justinzeus/discovery-by-llm
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
AI-powered music discovery PoC on the Spotify Web API — LLM as the recommender
3 commits 1 branch 0 tags 1.5 MiB
Find a file
Justin Visser ef9e102b05 feat: scaffold Vue 3 + TypeScript frontend with typed stream event contract
2026-08-09 20:59:12 +02:00
backend feat: scaffold FastAPI backend with ports-and-adapters layout 2026-08-09 20:58:10 +02:00
frontend feat: scaffold Vue 3 + TypeScript frontend with typed stream event contract 2026-08-09 20:59:12 +02:00
.gitignore chore: establish standards in AGENTS.md 2026-08-09 20:56:13 +02:00
AGENTS.md chore: establish standards in AGENTS.md 2026-08-09 20:56:13 +02:00
CLAUDE.md chore: establish standards in AGENTS.md 2026-08-09 20:56:13 +02:00
README.md feat: scaffold FastAPI backend with ports-and-adapters layout 2026-08-09 20:58:10 +02:00

README.md

discovery-by-llm

Music discovery with an LLM as the recommendation engine, on the Spotify Web API.

Thesis: Spotify removed its recommendation and audio-intelligence layer from the API (recommendations and audio features are gone for new apps). This proof of concept asks whether an LLM can take over that role, with Spotify demoted to resolver, verifier, personalisation source, and playback surface. A naive-search baseline makes the answer measurable.

Work in progress — this file is filled in during the build. Chronological build log (Dutch): docs/logboek.md.

Demo

(to follow: hosted instance + local docker compose up --build, with and without API keys)

How it works

(to follow: pipeline diagram and module map)

Choices

(to follow)

Performance and optimisations

(to follow)

Where to look

(to follow)

Method

(to follow)

What I cut / what I would do next

(to follow)