REST API

goldenmatch serve --file customers.csv --config config.yaml --port 8080

export GOLDENMATCH_API_TOKEN="your-secret-token"
goldenmatch serve --file customers.csv --host 0.0.0.0 --port 8080

curl -H "Authorization: Bearer your-secret-token" http://host:8080/stats

export GOLDENMATCH_API_CORS_ORIGINS="https://app.example.com,https://admin.example.com"

curl http://localhost:8080/health

{"status": "ok", "service": "goldenmatch", "ready": true}

curl http://localhost:8080/stats

{
    "total_records": 5000,
    "total_clusters": 847,
    "singleton_count": 3200,
    "match_rate": 0.12,
    "avg_cluster_size": 2.1,
    "max_cluster_size": 8
}

curl -X POST http://localhost:8080/match \
    -H "Content-Type: application/json" \
    -d '{"name": "John Smith", "zip": "10001"}'

{
    "matches": [
        {"row_id": 42, "score": 0.92, "name": "Jon Smyth", "zip": "10001"},
        {"row_id": 108, "score": 0.87, "name": "John Smithe", "zip": "10001"}
    ]
}

curl -X POST http://localhost:8080/match/batch \
    -H "Content-Type: application/json" \
    -d '{"records": [
        {"name": "John Smith", "zip": "10001"},
        {"name": "Jane Doe", "zip": "90210"}
    ]}'

curl -X POST http://localhost:8080/explain \
    -H "Content-Type: application/json" \
    -d '{
        "record_a": {"name": "John Smith", "zip": "10001"},
        "record_b": {"name": "John Smithe", "zip": "10001"}
    }'

{
    "overall_score": 0.92,
    "explanation": "Strong match: name similarity 0.88 (jaro_winkler), zip exact match.",
    "field_scores": [
        {"field": "name", "scorer": "jaro_winkler", "score": 0.88},
        {"field": "zip", "scorer": "exact", "score": 1.0}
    ]
}

curl http://localhost:8080/clusters

{
    "clusters": [
        {"cluster_id": 1, "size": 3, "confidence": 0.91},
        {"cluster_id": 2, "size": 2, "confidence": 0.87}
    ]
}

curl http://localhost:8080/clusters/1

{
    "cluster_id": 1,
    "size": 3,
    "confidence": 0.91,
    "members": [
        {"row_id": 42, "name": "John Smith", "email": "john@example.com"},
        {"row_id": 108, "name": "Jon Smyth", "email": "john@example.com"},
        {"row_id": 215, "name": "J. Smith", "email": "jsmith@example.com"}
    ],
    "pair_scores": {
        "42-108": 0.92,
        "42-215": 0.85,
        "108-215": 0.83
    },
    "bottleneck_pair": [108, 215]
}

curl http://localhost:8080/reviews

{
    "queue": [
        {
            "id": "rev_001",
            "id_a": 42,
            "id_b": 300,
            "score": 0.82,
            "record_a": {"name": "John Smith", "zip": "10001"},
            "record_b": {"name": "J. Smithson", "zip": "10001"}
        }
    ],
    "count": 1
}

curl -X POST http://localhost:8080/reviews/decide \
    -H "Content-Type: application/json" \
    -d '{"pair_id": "rev_001", "decision": "approve"}'

curl http://localhost:8080/reviews/decisions

import goldenmatch as gm

client = gm.Client("http://localhost:8080")

# Match a record
matches = client.match({"name": "John Smith", "zip": "10001"})

# List clusters
clusters = client.list_clusters()

# Explain a match
explanation = client.explain(42, 108)

# Get review queue
reviews = client.reviews()

# Re-profile the server's currently-loaded data
curl -X POST http://localhost:8080/autoconfig

# Or override with a different dataset
curl -X POST http://localhost:8080/autoconfig \
    -H "content-type: application/json" \
    -d '{"records": [{"name": "Alice", "email": "a@x.com"}, ...]}'

{
  "config": { "...": "full GoldenMatchConfig JSON" },
  "telemetry": {
    "available": true,
    "source": "rest_autoconfig",
    "stop_reason": "green",
    "health": "green",
    "elapsed_ms": 234.5,
    "scoring": {"n_pairs_scored": 4421, "mass_above_threshold": 0.087},
    "blocking": {"n_blocks": 312, "reduction_ratio": 0.94},
    "cluster": {"n_clusters": 1820, "transitivity_rate": 0.99},
    "column_priors": [{"column": "email", "identity_score": 0.95, "corruption_score": 0.0}],
    "decisions": [{"iteration": 1, "rule_name": "...", "rationale": "..."}],
    "committed_matchkeys": [{"name": "exact_email", "has_negative_evidence": true}],
    "negative_evidence": [{"matchkey_name": "exact_email", "field": "phone", "penalty": 0.5}]
  }
}

{"available": false, "source": null}

docker run --rm -p 8080:8080 -v $(pwd):/data \
    ghcr.io/benseverndev-oss/goldenmatch:latest \
    serve --file /data/customers.csv --port 8080