Skip to main content
NVIDIA

nvidia/Kumo Tabular

API Reference

Deploy

Ready to scale? Choose your deployment path.
Deploying your application in production? Get started with a 90-day evaluation of NVIDIA AI Enterprise

Follow the steps below to download and run the NVIDIA NIM inference microservice for this model on your infrastructure of choice.

Generate API Key

Pull and Run the NIM

$ docker login nvcr.io
Username: $oauthtoken
Password: <PASTE_API_KEY_HERE>

Pull and run the NVIDIA NIM with the command below. The container serves the single packaged kumo-tabular model; no external model mount or runtime model download is required.

docker run -it --rm \
    --gpus all \
    --shm-size=16GB \
    -p 8000:8000 \
    nvcr.io/nim/nvidia/kumo-tabular:1.0.0-rc2

The NIM listens on internal port 8000 by default. Set NIM_HTTP_API_PORT only when intentionally changing the container listen port, and update the Docker port mapping to match.

Test the NIM

You can now make a local API call using this curl command:

cat > /tmp/kumo-tabular-request.json <<'JSON'
{
  "model": "kumo-tabular",
  "task": {
    "kind": "classification",
    "target": {
      "column_name": "renewed",
      "dtype": "string",
      "classes": [
        "no",
        "yes"
      ],
      "positive_class": "yes"
    }
  },
  "schema": {
    "instance_table": {
      "columns": {
        "customer_id": {
          "dtype": "string",
          "stype": "ID",
          "nullable": false
        },
        "age": {
          "dtype": "int64",
          "stype": "numerical"
        },
        "country": {
          "dtype": "string",
          "stype": "categorical"
        },
        "plan": {
          "dtype": "string",
          "stype": "categorical"
        },
        "monthly_spend": {
          "dtype": "float64",
          "stype": "numerical"
        },
        "support_tickets": {
          "dtype": "int64",
          "stype": "numerical"
        },
        "renewed": {
          "dtype": "string",
          "stype": "categorical"
        }
      },
      "primary_key": "customer_id"
    },
    "related_tables": {},
    "relationships": []
  },
  "context": {
    "instance_table": {
      "format": "arrays",
      "columns": [
        "customer_id",
        "age",
        "country",
        "plan",
        "monthly_spend",
        "support_tickets",
        "renewed"
      ],
      "rows": [
        ["ctx-001", 33, "US", "pro", 69.0, 0, "yes"],
        ["ctx-002", 57, "CA", "free", 0.0, 4, "no"],
        ["ctx-003", 42, "DE", "enterprise", 199.0, 1, "yes"],
        ["ctx-004", 26, "US", "free", 0.0, 0, "no"],
        ["ctx-005", 49, "GB", "pro", 89.5, 2, "yes"],
        ["ctx-006", 61, "FR", "free", 0.0, 5, "no"]
      ]
    },
    "related_tables": {}
  },
  "predict": {
    "instance_table": {
      "format": "arrays",
      "columns": [
        "customer_id",
        "age",
        "country",
        "plan",
        "monthly_spend",
        "support_tickets"
      ],
      "rows": [
        ["lead-100", 29, "US", "free", 19.99, 0]
      ]
    },
    "related_tables": {}
  },
  "output": {
    "fields": [
      "prediction",
      "probabilities"
    ]
  },
  "metadata": {
    "request_id": "kumo-tabular-catalog-demo-001"
  }
}
JSON

curl -X 'POST' \
'http://127.0.0.1:8000/v1/predictions' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
--data-binary @/tmp/kumo-tabular-request.json

For more details on this NIM request format, see the API reference for POST /v1/predictions.