interface TogetherAICallOptionsBaseLLMCallOptionsPick<TogetherAIInputs, "modelName" | "model" | "temperature" | "topP" | "topK" | "repetitionPenalty" | "logprobs" | "safetyModel" | "maxTokens" | "stop">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.
Runtime values for attributes previously made configurable on this Runnable, or sub-Runnables.
An integer that specifies how many top token log probabilities are included in the response for each token generation step.
Describes the format of structured outputs. This should be provided if an output is considered to be structured
Maximum number of parallel calls to make.
Limit the number of tokens generated.
The name of the model to query.
The name of the model to query.
Alias for model
Maximum number of times a call can recurse. If not provided, defaults to 25.
A number that controls the diversity of generated text by reducing the likelihood of repeated sequences. Higher values decrease repetition.
Unique identifier for the tracer run for this call. If not provided, a new UUID will be generated.
Name for the tracer run for this call. Defaults to the name of the class.
Run an LLM-based input-output safeguard model on top of any model.
Abort signal for this call. If provided, the call will be aborted when the signal is aborted.
Stop tokens to use for this call. If not provided, the default stop tokens for the model will be used.
A decimal number that determines the degree of randomness in the response. A value of 1 will always yield the same output. A temperature less than 1 favors more correctness and is appropriate for question answering or summarization. A value greater than 1 introduces more randomness in the output.
Timeout for this call in milliseconds.
The topK parameter is used to limit the number of choices for the next predicted word or token.
It specifies the maximum number of tokens to consider at each step, based on their probability of occurrence.
This technique helps to speed up the generation process and can improve the quality of the generated text by focusing on the most likely options.
The topP (nucleus) parameter is used to dynamically adjust the number of choices for each predicted token based on the cumulative probabilities.
It specifies a probability threshold, below which all less likely tokens are filtered out.
This technique helps to maintain diversity and generate more fluent and natural-sounding text.