Ollama

Configuration for the Ollama model provider.

A provider block with kind = "ollama" configures a local Ollama runtime. Ollama runs entirely on the local machine and does not require an API key.

Fields

Field	Type	Required	runtime()	Default	Description
`kind`	`ollama`	yes	no	…	Provider kind.
`models`	array<string \| ModelEntry>	no	no	unset	Models permitted for this provider, with optional model-specific inference settings.
`config`	ProviderConfig	no		unset	Base URL of the Ollama server.
`params`	InferenceParams	no		unset	Default inference settings for requests to this provider.

When config.base_url is unset, the client connects to http://localhost:11434, which is the default address of a locally running Ollama instance.

ModelEntry

Field	Type	Required	runtime()	Default	Description
`name`	string	yes	no	…	Model identifier.
`params`	InferenceParams	no		unset	Model-specific inference parameter overrides.

ProviderConfig

Field	Type	Required	runtime()	Default	Description
`base_url`	string	no	yes	unset	Base URL of the Ollama server.
`headers`	map<string, HeaderValue>	no	yes	`{}`	HTTP headers sent with every model request, keyed by header name. Header names are case insensitive.

HeaderValue

A header value is one of:

Form	Header value
a string	The string, unchanged.
`expression("source")`	The result of the CEL expression `source`, evaluated for each model request.

config {
  headers = {
    "X-Team"      = "platform"
    "X-Tenant-Id" = expression("ctx.tenant_id")
  }
}

For the values an expression can read and how evaluation fails, see Send custom headers.

InferenceParams

The params block sets inference parameter defaults for all models under this provider. All fields are optional and support runtime().

Field	Type	Required	runtime()	Default	Description
`max_tokens`	integer	no	yes	unset	Maximum number of tokens to generate.
`temperature`	number	no	yes	unset	Controls randomness when selecting the next token; higher values produce more varied output.
`top_p`	number	no	yes	unset	Selects tokens from the smallest group whose combined probability reaches this value.
`top_k`	integer	no	yes	unset	Limits the next-token choices to the K most likely tokens.
`stop_sequences`	array<string>	no	yes	unset	Sequences that stop generation.
`frequency_penalty`	number	no	yes	unset	Reduces repetition by penalizing tokens according to how often they have appeared.
`presence_penalty`	number	no	yes	unset	Penalizes tokens that have already appeared to reduce repetition.
`seed`	integer	no	yes	unset	Seed for deterministic sampling.
`provider_params`	object	no	yes	unset	Additional provider-specific inference options sent directly to the API.

Example

agent.acl

provider "ollama" {
  kind = "ollama"
  models = [
    "llama3.2",
    {
      name = "mistral"
      params {
        temperature = 0.9
        seed        = 42
      }
    }
  ]

  config {
    base_url = runtime("OLLAMA_BASE_URL", "http://localhost:11434")
  }

  params {
    max_tokens  = 2048
    temperature = 0.6
  }
}

In this example, requests to llama3.2 use the provider-level defaults. Requests to mistral use temperature = 0.9 and seed = 42 from its model-level params, while inheriting max_tokens from the provider-level defaults.