llm4s-core
API
Generated with
llm4s-core/org.llm4s/org.llm4s.config/Llm4sConfig

Llm4sConfig

org.llm4s.config.Llm4sConfig
object Llm4sConfig

Application-edge configuration loader for LLM4S.

Reads all runtime configuration from environment variables and system properties via PureConfig. This is the single authorised entry point for configuration in application and test code — never read sys.env, System.getenv, or ConfigFactory.load() directly.

== Provider setup == Set LLM_MODEL to provider/model (e.g. "openai/gpt-4o", "anthropic/claude-sonnet-4-5-latest", "gemini/gemini-2.0-flash") and the corresponding API key environment variable. Then call provider to obtain a org.llm4s.llmconnect.config.ProviderConfig ready for org.llm4s.llmconnect.LLMConnect.getClient.

Attributes

See also

org.llm4s.config.ConfigKeys for the full list of recognised environment variable names.

Example 
for {
 cfg    <- Llm4sConfig.provider()
 client <- LLMConnect.getClient(cfg)
 agent  = new Agent(client)
 state  <- agent.run("Hello", ToolRegistry.empty)
} yield state
Graph
Supertypes
class Object
trait Matchable
class Any
Self type

Members list

Type members

Classlikes

final case class EmbeddingsChunkingSettings(enabled: Boolean, size: Int, overlap: Int)

Attributes

Supertypes
trait Serializable
trait Product
trait Equals
class Object
trait Matchable
class Any
Show all
final case class EmbeddingsInputSettings(inputPath: Option[String], inputPaths: Option[String], query: Option[String])

Attributes

Supertypes
trait Serializable
trait Product
trait Equals
class Object
trait Matchable
class Any
Show all
final case class EmbeddingsUiSettings(maxRowsPerFile: Int, topDimsPerRow: Int, globalTopK: Int, showGlobalTop: Boolean, colorEnabled: Boolean, tableWidth: Int)

Attributes

Supertypes
trait Serializable
trait Product
trait Equals
class Object
trait Matchable
class Any
Show all
final case class TextEmbeddingModelSettings(provider: String, modelName: String, dimensions: Int)

Attributes

Supertypes
trait Serializable
trait Product
trait Equals
class Object
trait Matchable
class Any
Show all

Value members

Concrete methods

def embeddings(): Result[(String, EmbeddingProviderConfig)]

Loads the active embedding provider and its configuration from the current environment.

Loads the active embedding provider and its configuration from the current environment.

Reads EMBEDDING_MODEL in provider/model format (e.g. "openai/text-embedding-3-small", "voyage/voyage-3", "ollama/nomic-embed-text"). Returns the provider name and typed config.

Attributes

Returns

a pair of (providerName, EmbeddingProviderConfig), or a org.llm4s.error.ConfigurationError when EMBEDDING_MODEL is absent or the provider is unrecognised.

def exchangeLogging(): Result[ProviderExchangeLogging]

Loads provider exchange logging configuration from the current environment.

Loads provider exchange logging configuration from the current environment.

Reads the optional llm4s.exchangeLogging section. When absent or disabled, exchange logging remains off. When enabled, a JSONL sink is constructed from a configured directory and writes to a new per-run file.

Attributes

def experimentalStubsEnabled: Boolean

Returns true when experimental embedding stubs are enabled.

Returns true when experimental embedding stubs are enabled.

Controlled by the llm4s.embeddings.experimentalStubs config key. Defaults to false when the key is absent.

Attributes

def loadBraveSearchTool(): Result[BraveSearchToolConfig]

Load Brave Search API configuration.

Load Brave Search API configuration.

Requires BRAVE_SEARCH_API_KEY environment variable.

Attributes

Returns

Result containing BraveSearchToolConfig with API key and settings

def loadDuckDuckGoSearchTool(): Result[DuckDuckGoSearchToolConfig]

Load DuckDuckGo Search configuration.

Load DuckDuckGo Search configuration.

No API key required.

Attributes

Returns

Result containing DuckDuckGoSearchToolConfig with settings

def loadEmbeddingsChunking(): Result[EmbeddingsChunkingSettings]

Loads text-chunking settings for the embeddings pipeline from the current environment.

Loads text-chunking settings for the embeddings pipeline from the current environment.

Reads CHUNK_SIZE, CHUNK_OVERLAP, and CHUNKING_ENABLED, applying defaults of 1000, 100, and true respectively when variables are absent.

Attributes

Returns

chunking settings; always returns Right — missing variables fall back to defaults rather than failing.

def loadEmbeddingsInputs(): Result[EmbeddingsInputSettings]

Loads input path and query settings for the embeddings pipeline from the current environment.

Loads input path and query settings for the embeddings pipeline from the current environment.

Reads EMBEDDING_INPUT_PATH, llm4s.embeddings.inputPaths, and EMBEDDING_QUERY. All fields are optional; returns Right with None values when variables are absent.

Attributes

def loadEmbeddingsUiSettings(): Result[EmbeddingsUiSettings]

Loads UI display settings for the embeddings explorer from the current environment.

Loads UI display settings for the embeddings explorer from the current environment.

Applies defaults when variables are absent: maxRowsPerFile=200, topDimsPerRow=6, globalTopK=10, showGlobalTop=false, colorEnabled=true, tableWidth=120.

Attributes

Returns

UI settings; always returns Right — missing variables fall back to defaults rather than failing.

def loadExaSearchTool(): Result[ExaSearchToolConfig]

Load Exa Search API configuration.

Load Exa Search API configuration.

Requires EXA_API_KEY environment variable.

Attributes

Returns

Result containing ExaSearchToolConfig with API key and settings

def loadTextEmbeddingModel(): Result[TextEmbeddingModelSettings]

Loads and resolves the active embedding model, including its output dimensions.

Loads and resolves the active embedding model, including its output dimensions.

Reads EMBEDDING_MODEL and looks up the known dimension count for the provider/model combination from the bundled dimension registry.

Attributes

Returns

the resolved settings, or a org.llm4s.error.ConfigurationError when EMBEDDING_MODEL is absent or unrecognised.

def localEmbeddingModels(): Result[LocalEmbeddingModels]

Loads configuration for locally-available embedding models from the current environment.

Loads configuration for locally-available embedding models from the current environment.

Attributes

Returns

the local model configuration, or a org.llm4s.error.ConfigurationError when required variables are missing.

def metrics(): Result[(MetricsCollector, Option[PrometheusEndpoint])]

Load the metrics configuration.

Load the metrics configuration.

Returns a MetricsCollector and optional PrometheusEndpoint if metrics are enabled. Use MetricsCollector.noop if you want to disable metrics programmatically.

Attributes

Returns

Result containing (MetricsCollector, Option[PrometheusEndpoint])

def modelMetadataOverridePath: Option[String]

Returns the path to a user-supplied model-metadata override file, if configured.

Returns the path to a user-supplied model-metadata override file, if configured.

When set via llm4s.modelMetadata.file, the override file is consulted before the bundled model catalogue when resolving context-window sizes. Returns None when the key is absent or blank.

Attributes

def pgSearchIndex(): Result[PgConfig]

Loads PostgreSQL vector-search index configuration from the current environment.

Loads PostgreSQL vector-search index configuration from the current environment.

Attributes

Returns

the PgConfig, or a org.llm4s.error.ConfigurationError when required variables are missing.

def provider(): Result[ProviderConfig]

Loads LLM provider configuration from the current environment.

Loads LLM provider configuration from the current environment.

Reads LLM_MODEL (format: provider/model) and the matching credential variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.) to build a typed org.llm4s.llmconnect.config.ProviderConfig.

Attributes

Returns

the provider configuration, or a org.llm4s.error.ConfigurationError when required variables are missing or the provider prefix is unrecognised.

def tracing(): Result[TracingSettings]

Loads tracing configuration from the current environment.

Loads tracing configuration from the current environment.

Reads TRACING_MODE (langfuse, opentelemetry, console, or none) and the backend-specific variables (Langfuse keys, OTLP endpoint, etc.).

Attributes

Returns

the tracing settings, or a org.llm4s.error.ConfigurationError when a required backend variable is missing.

Generated with