OptionalcallbacksOptionalconfigurableRuntime values for attributes previously made configurable on this Runnable, or sub-Runnables.
OptionalheadersCustom headers to pass to the Anthropic API when making a request.
Optionalls_Describes the format of structured outputs. This should be provided if an output is considered to be structured
An object containing the method used for structured output (e.g., "jsonMode").
Optionalschema?: JsonSchema7TypeThe JSON schema describing the expected output structure.
OptionalmaxMaximum number of parallel calls to make.
OptionalmetadataMetadata for this call and any sub-calls (eg. a Chain calling an LLM). Keys should be strings, values should be JSON-serializable.
OptionalrecursionMaximum number of times a call can recurse. If not provided, defaults to 25.
OptionalrunUnique identifier for the tracer run for this call. If not provided, a new UUID will be generated.
OptionalrunName for the tracer run for this call. Defaults to the name of the class.
OptionalsignalAbort signal for this call. If provided, the call will be aborted when the signal is aborted.
OptionalstopStop tokens to use for this call. If not provided, the default stop tokens for the model will be used.
OptionalstreamWhether or not to include token usage data in streamed chunks.
OptionaltagsTags for this call and any sub-calls (eg. a Chain calling an LLM). You can use these to filter calls.
OptionaltimeoutTimeout for this call in milliseconds.
Optionaltool_Whether or not to specify what tool the model should use
Optionaltools
Callbacks for this call and any sub-calls (eg. a Chain calling an LLM). Tags are passed to all callbacks, metadata is passed to handle*Start callbacks.