Methods
ModelsExpand Collapse
type DpoHyperparametersResp struct{…}The hyperparameters used for the DPO fine-tuning job.
The hyperparameters used for the DPO fine-tuning job.
BatchSize DpoHyperparametersBatchSizeUnionRespoptionalNumber of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
Beta DpoHyperparametersBetaUnionRespoptionalThe beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.
The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.
type ReinforcementHyperparametersResp struct{…}The hyperparameters used for the reinforcement fine-tuning job.
The hyperparameters used for the reinforcement fine-tuning job.
BatchSize ReinforcementHyperparametersBatchSizeUnionRespoptionalNumber of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
ComputeMultiplier ReinforcementHyperparametersComputeMultiplierUnionRespoptionalMultiplier on amount of compute used for exploring search space during training.
Multiplier on amount of compute used for exploring search space during training.
EvalInterval ReinforcementHyperparametersEvalIntervalUnionRespoptionalThe number of training steps between evaluation runs.
The number of training steps between evaluation runs.
EvalSamples ReinforcementHyperparametersEvalSamplesUnionRespoptionalNumber of evaluation samples to generate per training step.
Number of evaluation samples to generate per training step.
LearningRateMultiplier ReinforcementHyperparametersLearningRateMultiplierUnionRespoptionalScaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
NEpochs ReinforcementHyperparametersNEpochsUnionRespoptionalThe number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
ReasoningEffort ReinforcementHyperparametersReasoningEffortoptionalLevel of reasoning effort.
Level of reasoning effort.
type ReinforcementMethod struct{…}Configuration for the reinforcement fine-tuning method.
Configuration for the reinforcement fine-tuning method.
Grader ReinforcementMethodGraderUnionThe grader used for the fine-tuning job.
The grader used for the fine-tuning job.
type StringCheckGrader struct{…}A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.
A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.
type TextSimilarityGrader struct{…}A TextSimilarityGrader object which grades text based on similarity metrics.
A TextSimilarityGrader object which grades text based on similarity metrics.
EvaluationMetric TextSimilarityGraderEvaluationMetricThe evaluation metric to use. One of cosine, fuzzy_match, bleu,
gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5,
or rouge_l.
The evaluation metric to use. One of cosine, fuzzy_match, bleu,
gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5,
or rouge_l.
type ScoreModelGrader struct{…}A ScoreModelGrader object that uses a model to assign a score to the input.
A ScoreModelGrader object that uses a model to assign a score to the input.
Input []ScoreModelGraderInputThe input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.
The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.
Content ScoreModelGraderInputContentUnionInputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.
Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.
type ScoreModelGraderInputContentInputImage struct{…}An image input block used within EvalItem content arrays.
An image input block used within EvalItem content arrays.
type ResponseInputAudio struct{…}An audio input to the model.
An audio input to the model.
type GraderInputs []GraderInputUnionA list of inputs, each of which may be either an input text, output text, input
image, or input audio object.
A list of inputs, each of which may be either an input text, output text, input image, or input audio object.
SamplingParams ScoreModelGraderSamplingParamsoptionalThe sampling parameters for the model.
The sampling parameters for the model.
The maximum number of tokens the grader model may generate in its response.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
type MultiGrader struct{…}A MultiGrader object combines the output of multiple graders to produce a single score.
A MultiGrader object combines the output of multiple graders to produce a single score.
Graders MultiGraderGradersUnionA StringCheckGrader object that performs a string comparison between input and reference using a specified operation.
A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.
type StringCheckGrader struct{…}A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.
A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.
type TextSimilarityGrader struct{…}A TextSimilarityGrader object which grades text based on similarity metrics.
A TextSimilarityGrader object which grades text based on similarity metrics.
EvaluationMetric TextSimilarityGraderEvaluationMetricThe evaluation metric to use. One of cosine, fuzzy_match, bleu,
gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5,
or rouge_l.
The evaluation metric to use. One of cosine, fuzzy_match, bleu,
gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5,
or rouge_l.
type ScoreModelGrader struct{…}A ScoreModelGrader object that uses a model to assign a score to the input.
A ScoreModelGrader object that uses a model to assign a score to the input.
Input []ScoreModelGraderInputThe input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.
The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.
Content ScoreModelGraderInputContentUnionInputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.
Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.
type ScoreModelGraderInputContentInputImage struct{…}An image input block used within EvalItem content arrays.
An image input block used within EvalItem content arrays.
type ResponseInputAudio struct{…}An audio input to the model.
An audio input to the model.
type GraderInputs []GraderInputUnionA list of inputs, each of which may be either an input text, output text, input
image, or input audio object.
A list of inputs, each of which may be either an input text, output text, input image, or input audio object.
SamplingParams ScoreModelGraderSamplingParamsoptionalThe sampling parameters for the model.
The sampling parameters for the model.
The maximum number of tokens the grader model may generate in its response.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
type LabelModelGrader struct{…}A LabelModelGrader object which uses a model to assign labels to each item
in the evaluation.
A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.
Input []LabelModelGraderInput
Content LabelModelGraderInputContentUnionInputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.
Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.
type LabelModelGraderInputContentInputImage struct{…}An image input block used within EvalItem content arrays.
An image input block used within EvalItem content arrays.
type ResponseInputAudio struct{…}An audio input to the model.
An audio input to the model.
type GraderInputs []GraderInputUnionA list of inputs, each of which may be either an input text, output text, input
image, or input audio object.
A list of inputs, each of which may be either an input text, output text, input image, or input audio object.
type SupervisedHyperparametersResp struct{…}The hyperparameters used for the fine-tuning job.
The hyperparameters used for the fine-tuning job.
BatchSize SupervisedHyperparametersBatchSizeUnionRespoptionalNumber of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.