a !fB@sddlmZddlmZmZmZmZmZmZddl m Z ddl Z ddl m Z mZddlmZmZmZmZmZddlmZmZdd lmZmZdd lmZmZdd lmZm Z dd l!m"Z"erdd l#m$Z$m%Z%ddgZ&GdddeZ'GdddeZ(GdddZ)GdddZ*dS)) annotations) TYPE_CHECKINGDictListUnionOptionaloverload)LiteralN) Completioncompletion_create_params) NOT_GIVENBodyQueryHeadersNotGiven) required_argsmaybe_transform)SyncAPIResourceAsyncAPIResource)to_raw_response_wrapperasync_to_raw_response_wrapper)Stream AsyncStream)make_request_options)OpenAI AsyncOpenAI CompletionsAsyncCompletionscseZdZUded<dddfdd Zeeeeeeeeeeeeeeeeddded d d d d ddd d d dd ddddddddddddddZeeeeeeeeeeeeeeedddedd d dd d ddd d d dd dddddddddddd dZeeeeeeeeeeeeeeedddedd d d!d d ddd d d dd dddddddddd"dd#dZed$d%ggd&eeeeeeeeeeeeeeeddded d d d d ddd d d dd dd'ddddddddd"dd(dZZ S))rCompletionsWithRawResponsewith_raw_responserNoneclientreturncst|t||_dSN)super__init__rr selfr# __class__]/var/www/html/python-backend/venv/lib/python3.9/site-packages/openai/resources/completions.pyr's zCompletions.__init__Nbest_ofechofrequency_penalty logit_biaslogprobs max_tokensnpresence_penaltyseedstopstreamsuffix temperaturetop_puser extra_headers extra_query extra_bodytimeoutUnion[str, Literal['babbage-002', 'davinci-002', 'gpt-3.5-turbo-instruct', 'text-davinci-003', 'text-davinci-002', 'text-davinci-001', 'code-davinci-002', 'text-curie-001', 'text-babbage-001', 'text-ada-001']]7Union[str, List[str], List[int], List[List[int]], None]Optional[int] | NotGivenOptional[bool] | NotGivenOptional[float] | NotGiven#Optional[Dict[str, int]] | NotGiven0Union[Optional[str], List[str], None] | NotGiven#Optional[Literal[False]] | NotGivenOptional[str] | NotGivenstr | NotGivenHeaders | None Query | None Body | None'float | httpx.Timeout | None | NotGivenr modelpromptr/r0r1r2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rAr$cCsdSu\ 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/overview) 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/gpt/parameter-details) 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) (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. 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. max_tokens: The maximum number of [tokens](/tokenizer) to generate 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/gpt/parameter-details) 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: 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). suffix: The suffix that comes after a completion of inserted text. 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)rQrRr/r0r1r2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rAr,r,r-creates!zCompletions.creater/r0r1r2r3r4r5r6r7r8r:r;r<r=r>r?r@rA Literal[True]zStream[Completion]rQrRr9r/r0r1r2r3r4r5r6r7r8r:r;r<r=r>r?r@rAr$cCsdSu\ 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/overview) 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/gpt/parameter-details) 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) (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. 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. max_tokens: The maximum number of [tokens](/tokenizer) to generate 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/gpt/parameter-details) 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: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. suffix: The suffix that comes after a completion of inserted text. 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)rQrRr9r/r0r1r2r3r4r5r6r7r8r:r;r<r=r>r?r@rAr,r,r-rUs!boolzCompletion | Stream[Completion]cCsdSrYr,rZr,r,r-rUcs!rQrRrQrRr93Optional[Literal[False]] | Literal[True] | NotGivencCsV|jdt||||||||| | | | | ||||dtjt||||dt| pJdttdSNz /completions)rQrRr/r0r1r2r3r4r5r6r7r8r9r:r;r<r=)r>r?r@rAF)bodyoptionsZcast_tor9Z stream_cls)_postrr CompletionCreateParamsrr rrTr,r,r-rUs<* __name__ __module__ __qualname____annotations__r'rr rUr __classcell__r,r,r*r-rs >">">"cseZdZUded<dddfdd Zeeeeeeeeeeeeeeeeddded d d d d ddd d d dd ddddddddddddddZeeeeeeeeeeeeeeedddedd d dd d ddd d d dd dddddddddddd dZeeeeeeeeeeeeeeedddedd d d!d d ddd d d dd dddddddddd"dd#dZed$d%ggd&eeeeeeeeeeeeeeeddded d d d d ddd d d dd dd'ddddddddd"dd(dZZ S))rAsyncCompletionsWithRawResponser rr!r"cst|t||_dSr%)r&r'rir r(r*r,r-r'Ss zAsyncCompletions.__init__Nr.rBrCrDrErFrGrHrIrJrKrLrMrNrOr rPcsdSrSr,rTr,r,r-rUWs!zAsyncCompletions.createrVrWzAsyncStream[Completion]rXcsdSrYr,rZr,r,r-rUs!r[z$Completion | AsyncStream[Completion]csdSrYr,rZr,r,r-rUs!rQrRr\r]cs\|jdt||||||||| | | | | ||||dtjt||||dt| pJdttdIdHSr^)rarr rbrr rrTr,r,r-rU=s<*rcr,r,r*r-rPs >">">"c@seZdZdddddZdS)rrr! completionsr$cCst|j|_dSr%)rrUr)rkr,r,r-r'sz#CompletionsWithRawResponse.__init__Nrdrerfr'r,r,r,r-rsrc@seZdZdddddZdS)rirr!rjcCst|j|_dSr%)rrUrlr,r,r-r'sz(AsyncCompletionsWithRawResponse.__init__Nrmr,r,r,r-risri)+ __future__rtypingrrrrrrZtyping_extensionsr Zhttpxtypesr r _typesr rrrr_utilsrrZ _resourcerr _responserrZ _streamingrrZ _base_clientrZ_clientrr__all__rrrrir,r,r,r-s2    <<