Serialized Form

Package xyz.felh.openai

Class xyz.felh.openai.DeleteResponse extends java.lang.Object implements Serializable

Serialized Fields

id

java.lang.String id

The id of the object.

object

java.lang.String object

The type of object deleted, for example "file" or "model"

deleted

boolean deleted

True if successfully deleted

Class xyz.felh.openai.OpenAiApiListResponse extends java.lang.Object implements Serializable

Serialized Fields

object

java.lang.String object

always "list"

data

java.util.List<E> data

A list containing the actual results

Class xyz.felh.openai.OpenAiApiObjectWithId extends java.lang.Object implements Serializable

Serialized Fields

id

java.lang.String id

An identifier for this model, used to specify the model when making completions, etc

object

java.lang.String object

The type of object returned

Class xyz.felh.openai.OpenAiError extends java.lang.Object implements Serializable

Serialized Fields

error

OpenAiError.ErrorDetail error

Class xyz.felh.openai.OpenAiError.ErrorDetail extends java.lang.Object implements Serializable

Serialized Fields

message

java.lang.String message

Human-readable error message

type

java.lang.String type

OpenAI error type, for example "invalid_request_error" https://platform.openai.com/docs/guides/error-codes/python-library-error-types

param

java.lang.String param

code

java.lang.String code

OpenAI error code, for example "invalid_api_key"

Class xyz.felh.openai.OpenAiHttpException extends java.lang.RuntimeException implements Serializable

Serialized Fields

statusCode

int statusCode

HTTP status code

code

java.lang.String code

OpenAI error code, for example "invalid_api_key"

param

java.lang.String param

type

java.lang.String type

OpenAI error type, for example "invalid_request_error" https://platform.openai.com/docs/guides/error-codes/python-library-error-types

Class xyz.felh.openai.Usage extends java.lang.Object implements Serializable

Serialized Fields

promptTokens

java.lang.Long promptTokens

The number of prompt tokens used.

completionTokens

java.lang.Long completionTokens

The number of completion tokens used.

totalTokens

java.lang.Long totalTokens

The number of total tokens used

Package xyz.felh.openai.audio

Class xyz.felh.openai.audio.AudioResponse extends java.lang.Object implements Serializable

Serialized Fields

text

java.lang.String text

Class xyz.felh.openai.audio.CreateAudioTranscriptionRequest extends CreateAudioTranslationRequest implements Serializable

Serialized Fields

language

java.lang.String language

Optional The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

Class xyz.felh.openai.audio.CreateAudioTranslationRequest extends java.lang.Object implements Serializable

Serialized Fields

filePath

java.lang.String filePath

Required must set filePath or file The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.

file

byte[] file

model

java.lang.String model

Required ID of the model to use. Only whisper-1 is currently available.

prompt

java.lang.String prompt

Optional An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

responseFormat

java.lang.String responseFormat

Optional Defaults to json The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.

temperature

java.lang.Double temperature

Optional Defaults to 0 The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

Package xyz.felh.openai.completion

Class xyz.felh.openai.completion.BaseCreateCompletionRequest extends java.lang.Object implements Serializable

Serialized Fields

model

java.lang.String model

ID of the model to use. Currently, only gpt-3.5-turbo and gpt-3.5-turbo-0301 are supported.

temperature

java.lang.Double temperature

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both. Optional Defaults to 1

topP

java.lang.Double topP

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. Optional Defaults to 1

n

java.lang.Integer n

How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop. Optional Defaults to 1

stream

java.lang.Boolean stream

Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Optional Defaults to false

stop

java.lang.String stop

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. string or array Optional Defaults to null

maxTokens

java.lang.Integer maxTokens

The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). Optional Defaults to 16

presencePenalty

java.lang.Double presencePenalty

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. See more information about frequency and presence penalties. Optional Defaults to 0

frequencyPenalty

java.lang.Double frequencyPenalty

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. See more information about frequency and presence penalties. Optional Defaults to 0

logitBias

java.util.Map<K,V> logitBias

Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.

Optional Defaults to null

user

java.lang.String user

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more. Optional

Class xyz.felh.openai.completion.Completion extends OpenAiApiObjectWithId implements Serializable

Serialized Fields

created

java.lang.Long created

model

java.lang.String model

choices

java.util.List<E> choices

usage

Usage usage

Class xyz.felh.openai.completion.CompletionChoice extends java.lang.Object implements Serializable

Serialized Fields

text

java.lang.String text

index

java.lang.Integer index

logprobs

Logprobs logprobs

finishReason

java.lang.String finishReason

Class xyz.felh.openai.completion.CreateCompletionRequest extends BaseCreateCompletionRequest implements Serializable

Serialized Fields

prompt

java.lang.String prompt

The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. string or array Optional Defaults to <|endoftext|>

suffix

java.lang.String suffix

The suffix that comes after a completion of inserted text. Optional Defaults to null

logprobs

java.lang.Integer logprobs

Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5. If you need more than this, please contact us through our Help center and describe your use case. Optional Defaults to null

echo

java.lang.Boolean echo

Echo back the prompt in addition to the completion Optional Defaults to false

bestOf

java.lang.Integer bestOf

Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop. Optional Defaults to 1

Class xyz.felh.openai.completion.Logprobs extends java.lang.Object implements Serializable

Serialized Fields

tokens

java.util.List<E> tokens

tokenLogprobs

java.util.List<E> tokenLogprobs

topLogprobs

java.util.List<E> topLogprobs

textOffset

java.util.List<E> textOffset

Package xyz.felh.openai.completion.chat

Class xyz.felh.openai.completion.chat.ChatCompletion extends OpenAiApiObjectWithId implements Serializable

Serialized Fields

created

java.lang.Long created

model

java.lang.String model

choices

java.util.List<E> choices

usage

Usage usage

Class xyz.felh.openai.completion.chat.ChatCompletionChoice extends java.lang.Object implements Serializable

Serialized Fields

index

java.lang.Integer index

message

ChatMessage message

delta

ChatMessage delta

finishReason

java.lang.String finishReason

Class xyz.felh.openai.completion.chat.CreateChatCompletionRequest extends BaseCreateCompletionRequest implements Serializable

Serialized Fields

messages

java.util.List<E> messages

The messages to generate chat completions for, in the chat format.
see ChatMessage

functions

java.util.List<E> functions

A list of functions the model may generate JSON inputs for.

functionCall

java.lang.Object functionCall

Controls how the model responds to function calls. "none" means the model does not call a function, and responds to the end-user. "auto" means the model can pick between an end-user or calling a function. Specifying a particular function via {"name":\ "my_function"} forces the model to call that function. "none" is the default when no functions are present. "auto" is the default if functions are present.

Package xyz.felh.openai.edit

Class xyz.felh.openai.edit.CreateEditRequest extends java.lang.Object implements Serializable

Serialized Fields

model

java.lang.String model

string Required ID of the model to use. You can use the text-davinci-edit-001 or code-davinci-edit-001 model with this endpoint.

input

java.lang.String input

Optional Defaults to '' The input text to use as a starting point for the edit.

instruction

java.lang.String instruction

Required The instruction that tells the model how to edit the prompt.

n

java.lang.Integer n

Optional Defaults to 1 How many edits to generate for the input and instruction.

temperature

java.lang.Double temperature

Optional Defaults to 1 What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

We generally recommend altering this or top_p but not both.

topP

java.lang.Double topP

Optional Defaults to 1 An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

Class xyz.felh.openai.edit.Edit extends java.lang.Object implements Serializable

Serialized Fields

object

java.lang.String object

The type of object returned, always "edit"

created

java.lang.Long created

The creation time in epoch seconds.

choices

java.util.List<E> choices

usage

Usage usage

Class xyz.felh.openai.edit.EditChoice extends java.lang.Object implements Serializable

Serialized Fields

text

java.lang.String text

index

java.lang.Integer index

Package xyz.felh.openai.embedding

Class xyz.felh.openai.embedding.CreateEmbeddingRequest extends java.lang.Object implements Serializable

Serialized Fields

model

java.lang.String model

Required ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

input

java.lang.String input

string or array Required Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings for multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed 8192 tokens in length.

user

java.lang.String user

Optional A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Class xyz.felh.openai.embedding.CreateEmbeddingResponse extends java.lang.Object implements Serializable

Serialized Fields

model

java.lang.String model

object

java.lang.String object

data

java.util.List<E> data

usage

Usage usage

Class xyz.felh.openai.embedding.Embedding extends java.lang.Object implements Serializable

Serialized Fields

object

java.lang.String object

embedding

java.util.List<E> embedding

index

java.lang.Integer index

Package xyz.felh.openai.file

Class xyz.felh.openai.file.File extends OpenAiApiObjectWithId implements Serializable

Serialized Fields

bytes

java.lang.Long bytes

File size in bytes.

createdAt

java.lang.Long createdAt

The creation time in epoch seconds.

filename

java.lang.String filename

The name of the file.

purpose

java.lang.String purpose

Description of the file's purpose.

Class xyz.felh.openai.file.RetrieveFileContentResponse extends java.lang.Object implements Serializable

Serialized Fields

prompt

java.lang.String prompt

completion

java.lang.String completion

Package xyz.felh.openai.finetune

Class xyz.felh.openai.finetune.CreateFineTuneRequest extends java.lang.Object implements Serializable

Serialized Fields

trainingFile

java.lang.String trainingFile

The ID of an uploaded file that contains training data.

validationFile

java.lang.String validationFile

The ID of an uploaded file that contains validation data.

model

java.lang.String model

The name of the base model to fine-tune. You can select one of "ada", "babbage", "curie", or "davinci". To learn more about these models, see the Engines documentation.

nEpochs

java.lang.Integer nEpochs

The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

batchSize

java.lang.Integer batchSize

The batch size to use for training. The batch size is the number of training examples used to train a single forward and backward pass.

By default, the batch size will be dynamically configured to be ~0.2% of the number of examples in the training set, capped at 256 - in general, we've found that larger batch sizes tend to work better for larger datasets.

learningRateMultiplier

java.lang.Double learningRateMultiplier

The learning rate multiplier to use for training. The fine-tuning learning rate is the original learning rate used for pretraining multiplied by this value.

By default, the learning rate multiplier is the 0.05, 0.1, or 0.2 depending on final batch_size (larger learning rates tend to perform better with larger batch sizes). We recommend experimenting with values in the range 0.02 to 0.2 to see what produces the best results.

promptLossWeight

java.lang.Double promptLossWeight

The weight to use for loss on the prompt tokens. This controls how much the model tries to learn to generate the prompt (as compared to the completion which always has a weight of 1.0), and can add a stabilizing effect to training when completions are short.

If prompts are extremely long (relative to completions), it may make sense to reduce this weight so as to avoid over-prioritizing learning the prompt.

computeClassificationMetrics

java.lang.Boolean computeClassificationMetrics

If set, we calculate classification-specific metrics such as accuracy and F-1 score using the validation set at the end of every epoch. These metrics can be viewed in the results file.

In order to compute classification metrics, you must provide a validation_file. Additionally, you must specify CreateFineTuneRequest.classificationNClasses for multiclass classification or CreateFineTuneRequest.classificationPositiveClass for binary classification.

classificationNClasses

java.lang.Integer classificationNClasses

The number of classes in a classification task.

This parameter is required for multiclass classification.

classificationPositiveClass

java.lang.String classificationPositiveClass

The positive class in binary classification.

This parameter is needed to generate precision, recall, and F1 metrics when doing binary classification.

classificationBetas

java.util.List<E> classificationBetas

If this is provided, we calculate F-beta scores at the specified beta values. The F-beta score is a generalization of F-1 score. This is only used for binary classification.

With a beta of 1 (i.e. the F-1 score), precision and recall are given the same weight. A larger beta score puts more weight on recall and less on precision. A smaller beta score puts more weight on precision and less on recall.

suffix

java.lang.String suffix

A string of up to 40 characters that will be added to your fine-tuned model name.

Class xyz.felh.openai.finetune.FineTune extends OpenAiApiObjectWithId implements Serializable

Serialized Fields

model

java.lang.String model

The name of the base model.

createdAt

java.lang.Long createdAt

The creation time in epoch seconds.

events

java.util.List<E> events

List of events in this job's lifecycle. Null when getting a list of fine-tune jobs.

fineTunedModel

java.lang.String fineTunedModel

The ID of the fine-tuned model, null if tuning job is not finished. This is the id used to call the model.

hyperparams

HyperParameters hyperparams

The specified hyper-parameters for the tuning job.

organizationId

java.lang.String organizationId

The ID of the organization this model belongs to.

resultFiles

java.util.List<E> resultFiles

Result files for this fine-tune job.

status

java.lang.String status

The status os the fine-tune job. "pending", "succeeded", or "cancelled"

trainingFiles

java.util.List<E> trainingFiles

Training files for this fine-tune job.

updatedAt

java.lang.Long updatedAt

The last update time in epoch seconds.

validationFiles

java.util.List<E> validationFiles

Class xyz.felh.openai.finetune.FineTuneEvent extends java.lang.Object implements Serializable

Serialized Fields

object

java.lang.String object

The type of object returned, should be "fine-tune-event".

createdAt

java.lang.Long createdAt

The creation time in epoch seconds.

level

java.lang.String level

The log level of this message.

message

java.lang.String message

The event message.

Class xyz.felh.openai.finetune.HyperParameters extends java.lang.Object implements Serializable

Serialized Fields

batchSize

java.lang.String batchSize

The batch size to use for training.

learningRateMultiplier

java.lang.Double learningRateMultiplier

The learning rate multiplier to use for training.

nEpochs

java.lang.Integer nEpochs

The number of epochs to train the model for.

promptLossWeight

java.lang.Double promptLossWeight

The weight to use for loss on the prompt tokens.

Package xyz.felh.openai.image

Class xyz.felh.openai.image.BaseCreateImageRequest extends java.lang.Object implements Serializable

Serialized Fields

n

java.lang.Integer n

Optional Defaults to 1 The number of images to generate. Must be between 1 and 10.

size

java.lang.String size

Optional Defaults to 1024x1024 The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.

responseFormat

java.lang.String responseFormat

Optional Defaults to url The format in which the generated images are returned. Must be one of url or b64_json.

user

java.lang.String user

Optional A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. learn more https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids

Class xyz.felh.openai.image.CreateImageRequest extends BaseCreateImageRequest implements Serializable

Serialized Fields

prompt

java.lang.String prompt

Required A text description of the desired image(s). The maximum length is 1000 characters.

Class xyz.felh.openai.image.Image extends java.lang.Object implements Serializable

Serialized Fields

url

java.lang.String url

b64Json

java.lang.String b64Json

Class xyz.felh.openai.image.ImageResponse extends java.lang.Object implements Serializable

Serialized Fields

created

java.lang.Long created

data

java.util.List<E> data

Package xyz.felh.openai.image.edit

Class xyz.felh.openai.image.edit.CreateImageEditRequest extends BaseCreateImageRequest implements Serializable

Serialized Fields

imagePath

java.lang.String imagePath

Required image or imagePath The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask.

image

byte[] image

mask

byte[] mask

Optional An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as image.

maskPath

java.lang.String maskPath

prompt

java.lang.String prompt

Required A text description of the desired image(s). The maximum length is 1000 characters.

Package xyz.felh.openai.image.variation

Class xyz.felh.openai.image.variation.CreateImageVariationRequest extends BaseCreateImageRequest implements Serializable

Serialized Fields

imagePath

java.lang.String imagePath

Required image or imagePath The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.

image

byte[] image

Package xyz.felh.openai.model

Class xyz.felh.openai.model.Model extends OpenAiApiObjectWithId implements Serializable

Serialized Fields

created

java.lang.Long created

ownedBy

java.lang.String ownedBy

permission

java.util.List<E> permission

root

java.lang.String root

parent

java.lang.String parent

Class xyz.felh.openai.model.Permission extends OpenAiApiObjectWithId implements Serializable

Serialized Fields

allowCreateEngine

java.lang.Boolean allowCreateEngine

allowSampling

java.lang.Boolean allowSampling

allowLogprobs

java.lang.Boolean allowLogprobs

allowSearchIndices

java.lang.Boolean allowSearchIndices

allowView

java.lang.Boolean allowView

allowFineTuning

java.lang.Boolean allowFineTuning

organization

java.lang.String organization

group

java.lang.String group

isBlocking

java.lang.Boolean isBlocking

Package xyz.felh.openai.moderation

Class xyz.felh.openai.moderation.CreateModerationRequest extends java.lang.Object implements Serializable

Serialized Fields

input

java.lang.String input

The input text to classify

model

java.lang.String model

Optional Defaults to text-moderation-latest Two content moderations models are available: text-moderation-stable and text-moderation-latest.

The default is text-moderation-latest which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use text-moderation-stable, we will provide advanced notice before updating the model. Accuracy of text-moderation-stable may be slightly lower than for text-moderation-latest.

Class xyz.felh.openai.moderation.CreateModerationResponse extends java.lang.Object implements Serializable

Serialized Fields

id

java.lang.String id

model

java.lang.String model

results

java.util.List<E> results

Class xyz.felh.openai.moderation.Moderation extends java.lang.Object implements Serializable

Serialized Fields

flagged

java.lang.Boolean flagged

Set to true if the model classifies the content as violating OpenAI's content policy, false otherwise

categories

ModerationCategories categories

Object containing per-category binary content policy violation flags. For each category, the value is true if the model flags the corresponding category as violated, false otherwise.

categoryScores

ModerationCategoryScores categoryScores

Object containing per-category raw scores output by the model, denoting the model's confidence that the input violates the OpenAI's policy for the category. The value is between 0 and 1, where higher values denote higher confidence. The scores should not be interpreted as probabilities.

Class xyz.felh.openai.moderation.ModerationCategories extends java.lang.Object implements Serializable

Serialized Fields

hate

boolean hate

hateThreatening

boolean hateThreatening

selfHarm

boolean selfHarm

sexual

boolean sexual

sexualMinors

boolean sexualMinors

violence

boolean violence

violenceGraphic

boolean violenceGraphic

Class xyz.felh.openai.moderation.ModerationCategoryScores extends java.lang.Object implements Serializable

Serialized Fields

hate

double hate

hateThreatening

double hateThreatening

selfHarm

double selfHarm

sexual

double sexual

sexualMinors

double sexualMinors

violence

double violence

violenceGraphic

double violenceGraphic