README.md

metadata

title: Rec Project
emoji: ⚡
colorFrom: gray
colorTo: gray
sdk: streamlit
sdk_version: 1.37.1
app_file: app.py
pinned: false

Shows Recs: TV Series Recommendation System

Overview

Shows Recs is a web application that provides TV series recommendations based on user input. It uses Sentence Transformers and FAISS to search and recommend series by embedding text queries and comparing them to a precomputed index of embeddings.

Features

• Metric Selection: Choose from L2, Dot Product, or Cosine Similarity.
• Customizable Recommendations: Specify the number of recommendations to display.
• Fast and Accurate: Leverages FAISS for efficient similarity search.

Installation & Usage

1. Clone the Repository

git clone https://huggingface.co/skudinov/shows_recs.git
cd shows_recs

2. Install Dependencies

Create a virtual environment and install the required packages:

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

3. Run the Application

Run the Streamlit app locally:

streamlit run app.py

The app will be accessible at http://localhost:8501.

4. Run with Docker

• Build the Docker image:

docker build -t your_docker_account/your_docker_repo .

• Run the Docker container:

docker run -p 8501:8501 your_docker_account/your_docker_repo

How to Use

• Enter a query in the text input field.
• Select a similarity metric (L2, Dot Product, Cosine Similarity).
• Choose the number of recommendations.
• Click "Search" to get a list of TV series recommendations.