zvhpddlmZddlmZmZmZmZmZddlm Z m Z ddl Z ddl m Z ddlmZddlmZmZmZmZmZdd lmZmZmZdd lmZdd lmZmZdd lm Z m!Z!dd l"m#Z#m$Z$ddl%m&Z&ddl'm(Z(ddl)m*Z*ddgZ+GddeZ,GddeZ-GddZ.GddZ/GddZ0GddZ1y)) annotations)DictListUnionIterableOptional)LiteraloverloadN)_legacy_response)completion_create_params) NOT_GIVENBodyQueryHeadersNotGiven) required_argsmaybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)Stream AsyncStream)make_request_options) Completion) ChatCompletionStreamOptionsParam CompletionsAsyncCompletionsceZdZed dZeddZeeeeeeeeeeeeeeeeeddded ddZeeeeeeeeeeeeeeeeddded dd Zeeeeeeeeeeeeeeeeddded dd Ze ddggd eeeeeeeeeeeeeeeeddded dd Zy)r ct|Sa This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content. For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers )CompletionsWithRawResponseselfs T/var/www/html/luna/venv/lib/python3.12/site-packages/openai/resources/completions.pywith_raw_responsezCompletions.with_raw_responses*$//ct|Sz An alternative to `.with_raw_response` that doesn't eagerly read the response body. For more information, see https://www.github.com/openai/openai-python#with_streaming_response ) CompletionsWithStreamingResponser&s r(with_streaming_responsez#Completions.with_streaming_response&s055r*Nbest_ofechofrequency_penalty logit_biaslogprobs max_tokensnpresence_penaltyseedstopstreamstream_optionssuffix temperaturetop_puser extra_headers extra_query extra_bodytimeoutmodelpromptcyu3 Creates a completion for the provided prompt and parameters. 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'rDrEr0r1r2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCs r(createzCompletions.create/r r*r0r1r2r3r4r5r6r7r8r9r;r<r=r>r?r@rArBrCcyu3 Creates a completion for the provided prompt and parameters. 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 NrHr'rDrEr:r0r1r2r3r4r5r6r7r8r9r;r<r=r>r?r@rArBrCs r(rJzCompletions.createrKr*cyrNrHrOs r(rJzCompletions.createerKr*rDrEr:c 2|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|i| rtjntjt ||||t | xsdtt SNz /completionsrDrEr0r1r2r3r4r5r6r7r8r9r:r;r<r=r>r?)r@rArBrCF)bodyoptionscast_tor: stream_cls)_postrr CompletionCreateParamsStreaming"CompletionCreateParamsNonStreamingrrrrIs r(rJzCompletions.createsC:zz  UfwD  ():  !* !*'(8DDf%nf ";!"U#$D%*)HH-PP/2)+Q[el?Uj)A! ! r*)returnr%)r[r-.rDKUnion[str, Literal['gpt-3.5-turbo-instruct', 'davinci-002', 'babbage-002']]rECUnion[str, List[str], Iterable[int], Iterable[Iterable[int]], None]r0Optional[int] | NotGivenr1Optional[bool] | NotGivenr2Optional[float] | NotGivenr3#Optional[Dict[str, int]] | NotGivenr4r_r5r_r6r_r7rar8r_r90Union[Optional[str], List[str], None] | NotGivenr:z#Optional[Literal[False]] | NotGivenr;5Optional[ChatCompletionStreamOptionsParam] | NotGivenr<Optional[str] | NotGivenr=rar>rar?str | NotGivenr@Headers | NonerA Query | NonerB Body | NonerC'float | httpx.Timeout | None | NotGivenr[r).rDr]rEr^r: Literal[True]r0r_r1r`r2rar3rbr4r_r5r_r6r_r7rar8r_r9rcr;rdr<rer=rar>rar?rfr@rgrArhrBrirCrjr[zStream[Completion]).rDr]rEr^r:boolr0r_r1r`r2rar3rbr4r_r5r_r6r_r7rar8r_r9rcr;rdr<rer=rar>rar?rfr@rgrArhrBrirCrjr[Completion | Stream[Completion]).rDr]rEr^r0r_r1r`r2rar3rbr4r_r5r_r6r_r7rar8r_r9rcr:3Optional[Literal[False]] | Literal[True] | NotGivenr;rdr<rer=rar>rar?rfr@rgrArhrBrirCrjr[rm __name__ __module__ __qualname__rr)r.r rrJrrHr*r(r r ss0066 -6*38A:C-6/8&/7@)2AJ6?PY+42;,5()-$("&;D5X [X T X * X ( X 6X 8X +X -X  $X 5X 'X ?X 4X N!X ")#X $0%X &*'X ()X .&/X 0"1X 2 3X 495X 6 7X X t-6*38A:C-6/8&/7@)2AJPY+42;,5()-$("&;D5X [X T X  X * X (X 6X 8X +X -X  $X 5X 'X ?X N!X ")#X $0%X &*'X ()X .&/X 0"1X 2 3X 495X 6 7X X t-6*38A:C-6/8&/7@)2AJPY+42;,5()-$("&;D5X [X T X  X * X (X 6X 8X +X -X  $X 5X 'X ?X N!X ")#X $0%X &*'X ()X .&/X 0"1X 2 3X 495X 6 )7X X tGX&(EF -6*38A:C-6/8&/7@)2AJFOPY+42;,5()-$("&;D5= [= T = * = ( = 6= 8= += -=  $= 5= '= ?= D= N!= ")#= $0%= &*'= ()= .&/= 0"1= 2 3= 495= 6 )7= G= r*ceZdZed dZeddZeeeeeeeeeeeeeeeeeddded ddZeeeeeeeeeeeeeeeeddded dd Zeeeeeeeeeeeeeeeeddded dd Ze ddggd eeeeeeeeeeeeeeeeddded dd Zy)r!ct|Sr$)AsyncCompletionsWithRawResponser&s r(r)z"AsyncCompletions.with_raw_responseBs/t44r*ct|Sr,)%AsyncCompletionsWithStreamingResponser&s r(r.z(AsyncCompletions.with_streaming_responseLs5T::r*Nr/rDrEc KywrGrHrIs r(rJzAsyncCompletions.createU r rLc KywrNrHrOs r(rJzAsyncCompletions.createryrzc KywrNrHrOs r(rJzAsyncCompletions.createryrzrQc bK|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|i| rtjntjd{t ||||t | xsdtt d{S757wrS)rXrr rYrZrrrrIs r(rJzAsyncCompletions.create&s\:ZZ ,UfwD  ():  !* !*'(8DDf%nf ";!"U#$D%*)HH-PP/2)+Q[el?U":.A ! ! ! ! s$A3B/5B+ 60B/&B-'B/-B/)r[ru)r[rwr\).rDr]rEr^r:rkr0r_r1r`r2rar3rbr4r_r5r_r6r_r7rar8r_r9rcr;rdr<rer=rar>rar?rfr@rgrArhrBrirCrjr[zAsyncStream[Completion]).rDr]rEr^r:rlr0r_r1r`r2rar3rbr4r_r5r_r6r_r7rar8r_r9rcr;rdr<rer=rar>rar?rfr@rgrArhrBrirCrjr[$Completion | AsyncStream[Completion]).rDr]rEr^r0r_r1r`r2rar3rbr4r_r5r_r6r_r7rar8r_r9rcr:rnr;rdr<rer=rar>rar?rfr@rgrArhrBrirCrjr[r~rorHr*r(r!r!Ass55;; -6*38A:C-6/8&/7@)2AJ6?PY+42;,5()-$("&;D5X [X T X * X ( X 6X 8X +X -X  $X 5X 'X ?X 4X N!X ")#X $0%X &*'X ()X .&/X 0"1X 2 3X 495X 6 7X X t-6*38A:C-6/8&/7@)2AJPY+42;,5()-$("&;D5X [X T X  X * X (X 6X 8X +X -X  $X 5X 'X ?X N!X ")#X $0%X &*'X ()X .&/X 0"1X 2 3X 495X 6 !7X X t-6*38A:C-6/8&/7@)2AJPY+42;,5()-$("&;D5X [X T X  X * X (X 6X 8X +X -X  $X 5X 'X ?X N!X ")#X $0%X &*'X ()X .&/X 0"1X 2 3X 495X 6 .7X X tGX&(EF -6*38A:C-6/8&/7@)2AJFOPY+42;,5()-$("&;D5= [= T = * = ( = 6= 8= += -=  $= 5= '= ?= D= N!= ")#= $0%= &*'= ()= .&/= 0"1= 2 3= 495= 6 .7= G= r*ceZdZddZy)r%cZ||_tj|j|_yN) _completionsr to_raw_response_wrapperrJr' completionss r(__init__z#CompletionsWithRawResponse.__init__hs%'&>>     r*Nrr r[NonerprqrrrrHr*r(r%r%g r*r%ceZdZddZy)rucZ||_tj|j|_yr)rr async_to_raw_response_wrapperrJrs r(rz(AsyncCompletionsWithRawResponse.__init__qs%'&DD     r*Nrr!r[rrrHr*r(ruruprr*ruceZdZddZy)r-cF||_t|j|_yr)rrrJrs r(rz)CompletionsWithStreamingResponse.__init__zs'2     r*NrrrHr*r(r-r-yrr*r-ceZdZddZy)rwcF||_t|j|_yr)rrrJrs r(rz.AsyncCompletionsWithStreamingResponse.__init__s'8     r*NrrrHr*r(rwrwrr*rw)2 __future__rtypingrrrrrtyping_extensionsr r httpxr typesr _typesrrrrr_utilsrrr_compatr _resourcerr _responserr _streamingrr _base_clientrtypes.completionr/types.chat.chat_completion_stream_options_paramr__all__r r!r%rur-rwrHr*r(rs#88/ ,>>JJ%9X,*^ , -c /c Lc 'c L        r*