metadata

title: TaylorSwiftDJ
emoji: 🌟
colorFrom: pink
colorTo: indigo
sdk: streamlit
sdk_version: 1.26.0
app_file: app.py
pinned: false
license: creativeml-openrail-m

TaylorSwiftDJ 🌟

Made with DeepLake 🚀 and LangChain 🦜⛓️

💫 Hey there Swifties! Welcome to "TaylorSwiftDJ"! 🎤🎶
This streamlit powered app recommends Taylor Swift's iconic songs 'tailored'(hah! :D) to your emotions.
Dance, reminisce, and embrace your feelings with every beat – because life's a melody, and Taylor's your DJ. ✨ 🌈 💖

How it works

The application follows a sequence of steps to deliver Taylor Swift songs matching the user's emotions:

User Input: The application starts by collecting user's emotional state through a text input.
Emotion Encoding: The user-provided emotions are then fed to a Language Model (LLM). The LLM interprets and encodes these emotions.
Similarity Search: These encoded emotions are utilized to perform a similarity search within our vector database. This database houses ~130 Taylor Swift songs, each represented as emotional embeddings.
Song Selection: From the pool of top matching songs, the application randomly selects one. The selection is weighted, giving preference to songs with higher similarity scores.
Song Retrieval: The selected song's embedded player is displayed on the webpage for the user. Additionally, the LLM interpreted emotional state associated with the chosen song is displayed.

Setup instructions

--TODO--

DISCLAIMER: This project is 200% inspired by Francesco's FairyTaleDJ.