Constructor Detail

Method Detail

• model

   final CompletionCreateParams.Body.Builder model(CompletionCreateParams.Model model)

  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.

• model

   final CompletionCreateParams.Body.Builder model(JsonField<CompletionCreateParams.Model> model)

  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.

• model

   final CompletionCreateParams.Body.Builder model(String value)

  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.

• prompt

   final CompletionCreateParams.Body.Builder prompt(CompletionCreateParams.Prompt 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.

• prompt

   final CompletionCreateParams.Body.Builder prompt(Optional<CompletionCreateParams.Prompt> 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.

• prompt

   final CompletionCreateParams.Body.Builder prompt(JsonField<CompletionCreateParams.Prompt> 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.

• prompt

   final CompletionCreateParams.Body.Builder prompt(String string)

  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.

• promptOfArrayOfStrings

   final CompletionCreateParams.Body.Builder promptOfArrayOfStrings(List<String> arrayOfStrings)

  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.

• promptOfArrayOfTokens

   final CompletionCreateParams.Body.Builder promptOfArrayOfTokens(List<Long> arrayOfTokens)

  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.

• promptOfArrayOfTokenArrays

   final CompletionCreateParams.Body.Builder promptOfArrayOfTokenArrays(List<List<Long>> arrayOfTokenArrays)

  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.

• bestOf

   final CompletionCreateParams.Body.Builder bestOf(Long 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.

• bestOf

   final CompletionCreateParams.Body.Builder bestOf(Long 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.

• bestOf

   final CompletionCreateParams.Body.Builder bestOf(Optional<Long> 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.

• bestOf

   final CompletionCreateParams.Body.Builder bestOf(JsonField<Long> 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.

• echo

   final CompletionCreateParams.Body.Builder echo(Boolean echo)

  Echo back the prompt in addition to the completion

• echo

   final CompletionCreateParams.Body.Builder echo(Boolean echo)

  Echo back the prompt in addition to the completion

• echo

   final CompletionCreateParams.Body.Builder echo(Optional<Boolean> echo)

  Echo back the prompt in addition to the completion

• echo

   final CompletionCreateParams.Body.Builder echo(JsonField<Boolean> echo)

  Echo back the prompt in addition to the completion

• frequencyPenalty

   final CompletionCreateParams.Body.Builder frequencyPenalty(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.

• frequencyPenalty

   final CompletionCreateParams.Body.Builder frequencyPenalty(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.

• frequencyPenalty

   final CompletionCreateParams.Body.Builder frequencyPenalty(Optional<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.

• frequencyPenalty

   final CompletionCreateParams.Body.Builder frequencyPenalty(JsonField<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.

• logitBias

   final CompletionCreateParams.Body.Builder logitBias(CompletionCreateParams.LogitBias 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?view=bpe 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.

• logitBias

   final CompletionCreateParams.Body.Builder logitBias(Optional<CompletionCreateParams.LogitBias> 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?view=bpe 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.

• logitBias

   final CompletionCreateParams.Body.Builder logitBias(JsonField<CompletionCreateParams.LogitBias> 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?view=bpe 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.

• logprobs

   final CompletionCreateParams.Body.Builder logprobs(Long logprobs)

  Include the log probabilities on the logprobs most likely output 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.

• logprobs

   final CompletionCreateParams.Body.Builder logprobs(Long logprobs)

  Include the log probabilities on the logprobs most likely output 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.

• logprobs

   final CompletionCreateParams.Body.Builder logprobs(Optional<Long> logprobs)

  Include the log probabilities on the logprobs most likely output 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.

• logprobs

   final CompletionCreateParams.Body.Builder logprobs(JsonField<Long> logprobs)

  Include the log probabilities on the logprobs most likely output 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.

• maxTokens

   final CompletionCreateParams.Body.Builder maxTokens(Long maxTokens)

  The maximum number of /tokenizer that can be generated in the completion.

  The token count of your prompt plus max_tokens cannot exceed the model's context length. Example Python code for counting tokens.

• maxTokens

   final CompletionCreateParams.Body.Builder maxTokens(Long maxTokens)

  The maximum number of /tokenizer that can be generated in the completion.

  The token count of your prompt plus max_tokens cannot exceed the model's context length. Example Python code for counting tokens.

• maxTokens

   final CompletionCreateParams.Body.Builder maxTokens(Optional<Long> maxTokens)

  The maximum number of /tokenizer that can be generated in the completion.

  The token count of your prompt plus max_tokens cannot exceed the model's context length. Example Python code for counting tokens.

• maxTokens

   final CompletionCreateParams.Body.Builder maxTokens(JsonField<Long> maxTokens)

  The maximum number of /tokenizer that can be generated in the completion.

  The token count of your prompt plus max_tokens cannot exceed the model's context length. Example Python code for counting tokens.

• n

   final CompletionCreateParams.Body.Builder n(Long 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.

• n

   final CompletionCreateParams.Body.Builder n(Long 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.

• n

   final CompletionCreateParams.Body.Builder n(Optional<Long> 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.

• n

   final CompletionCreateParams.Body.Builder n(JsonField<Long> 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.

• presencePenalty

   final CompletionCreateParams.Body.Builder presencePenalty(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.

• presencePenalty

   final CompletionCreateParams.Body.Builder presencePenalty(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.

• presencePenalty

   final CompletionCreateParams.Body.Builder presencePenalty(Optional<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.

• presencePenalty

   final CompletionCreateParams.Body.Builder presencePenalty(JsonField<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.

• seed

   final CompletionCreateParams.Body.Builder seed(Long seed)

  If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

  Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

• seed

   final CompletionCreateParams.Body.Builder seed(Long seed)

  If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

  Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

• seed

   final CompletionCreateParams.Body.Builder seed(Optional<Long> seed)

  If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

  Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

• seed

   final CompletionCreateParams.Body.Builder seed(JsonField<Long> seed)

  If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

  Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

• stop

   final CompletionCreateParams.Body.Builder stop(CompletionCreateParams.Stop stop)

  Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

• stop

   final CompletionCreateParams.Body.Builder stop(Optional<CompletionCreateParams.Stop> stop)

  Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

• stop

   final CompletionCreateParams.Body.Builder stop(JsonField<CompletionCreateParams.Stop> stop)

  Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

• stop

   final CompletionCreateParams.Body.Builder stop(String string)

  Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

• stopOfStrings

   final CompletionCreateParams.Body.Builder stopOfStrings(List<String> strings)

  Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

• streamOptions

   final CompletionCreateParams.Body.Builder streamOptions(ChatCompletionStreamOptions streamOptions)

  Options for streaming response. Only set this when you set stream: true.

• streamOptions

   final CompletionCreateParams.Body.Builder streamOptions(Optional<ChatCompletionStreamOptions> streamOptions)

  Options for streaming response. Only set this when you set stream: true.

• streamOptions

   final CompletionCreateParams.Body.Builder streamOptions(JsonField<ChatCompletionStreamOptions> streamOptions)

  Options for streaming response. Only set this when you set stream: true.

• suffix

   final CompletionCreateParams.Body.Builder suffix(String suffix)

  The suffix that comes after a completion of inserted text.

  This parameter is only supported for gpt-3.5-turbo-instruct.

• suffix

   final CompletionCreateParams.Body.Builder suffix(Optional<String> suffix)

  The suffix that comes after a completion of inserted text.

  This parameter is only supported for gpt-3.5-turbo-instruct.

• suffix

   final CompletionCreateParams.Body.Builder suffix(JsonField<String> suffix)

  The suffix that comes after a completion of inserted text.

  This parameter is only supported for gpt-3.5-turbo-instruct.

• temperature

   final CompletionCreateParams.Body.Builder temperature(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.

• temperature

   final CompletionCreateParams.Body.Builder temperature(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.

• temperature

   final CompletionCreateParams.Body.Builder temperature(Optional<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.

• temperature

   final CompletionCreateParams.Body.Builder temperature(JsonField<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.

• topP

   final CompletionCreateParams.Body.Builder topP(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.

• topP

   final CompletionCreateParams.Body.Builder topP(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.

• topP

   final CompletionCreateParams.Body.Builder topP(Optional<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.

• topP

   final CompletionCreateParams.Body.Builder topP(JsonField<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.

• user

   final CompletionCreateParams.Body.Builder user(String user)

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

• user

   final CompletionCreateParams.Body.Builder user(JsonField<String> user)

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

• additionalProperties

   final CompletionCreateParams.Body.Builder additionalProperties(Map<String, JsonValue> additionalProperties)

• putAdditionalProperty

   final CompletionCreateParams.Body.Builder putAdditionalProperty(String key, JsonValue value)

• putAllAdditionalProperties

   final CompletionCreateParams.Body.Builder putAllAdditionalProperties(Map<String, JsonValue> additionalProperties)

• removeAdditionalProperty

   final CompletionCreateParams.Body.Builder removeAdditionalProperty(String key)

• removeAllAdditionalProperties

   final CompletionCreateParams.Body.Builder removeAllAdditionalProperties(Set<String> keys)

• build

   final CompletionCreateParams.Body build()