Optional
callbacks?: undefined | CallbacksCallbacks 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.
Optional
maxMaximum number of parallel calls to make.
Optional
metadata?: undefined | Record<string, unknown>Metadata for this call and any sub-calls (eg. a Chain calling an LLM). Keys should be strings, values should be JSON-serializable.
Optional
recursionMaximum number of times a call can recurse. If not provided, defaults to 25.
Optional
runUnique identifier for the tracer run for this call. If not provided, a new UUID will be generated.
Optional
runName for the tracer run for this call. Defaults to the name of the class.
Optional
signal?: undefined | AbortSignalAbort signal for this call. If provided, the call will be aborted when the signal is aborted.
Optional
stop?: undefined | string[]Stop tokens to use for this call. If not provided, the default stop tokens for the model will be used.
Optional
tags?: undefined | string[]Tags for this call and any sub-calls (eg. a Chain calling an LLM). You can use these to filter calls.
Optional
timeout?: undefined | numberTimeout for this call in milliseconds.
Optional
tool_Specifies how the chat model should use tools.
undefined
Possible values:
- "auto": The model may choose to use any of the provided tools, or none.
- "any": The model must use one of the provided tools.
- "none": The model must not use any tools.
- A string (not "auto", "any", or "none"): The name of a specific tool the model must use.
- An object: A custom schema specifying tool choice parameters. Specific to the provider.
Note: Not all providers support tool_choice. An error will be thrown
if used with an unsupported model.
Represents the call options for a base chat model.