Introducing Wiki Topic Grapher 👾
Leverage the power of Google #NLP to retrieve entity relationships from Wikipedia URLs or topics!
Get interactive graphs of connected entities
Export results with entity types and salience to CSV!
Try the app here!
Many cool use cases!
Research any topic then get entity associations that exist from that seed topic
Map out related entities with your product, service or brand
Find how well you've covered a specific topic on your website
Differentiate your pages!
About the stack, it's 100% #Python! 🐍🔥
@GCPcloud Natural Language API
Streamlit Components -> streamlit.io/components
⚒️ Still To-Do’s
💰 Add a budget estimator to get a sense of @GCPcloud costs!
🌍Add a multilingual option (currently English only)
📈Add on-the-fly physics controls to the network graph
💯Add Google KG #API to add more data (scores, etc.) (ht @LoukilAymen)
That code currently lays 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! I just need to clean it a tad, remove some sensitive bits, etc.
Kudos to @jroakes for the original script. Buy that man a 🍺 for his sterling contributions! -> paypal.com/paypalme/codes…
Kudos also to fellow @streamlit Creators:
@napoles3D who told me about the PyVis lib! 🔥
@andfanilo/@ChristianKlose3 for their precious advice! 🙏
💲 Beware on costs!
It can get expensive quickly with that Google Natural Language API!
Monitor your costs via the GCP console regularly and/or put quotas to tame that G beast! I'm planning to add a budget estimator pre-API calls. Should come handy.
Feedback and support
Wiki Topic Grapher's still in Beta, with possible rough edges! Head-off to my Gitter page for bug reports, questions, or suggestions.
This app is free. If it's useful to you, you can buy me a ☕ to support my work! 🙏 ▶️ buymeacoffee.com/cwar05
That's all, folks. Enjoy!