llm4s-docs/org.llm4s/org.llm4s.llmconnect/org.llm4s.llmconnect.spi/ProviderDescriptor

ProviderDescriptor

org.llm4s.llmconnect.spi.ProviderDescriptor

See theProviderDescriptor companion object

@Stable

Everything llm4s needs to know about one LLM provider, supplied by the provider itself.

A descriptor is the whole extension point: implement it, register it (by listing it in an Llm4sProviderModule, or by handing it to ProviderRegistry.of), and the provider becomes reachable from configuration, validation, client construction and model discovery without editing anything in llm4s-core. Before this existed, adding a provider meant edits to roughly eight shared files — see #1131.

Attributes

Example

object BedrockProvider extends ProviderDescriptor:
 val id         = ProviderId("bedrock")
 val configSpec = ProviderConfigSpec(
   extras = Seq(
     ProviderConfigKey.required("region", "the AWS region hosting the model, e.g. us-east-1"),
     ProviderConfigKey.optional("profile", "the AWS named profile to authenticate with")
   )
 )
 def buildConfig(providerName: String, section: NamedProviderConfig)(using
   ContextWindowResolver
 ): Result[ProviderConfig] =
   ProviderDescriptor
     .requireExtra(providerName, section, "region")
     .flatMap(region => BedrockConfig.fromValues(section.model.asString, region, section.extra("profile")))
 def buildClient(config: ProviderConfig, options: LlmClientOptions)(using
   ModelRegistryService
 ): Result[LLMClient] =
   ProviderDescriptor.expectConfig[BedrockConfig](id, config).flatMap(BedrockClient(_, options.metrics))

Companion

object

Graph

Supertypes

class Object

trait Matchable

class Any

Known subtypes

object AnthropicProvider

object AzureProvider

object BedrockProvider

object CohereProvider

object DeepSeekProvider

object GeminiProvider

object MistralProvider

object OllamaProvider

object OpenAICompatibleProvider

object OpenAIProvider

object OpenRouterProvider

object RequestyProvider

object VertexAIProvider

object WatsonXProvider

object ZaiProvider

Show all

Members list

Value members

Abstract methods

Constructs the client for a ProviderConfig this provider produced.

config is whatever the caller passed, so implementations must check the type rather than cast — ProviderDescriptor.expectConfig does that and produces the standard mismatch error.

Attributes

Turns a validated config section into the runtime ProviderConfig for this provider.

The section has already been checked against configSpec, so required fields are present and section.extras holds exactly the declared provider-specific keys that have a value (defaults applied, deprecated aliases resolved). A Left here means something configSpec cannot express (a malformed value, say).

Value parameters

providerName: the user's instance name (llm4s.providers.<name>), for error messages.

Attributes

Which config fields this provider requires, its default endpoint, and the provider-specific keys (ProviderConfigSpec.extras) its section accepts.

Attributes

Canonical id, e.g. ProviderId("openai"). Must be unique within a registry.

Attributes

Concrete methods

Alternative spellings accepted in provider = "...", folded onto id.

For example Gemini accepts "google". Aliases are matched after the same trim/lowercase canonicalisation as id itself.

Attributes

What this provider's client implements. Defaults to the full interface.

Attributes

Live model discovery, when the provider's API offers it.

Attributes

In this article

Generated with