mitigate bumps and allow for more content to be analysed
βœ“ Provide additional Q&A algorithms

Kudos to @huggingFaces and @Streamit DevOps for their support so far! πŸ™Œ

8/10

πŸ“‚ About open-sourcing the code:

That code currently lies in a private repo. I should be able to make it public soon for you to re-use it in your own apps and creations!

Keep your eyes peeled! πŸ™Œ

9/10

WTFaq is still in beta, head-off to my Gitter page for bug reports, Qs or suggestions:
▢️ gitter.im/DataChaz/what-…

This app is free! You can buy me a β˜• to support my work if it's useful to you!
▢️ buymeacoffee.com/cwar05

🎲 Check my other apps! charlywargnier.com/my-public-web-…

10/10

Share this Scrolly Tale with your friends.

A Scrolly Tale is a new way to read Twitter threads with a more visually immersive experience.
Discover more beautiful Scrolly Tales like this.

Keep scrolling