Music Catalog Intelligence
Date Published:
DiscoveryThe catalog already contains useful information. This project adds analysis and reviewed suggestions to make that information easier to use.
Diagram source
flowchart TB
App["Catalog app<br/>browse · review · curate"]
API["Catalog API<br/>artists · releases · tracks"]
PG[("PostgreSQL<br/>canonical · provenance")]
IK["ImageKit<br/>storage · delivery"]
subgraph PHX["Arize Phoenix · traces · evals · experiments"]
EA["Enrichment API<br/>jobs · validation · provenance"]
SIG["Signal analysis<br/>Essentia · librosa"]
ML["Audio ML<br/>CLAP embeddings"]
LLM["Semantic AI<br/>tags · description"]
BF["Bifrost<br/>model gateway · routing · fallback"]
end
App -->|calls| API
API -->|owns| PG
API -->|stores| IK
API -->|syncs| IK
API -->|submits job| EA
EA -->|analyses| SIG
EA -->|embeds| ML
EA -->|drafts| LLM
LLM -->|asks| BFFig. 1. Enrichment runs beside the catalog. ImageKit stores files, Postgres owns canonical data, and Phoenix traces the AI workflow.
The canonical catalog lives in the application's own database. ImageKit handles files, transformations, and delivery, and receives selected fields for asset discovery. The catalog remains the source of truth while changes sync in both directions.
Keep music-specific rules such as versioning, credits, and provenance out of ImageKit.
Measured facts stay out of the LLM
Diagram source
flowchart LR
subgraph DET["deterministic · no model"]
SIG["Signal analysis<br/>tempo · loudness"]
ML["Audio ML<br/>embeddings"]
end
EV["Evidence<br/>numbers, not wording"]
subgraph LM["language model only"]
SA["Semantic AI<br/>via Bifrost"]
DM["Draft metadata<br/>mood · tags"]
end
SIG -->|features| EV
ML -->|vectors| EV
EV -->|prompt| SA
SA -->|writes| DMFig. 2. Signal analysis and audio models produce evidence. The language model turns it into words.
Tempo is measured, so the model should use that value rather than guess. Mood requires judgment, so a library cannot measure it. Each layer has a defined job, output type, and owner.
Seed the prompt with measured facts and the nearest neighbours. The LLM can interpret them without inventing a BPM.
Start with one path
Diagram source
flowchart LR
subgraph G1["Intake · steps 1–3"]
S1["1 Upload track<br/>you · app"] --> S2["2 Register asset<br/>ImageKit · file stored"] --> S3["3 Read existing metadata<br/>deterministic · no model"]
endDiagram source
flowchart LR
subgraph G2["Enrichment · steps 4–6"]
S4["4 Analyse audio<br/>Essentia · CLAP"] --> S5["5 Generate suggestions<br/>Bifrost · one task per call"] --> S6["6 Validate and record provenance<br/>deterministic · schema and rules"]
endDiagram source
flowchart LR
subgraph G3["Review and write · steps 7–9"]
S7["7 Human review<br/>you · accept, edit, reject"] --> S8["8 Update canonical metadata<br/>catalog · the only writer"] --> S9["9 Sync selected fields<br/>ImageKit · discovery only"]
endFig. 3. Steps 1–6 run unattended. A person reviews the suggestions before canonical metadata changes.
Make this path reliable before building a large catalog interface. A polished interface cannot make an unreliable pipeline dependable.
Human review approves suggestions
Diagram source
flowchart TD
O["Original metadata<br/>ingestion"] -->|imported| REC["Field record<br/>genre"]
M["Machine suggestion<br/>Bifrost · v1"] -->|proposed| REC
X["External source<br/>attributed"] -->|imported| REC
REC -->|queues| HR["Human review<br/>accept · edit · reject"]
HR -->|approves| CAN[("Canonical metadata")]
HR -->|rejects| EVA["Evaluation example"]
CAN -->|retested by| M2["Model v2"]
M2 -.->|compared with| EVAFig. 4. Each value records who created it and when. An owner's edit becomes an evaluation case (illustrative sequence).
One field can have four values, but only one is canonical.
| Representation | Written by | Can overwrite canonical |
|---|---|---|
| Original metadata | Ingestion, existing tags | no |
| Machine suggestion | Enrichment run | no |
| Human-approved metadata | Owner after review | yes |
| Externally sourced metadata | Third party, with attribution | no |
Record the task, field, input asset, model and version, prompt version, timestamp, output, validation result, and review decision. Treat model-reported confidence as a hint until it has been calibrated.
Route by task, then measure the route
| Task | Model tier | Guard |
|---|---|---|
| Basic classification | small, low cost | schema check |
| Mood interpretation | stronger | sampled human review |
| Editorial description | mid-tier | schema and length |
| Metadata validation | small, plus rules | deterministic checks first |
| Low confidence | escalate | human review |
Bifrost is the only gateway to a model. It handles provider abstraction, routing, fallback, caching, and cost control.
Arize Phoenix traces that path (Fig. 1) and compares prompt versions across the catalog. A response parsing successfully does not show whether the prompt is better.