o RWj@sTddlmZddlmZmZmZmZddlmZm Z ddl Z ddl m Z ddl mZddlmZmZmZmZmZmZmZmZdd lmZmZmZdd lmZdd lmZm Z dd l!m"Z"m#Z#dd l$m%Z%m&Z&ddl'm(Z(ddl)m*Z*ddl+m,Z,ddgZ-GdddeZ.Gddde Z/GdddZ0GdddZ1GdddZ2GdddZ3dS)) annotations)DictUnionIterableOptional)LiteraloverloadN)_legacy_response)completion_create_params)BodyOmitQueryHeadersNotGivenSequenceNotStromit not_given) required_argsmaybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)Stream AsyncStream)make_request_options) Completion) ChatCompletionStreamOptionsParam CompletionsAsyncCompletionsc@eZdZdZed=ddZed>ddZeeeeeeeeeeeeeeeeed d d e d d?d1d2Z eeeeeeeeeeeeeeeed d d e d3d@d6d2Z eeeeeeeeeeeeeeeed d d e d3dAd9d2Z e d d ggd:eeeeeeeeeeeeeeeed d d e d dBdOptional[Literal[False]] | Omitr?1Optional[ChatCompletionStreamOptionsParam] | Omitr@Optional[str] | OmitrArBrC str | OmitrDHeaders | NonerE Query | NonerF Body | NonerG'float | httpx.Timeout | None | NotGivenrcCdSu Creates a completion for the provided prompt and parameters. Returns a completion object, or a sequence of completion objects if the request is streamed. Args: model: ID of the model to use. You can use the [List models](https://platform.openai.com/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](https://platform.openai.com/docs/models) for descriptions of them. 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. best_of: 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: Echo back the prompt in addition to the completion frequency_penalty: 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.](https://platform.openai.com/docs/guides/text-generation) logit_bias: 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) 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: 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. max_tokens: The maximum number of [tokens](/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](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. 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`. presence_penalty: 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.](https://platform.openai.com/docs/guides/text-generation) 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: Not supported with latest reasoning models `o3` and `o4-mini`. Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. stream: Whether to stream back partial progress. If set, 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. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). stream_options: Options for streaming response. Only set this when you set `stream: true`. suffix: The suffix that comes after a completion of inserted text. This parameter is only supported for `gpt-3.5-turbo-instruct`. 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. top_p: 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: 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). extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Nr+r*rHrJr4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrErFrGr+r+r,create3zCompletions.creater4r5r6r7r8r9r:r;r<r=r?r@rArBrCrDrErFrG Literal[True]Stream[Completion]cCrYu Creates a completion for the provided prompt and parameters. Returns a completion object, or a sequence of completion objects if the request is streamed. Args: model: ID of the model to use. You can use the [List models](https://platform.openai.com/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](https://platform.openai.com/docs/models) for descriptions of them. 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. stream: Whether to stream back partial progress. If set, 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. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). best_of: 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: Echo back the prompt in addition to the completion frequency_penalty: 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.](https://platform.openai.com/docs/guides/text-generation) logit_bias: 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) 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: 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. max_tokens: The maximum number of [tokens](/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](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. 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`. presence_penalty: 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.](https://platform.openai.com/docs/guides/text-generation) 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: Not supported with latest reasoning models `o3` and `o4-mini`. Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. stream_options: Options for streaming response. Only set this when you set `stream: true`. suffix: The suffix that comes after a completion of inserted text. This parameter is only supported for `gpt-3.5-turbo-instruct`. 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. top_p: 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: 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). extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Nr+r*rHrJr>r4r5r6r7r8r9r:r;r<r=r?r@rArBrCrDrErFrGr+r+r,r\r]boolCompletion | Stream[Completion]cCrYrar+rbr+r+r,r\or]rHrJr>/Optional[Literal[False]] | Literal[True] | Omitc Cs|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|i| rAtjntjt||||ddidt| pRdttdSNz /completionsrHrJr4r5r6r7r8r9r:r;r<r=r>r?r@rArBrC bearer_authT)rDrErFrGsecurityF)bodyoptionscast_tor> stream_cls)_postrr CompletionCreateParamsStreaming"CompletionCreateParamsNonStreamingrrrr[r+r+r,r\ sn     )r%r&)r%r/.rHrIrJrKr4rLr5rMr6rNr7rOr8rLr9rLr:rLr;rNr<rLr=rPr>rQr?rRr@rSrArNrBrNrCrTrDrUrErVrFrWrGrXr%r).rHrIrJrKr>r_r4rLr5rMr6rNr7rOr8rLr9rLr:rLr;rNr<rLr=rPr?rRr@rSrArNrBrNrCrTrDrUrErVrFrWrGrXr%r`).rHrIrJrKr>rcr4rLr5rMr6rNr7rOr8rLr9rLr:rLr;rNr<rLr=rPr?rRr@rSrArNrBrNrCrTrDrUrErVrFrWrGrXr%rd).rHrIrJrKr4rLr5rMr6rNr7rOr8rLr9rLr:rLr;rNr<rLr=rPr>rfr?rRr@rSrArNrBrNrCrTrDrUrErVrFrWrGrXr%rd __name__ __module__ __qualname____doc__rr-r1rrrr\rr+r+r+r,r!  c@r#)Cr"r$r%AsyncCompletionsWithRawResponsecCr'r()rxr)r+r+r,r-Wr.z"AsyncCompletions.with_raw_response%AsyncCompletionsWithStreamingResponsecCr'r0)ryr)r+r+r,r1ar2z(AsyncCompletions.with_streaming_responseNr3rHrIrJrKr4rLr5rMr6rNr7rOr8r9r:r;r<r=rPr>rQr?rRr@rSrArBrCrTrDrUrErVrFrWrGrXrcdSrZr+r[r+r+r,r\jzAsyncCompletions.creater^r_AsyncStream[Completion]crzrar+rbr+r+r,r\r{rc$Completion | AsyncStream[Completion]crzrar+rbr+r+r,r\r{rerfc s|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|i| rBtjntjIdHt||||ddidt| pVdttdIdHSrg)rnrr rorprrrr[r+r+r,r\Dsp      )r%rx)r%ryrq).rHrIrJrKr>r_r4rLr5rMr6rNr7rOr8rLr9rLr:rLr;rNr<rLr=rPr?rRr@rSrArNrBrNrCrTrDrUrErVrFrWrGrXr%r|).rHrIrJrKr>rcr4rLr5rMr6rNr7rOr8rLr9rLr:rLr;rNr<rLr=rPr?rRr@rSrArNrBrNrCrTrDrUrErVrFrWrGrXr%r}).rHrIrJrKr4rLr5rMr6rNr7rOr8rLr9rLr:rLr;rNr<rLr=rPr>rfr?rRr@rSrArNrBrNrCrTrDrUrErVrFrWrGrXr%r}rrr+r+r+r,r"Rrwc@eZdZdddZdS) r& completionsr!r%NonecC||_t|j|_dSN) _completionsr to_raw_response_wrapperr\r*rr+r+r,__init__ z#CompletionsWithRawResponse.__init__Nrr!r%rrsrtrurr+r+r+r,r&r&c@r~) rxrr"r%rcCrr)rr async_to_raw_response_wrapperr\rr+r+r,rrz(AsyncCompletionsWithRawResponse.__init__Nrr"r%rrr+r+r+r,rxrrxc@r~) r/rr!r%rcC||_t|j|_dSr)rrr\rr+r+r,r z)CompletionsWithStreamingResponse.__init__Nrrr+r+r+r,r/rr/c@r~) ryrr"r%rcCrr)rrr\rr+r+r,rrz.AsyncCompletionsWithStreamingResponse.__init__Nrrr+r+r+r,ryrry)4 __future__rtypingrrrrtyping_extensionsrrhttpxr typesr _typesr r rrrrrr_utilsrrr_compatr _resourcerr _responserr _streamingrr _base_clientrtypes.completionr/types.chat.chat_completion_stream_options_paramr __all__r!r"r&rxr/ryr+r+r+r,s<   (    ;;