Class IntentSharpSettings

Settings bound from configuration (section "IntentSharp" by default).

public sealed class IntentSharpSettings

Inherited Members: object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Extension Methods: IntentExtensions.RunIntentAsync(object?, IntentRuntime, string, CancellationToken)

IntentExtensions.RunIntentAsync(object?, string, CancellationToken)

IntentExtensions.RunIntentAsync<T>(object?, IntentRuntime, string, CancellationToken)

IntentExtensions.RunIntentAsync<T>(object?, string, CancellationToken)

AIExtensions.AIAsync(object?, IntentClient, string, AIRequestOptions?, CancellationToken)

AIExtensions.AIAsync<T>(object?, IntentClient, string, AIRequestOptions?, CancellationToken)

AIExtensions.AIClassifyAsync<TEnum>(object?, IntentClient, string?, AIRequestOptions?, CancellationToken)

AIExtensions.AIConvertAsync<T>(object?, IntentClient, AIRequestOptions?, CancellationToken)

AmbientAIExtensions.AIAsync(object?, string, AIRequestOptions?, CancellationToken)

AmbientAIExtensions.AIAsync<T>(object?, string, AIRequestOptions?, CancellationToken)

AmbientAIExtensions.AIClassifyAsync<TEnum>(object?, string?, AIRequestOptions?, CancellationToken)

AmbientAIExtensions.AIConvertAsync<T>(object?, AIRequestOptions?, CancellationToken)

Constructors

IntentSharpSettings(): Creates settings with the default on each property, reading the OpenAI and Anthropic keys from the OPENAI_API_KEY and ANTHROPIC_API_KEY environment variables now.

AnthropicApiKey: The Anthropic API key. Defaults to the ANTHROPIC_API_KEY environment variable. When both keys are set, the provider that is not the primary becomes the fallback; null or blank leaves Anthropic out.

AnthropicModel: The Anthropic model used when a request names none. Null uses the provider's default model.

CacheCapacity: Entries the in-process request cache holds before it evicts the least recently used one. Default 1000.

EnableRequestCache: Serve identical requests from a request cache. Default true. The cache is the registered IRequestCache when there is one, otherwise an in-process cache of CacheCapacity entries.

MemoryPath: Path for SQLite memory. Null uses in-process memory; empty string disables memory.

OpenAIApiKey: The OpenAI API key. Defaults to the OPENAI_API_KEY environment variable. When both keys are set, the provider that is not the primary becomes the fallback; null or blank leaves OpenAI out.

OpenAIModel: The OpenAI model used when a request names none. Null uses the provider's default model.

Options: The client-wide options. From configuration they bind from the Options subsection, for example IntentSharp:Options:LicenseKey.

PrimaryProvider: "OpenAI" or "Anthropic", ignoring case. Defaults to whichever key is present, Anthropic first when both are. Any other value stops the client from being built with InvalidOperationException.

RateLimitBurst: Requests a provider may make in a burst before the throttle holds it to RateLimitPerSecond. Default 10.

RateLimitPerSecond: Requests per second per provider for the local throttle. 0 disables it.