LocalEngineOptions
Options & Configuration · AiDotNet.Agentic.Models.Local
Settings for LocalEngineChatClient: the reported model id, the default generation length,
and the default sampling behavior (overridable per request via ChatOptions).
For Beginners
These are the local model’s defaults. The most useful is
MaxOutputTokens (how long a reply may get before the engine stops). Leave
Sampling unset for safe, near-greedy behavior, or set it to make replies more creative.
Constructors
| Constructor | Summary |
|---|---|
LocalEngineOptions() |
Properties
| Property | Summary |
|---|---|
ITokenConstraint Constraint { get; set; } |
Gets or sets a token constraint applied during generation (constrained decoding). |
LocalSamplingOptions Sampling { get; set; } |
Gets or sets the default sampling settings. |
int? BeamWidth { get; set; } |
Gets or sets the beam width for beam-search decoding. |
int? MaxOutputTokens { get; set; } |
Gets or sets the default maximum number of tokens to generate per reply. |
string ModelId { get; set; } |
Gets or sets the model id reported by ModelId. |
Fields
| Field | Summary |
|---|---|
int DefaultMaxOutputTokens |
The default maximum number of tokens generated per reply when none is specified. |