Skip to main content
Version: 0.16

SpamLlm

Configures the LLM-based spam classifier.

Enterprise feature

This object is only available with an Enterprise license.

This object can be configured from the WebUI under Settings › Spam Filter › LLM Classifier

Fields​

SpamLlm is a multi-variant object: each instance has an @type discriminator selecting one of the variants below, and each variant carries its own set of fields.

@type: "Disable"​

Disabled

@type: "Enable"​

Enabled

categories​

Type: String[] · default: ["Unsolicited","Commercial","Harmful","Legitimate"] · min items: 2

The expected categories in the LLM response

confidence​

Type: String[] · default: ["High","Medium","Low"]

The expected confidence levels in the LLM response

responsePosCategory​

Type: UnsignedInt · default: 0

The position of the category field in the LLM response.

responsePosConfidence​

Type: UnsignedInt? · default: 1

The position of the confidence field in the LLM response.

responsePosExplanation​

Type: UnsignedInt? · default: 2

The position of the explanation field in the LLM response.

modelId​

Type: Id<AiModel> · required

The AI model to use for the LLM classifier

prompt​

Type: Text · required

The prompt to use for the LLM classifier

separator​

Type: String · default: ","

The separator character used to parse the LLM response.

temperature​

Type: Float · default: 0.5 · max: 1 · min: 0

The temperature to use for the LLM classifier

JMAP API​

The SpamLlm singleton is available via the urn:stalwart:jmap capability.

x:SpamLlm/get​

This is a standard Foo/get method as defined in RFC 8620, Section 5.1.

For singletons, the ids argument should be the literal singleton (or null to return the single instance).

This method requires the sysSpamLlmGet permission.

curl -X POST https://mail.example.com/api \
  -H 'Authorization: Bearer $TOKEN' \
  -H 'Content-Type: application/json' \
  -d '{
      "methodCalls": [
        [
          "x:SpamLlm/get",
          {
            "ids": [
              "singleton"
            ]
          },
          "c1"
        ]
      ],
      "using": [
        "urn:ietf:params:jmap:core",
        "urn:stalwart:jmap"
      ]
    }'

x:SpamLlm/set​

This is a standard Foo/set method as defined in RFC 8620, Section 5.3.

For singletons, only the update argument with id singleton is accepted; create and destroy arguments are rejected.

This method requires the sysSpamLlmUpdate permission.

curl -X POST https://mail.example.com/api \
  -H 'Authorization: Bearer $TOKEN' \
  -H 'Content-Type: application/json' \
  -d '{
      "methodCalls": [
        [
          "x:SpamLlm/set",
          {
            "update": {
              "singleton": {
                "id": "id1"
              }
            }
          },
          "c1"
        ]
      ],
      "using": [
        "urn:ietf:params:jmap:core",
        "urn:stalwart:jmap"
      ]
    }'

CLI​

stalwart-cli wraps the same JMAP calls. See the CLI reference for installation, authentication, and general usage.

Fetch​

stalwart-cli get spam-llm

Update​

stalwart-cli update spam-llm --field description='Updated'