Personalized Mini TikTok

Built with FirstBatch + Streamlit + Pinecone

Visit demo

From curating the perfect dataset to deploying an intuitive web app with Streamlit, this journey is a testament to the power of embeddings & vector databases. Go through the blog post for detailed outline!

Blog post: https://andthattoo.substack.com/p/personalized-mini-tiktok

1. Curating the Kaggle Dataset

2. TikTok Videos as Embeddings

3. Efficiently Storing Embeddings in Pinecone

4. Crafting a Custom Algorithm through FirstBatch Dashboard

5. Designing a Streamlit Web Application for User Interaction

6. The Final Step: Share it!

Source code