AI-powered music discovery PoC on the Spotify Web API — LLM as the recommender
Find a file
2026-08-10 11:31:06 +02:00
.github/workflows feat: add single-image compose deliverable and CI 2026-08-09 20:59:58 +02:00
backend feat: add Spotify client and auth routes 2026-08-10 11:31:06 +02:00
docs docs: open the build log 2026-08-10 10:24:54 +02:00
frontend feat: scaffold Vue 3 + TypeScript frontend with lint and typecheck tooling 2026-08-09 20:59:12 +02:00
.env.example feat: add Spotify client and auth routes 2026-08-10 11:31:06 +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
docker-compose.yml feat: add single-image compose deliverable and CI 2026-08-09 20:59:58 +02:00
README.md chore: establish standards in AGENTS.md 2026-08-09 20:56:13 +02:00

discovery-by-llm

This is a demo that serves as a proof of concept for LLM utilization for music discovery, specifically using the Spotify API. The form-factor is an LLM-chat like experience, with direct Spotify integration.

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)