PB & Jam

Inspiration

Many ethical concerns surround AI's impact on artistry, including questions about originality and the devaluation of human creativity. With our AI-driven web application, we aim to do the opposite by showcasing songs from a wide range of artists, from popular names to lesser-known talents, so that the user can discover various art.

What it does

PB & Jam uses a machine learning algorithm to find songs similar to the user-inputted song, carefully selecting measures of success (tempo, energy, etc.). We also utilized the OpenAI API to convert user-inputted emotions into ranges that can be fed into our machine-learning algorithm to curate a playlist according to the user's mood.

How we built it

Streamlit and numerous Python imports.

Challenges we ran into

Deploying Python’s Streamlit is a slightly different process the same way you would other web application languages (Node.js, React, etc.), so we could not attach our custom domain name to PB ‘n’ Jam. Streamlit does not work well with HTML or CSS, leading to issues when adding images. Nav bar, side bar gave us trouble when interacting with our main code. Configuring pip install took two hours and cost us a lot of motivation.

Accomplishments that we're proud of

Completing a project within the time frame and overcoming the multiple errors that popped up last minute.

What we learned

You can create a nice-looking project quickly with Streamlit, but the customization and formatting are still limited. In the future, with more time to combine Streamlit with other platforms and programs, we can build a better implementation.

What's next for PB & Jam

Have AI go through the lyrics of songs and recommend them based on the user's inputted mood. Make the program more reliable. Refine our algorithm to curate our user's palate.

Built With

• ai
• machine-learning
• openai
• pandas
• plotly
• python
• sckit-learn
• spotify
• streamlit