序列化表格

程序包 org.elsfs.openai.exception

类org.elsfs.openai.exception.OpenaiException扩展Exception实现可序列化

程序包 org.elsfs.openai.request

类org.elsfs.openai.request.CommonRequest扩展Object实现可序列化

序列化字段

temperature

Float temperature

optional

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. 使用什么样的采样温度，介于0和2之间。值越高（如0.8），输出越随机，而值越低（如0.2），输出就越集中，确定性更强。

n

Integer n

optional How many answers to generate for each question. 每个问题要生成多少个答案。

stop

List<E> stop

optional *API将停止生成更多令牌的最多4个序列。返回的文本将不包含停止序列。

maxTokens

Integer maxTokens

optional The maximum number of tokens allowed for the generated answer 生成的答案允许的最大令牌数

logitBias

Map<K,V> logitBias

optional 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](/tokenizer?view=bpe) (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. 修改指定令牌出现在完成中的可能性。接受一个json对象，该对象将令牌（由GPT令牌化器中的令牌ID指定）映射到从-100到100的相关偏差值。您可以使用此[tokenizer工具]（/tokenizer？view=bpe）（适用于GPT-2和GPT-3）将文本转换为令牌ID。从数学上讲，在采样之前，将偏差添加到模型生成的logits中。每个模型的确切效果会有所不同，但-1到1之间的值应该会降低或增加选择的可能性；像-100或100这样的值应该导致对相关令牌的禁止或独占选择。例如，您可以传递“5025“：-100｝”以防止生成<|endoftext|>令牌。

user

String user

optional A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids). 代表您的最终用户的唯一标识符，可以帮助OpenAI监控和检测滥用。[了解更多信息]（/docs/guides/安全最佳实践/最终用户id）。

类org.elsfs.openai.request.CreateChatCompletionRequest扩展CommonRequest实现可序列化

序列化字段

model

String model

D of the model to use for completion. You can select one of `ada`, `babbage`, `curie`, or `davinci`. 要使用的模型的ID。目前，仅支持“gpt-3.5-turbo”和“gpt-3.5-turbo-0301”。

messages

List<E> messages

The messages to generate chat completions for, in the [chat format](/docs/guides/chat/introduction). 要为生成聊天完成的消息，格式为[聊天格式]（/docs/guideschat/introduction）。 https://platform.openai.com/docs/guides/chat

topP

Float topP

optional 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. 一种替代温度采样的方法，称为核采样，其中模型考虑具有top_p概率质量的令牌的结果。因此，0.1意味着只考虑包含前10%概率质量的代币。我们通常建议改变这个或“温度”，但不能同时改变。

stream

String stream

optional If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. 如果设置，将发送部分消息增量，就像在ChatGPT中一样。令牌将仅作为数据发送[服务器发送的事件](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)当它们变得可用时，流由“data:[DONE]”消息终止。

presencePenalty

Float presencePenalty

optional 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.](/docs/api-reference/parameter-details) *介于-2.0和2.0之间的数字。到目前为止，正值会根据新标记是否出现在文本中来惩罚它们，从而增加模型谈论新主题的可能性。[查看有关频率和存在惩罚的更多信息。]（/docs/api reference/parameter details）

frequencyPenalty

Float frequencyPenalty

optional 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.](/docs/api-reference/parameter-details) 介于-2.0和2.0之间的数字。到目前为止，正值会根据新标记在文本中的现有频率对其进行惩罚，从而降低模型逐字重复同一行的可能性。[查看有关频率和存在惩罚的更多信息。]（/docs/api reference/parameter details）

类org.elsfs.openai.request.CreateEditRequest扩展CommonRequest实现可序列化

序列化字段

model

String model

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

input

String input

optional The input text to use as a starting point for the edit.

instruction

String instruction

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

topP

String topP

程序包 org.elsfs.openai.response

类org.elsfs.openai.response.ListModelsResponse扩展Object实现可序列化

序列化字段

object

String object

data

List<E> data