Published On May 29, 2024
In this video, I demonstrate how to build a content-based recommender system that provides personalized recommendations based on the user's watch history, specifically what they have liked and disliked.
โจ Follow along as I guide you through:
- Generating text embeddings
- Inserting collections into Qdrant Cloud
- Providing personalized recommendations based on user watch history, focusing on what they have liked and disliked
- Designing the app's frontend using Streamlit
๐ฅ Don't forget to ๐๐๐ฏ๐๐ฐ๐ฟ๐ถ๐ฏ๐ฒ, ๐ฌ๐ฆ๐๐ฌ๐ก the ๐น๐ถ๐ธ๐ฒ ๐๐ฎ๐ญ๐ญ๐จ๐ง, and ๐ญ๐ฎ๐ซ๐ง ๐จ๐ง the ๐ง๐จ๐ญ๐ข๐๐ข๐๐๐ญ๐ข๐จ๐ง ๐๐๐ฅ๐ฅ for more ๐ฒ๐
๐ฐ๐ถ๐๐ถ๐ป๐ด ๐ฝ๐ฟ๐ผ๐ท๐ฒ๐ฐ๐๐ and ๐๐๐๐ผ๐ฟ๐ถ๐ฎ๐น๐.
๐ Timestamps:
0:00 Introduction
0:21 Demo
0:49 Workflow - Flow diagram of Content-based Recommendation System
02:49 Setup Environment
03:17 Insert embeddings to Qdrant
12:42 Design Streamlit frontend
17:10 Generate Recommendations based on watch history and preferences
21:44 Test Recommendation System
22:24 Conclusion
Links:
๐ป Code: https://github.com/Eduardovasquezn/mo...
โ๏ธ Buy me a coffee... or an iced tea: https://www.buymeacoffee.com/eduardov
๐ LinkedIn: ย ย /ย eduardo-vasquez-nย ย
โ
#RecommendationSystem #AI #Google #RecommenderSystem #RecommendationEngine #Qdrant #MachineLearning #AI #ContentBasedFiltering #TextEmbeddings #Streamlit #DataScience #AnimeRecommendations #TechTutorial #Coding #Python #AIApplications #DataScience #Data #Tutorial