FirstBatch SDK
  • Get Started
    • Introduction
    • Installation
    • Quick Start
  • Learn
    • Key Concepts
      • Embeddings
      • Vector Databases
      • User Embeddings
    • Sessions
    • Signals
    • Batches
    • Algorithms
      • Batch Types
        • Random
        • Sampled
        • Personalized
        • Biased
      • Parameters & Tuning
    • Cookbook
      • Simple Flask App
      • Personalized RSS Feed
      • Personalized Mini TikTok
      • User-Intent AI Agents
      • Extending RAG: User Embeddings
      • Prompt Based User Journeys
      • User-Centric Promoted Content
  • Modules
    • FirstBatch
    • Algorithms
    • VectorStores
      • Pinecone
      • Weaviate
      • Qdrant
      • Typesense
      • Supabase
      • Chroma
Powered by GitBook
On this page
  1. Learn
  2. Cookbook

Personalized Mini TikTok

Built with FirstBatch + Streamlit + Pinecone

PreviousPersonalized RSS FeedNextUser-Intent AI Agents

Last updated 1 year ago

Visit

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 for detailed outline!

Blog post:

  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

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