o j@s8ddlmZddlmZmZmZmZmZmZddl m Z ddl Z ddl m Z ddlmZmZddlmZmZmZmZmZdd lmZmZmZdd lmZdd lmZmZdd l m!Z!m"Z"dd l#m$Z$m%Z%ddl&m'Z'ddgZ(GdddeZ)GdddeZ*GdddZ+GdddZ,GdddZ-GdddZ.dS)) annotations)DictListUnionIterableOptionaloverload)LiteralN)_legacy_response) Completioncompletion_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 CompletionsAsyncCompletionsc@eZdZed:ddZed;ddZeeeeeeeeeeeeeeeeddded dd6d/Ze d d ggd7eeeeeeeeeeeeeeeddded d?d9d/ZdS)@rreturnCompletionsWithRawResponsecCt|SN)r"selfr'b/var/www/html/fyndo/pharma/fyndo/venv/lib/python3.10/site-packages/openai/resources/completions.pywith_raw_responsezCompletions.with_raw_response CompletionsWithStreamingResponsecCr#r$)r+r%r'r'r(with_streaming_response"r*z#Completions.with_streaming_responseNbest_ofechofrequency_penalty logit_biaslogprobs max_tokensnpresence_penaltyseedstopstreamsuffix temperaturetop_puser extra_headers extra_query extra_bodytimeoutmodelKUnion[str, Literal['gpt-3.5-turbo-instruct', 'davinci-002', 'babbage-002']]promptCUnion[str, List[str], Iterable[int], Iterable[Iterable[int]], None]r.Optional[int] | NotGivenr/Optional[bool] | NotGivenr0Optional[float] | NotGivenr1#Optional[Dict[str, int]] | NotGivenr2r3r4r5r6r70Union[Optional[str], List[str], None] | NotGivenr8#Optional[Literal[False]] | NotGivenr9Optional[str] | NotGivenr:r;r<str | NotGivenr=Headers | Noner> Query | Noner? Body | Noner@'float | httpx.Timeout | None | NotGivenr cCdSu 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/text-generation/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) 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/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. 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&rArCr.r/r0r1r2r3r4r5r6r7r8r9r:r;r<r=r>r?r@r'r'r(create&zCompletions.creater.r/r0r1r2r3r4r5r6r7r9r:r;r<r=r>r?r@ Literal[True]Stream[Completion]cCrQu 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/text-generation/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) 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/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. 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&rArCr8r.r/r0r1r2r3r4r5r6r7r9r:r;r<r=r>r?r@r'r'r(rTrUboolCompletion | Stream[Completion]cCrQrYr'rZr'r'r(rTRrUrArCr83Optional[Literal[False]] | Literal[True] | NotGivenc Cs|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|tjt||||dt| pFdttdSNz /completionsrArCr.r/r0r1r2r3r4r5r6r7r8r9r:r;r<)r=r>r?r@F)bodyoptionscast_tor8 stream_cls)_postrr CompletionCreateParamsrr rrSr'r'r(rTs^     )r!r")r!r+,rArBrCrDr.rEr/rFr0rGr1rHr2rEr3rEr4rEr5rGr6rEr7rIr8rJr9rKr:rGr;rGr<rLr=rMr>rNr?rOr@rPr!r ),rArBrCrDr8rWr.rEr/rFr0rGr1rHr2rEr3rEr4rEr5rGr6rEr7rIr9rKr:rGr;rGr<rLr=rMr>rNr?rOr@rPr!rX),rArBrCrDr8r[r.rEr/rFr0rGr1rHr2rEr3rEr4rEr5rGr6rEr7rIr9rKr:rGr;rGr<rLr=rMr>rNr?rOr@rPr!r\),rArBrCrDr.rEr/rFr0rGr1rHr2rEr3rEr4rEr5rGr6rEr7rIr8r^r9rKr:rGr;rGr<rLr=rMr>rNr?rOr@rPr!r\ __name__ __module__ __qualname__rr)r,rrrTrr'r'r'r(r  c@r )@rr!AsyncCompletionsWithRawResponsecCr#r$)rlr%r'r'r(r)&r*z"AsyncCompletions.with_raw_response%AsyncCompletionsWithStreamingResponsecCr#r$)rmr%r'r'r(r,*r*z(AsyncCompletions.with_streaming_responseNr-rArBrCrDr.rEr/rFr0rGr1rHr2r3r4r5r6r7rIr8rJr9rKr:r;r<rLr=rMr>rNr?rOr@rPr cdSrRr'rSr'r'r(rT.zAsyncCompletions.createrVrWAsyncStream[Completion]crnrYr'rZr'r'r(rTror[$Completion | AsyncStream[Completion]crnrYr'rZr'r'r(rTZror]r^c s|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|tjIdHt||||dt| pJdttdIdHSr_)rdrr rerr rrSr'r'r(rTs`      )r!rl)r!rmrf),rArBrCrDr8rWr.rEr/rFr0rGr1rHr2rEr3rEr4rEr5rGr6rEr7rIr9rKr:rGr;rGr<rLr=rMr>rNr?rOr@rPr!rp),rArBrCrDr8r[r.rEr/rFr0rGr1rHr2rEr3rEr4rEr5rGr6rEr7rIr9rKr:rGr;rGr<rLr=rMr>rNr?rOr@rPr!rq),rArBrCrDr.rEr/rFr0rGr1rHr2rEr3rEr4rEr5rGr6rEr7rIr8r^r9rKr:rGr;rGr<rLr=rMr>rNr?rOr@rPr!rqrgr'r'r'r(r%rkc@eZdZdddZdS) r" completionsrr!NonecC||_t|j|_dSr$) _completionsr to_raw_response_wrapperrTr&rsr'r'r(__init__. z#CompletionsWithRawResponse.__init__Nrsrr!rtrhrirjryr'r'r'r(r"-r"c@rr) rlrsrr!rtcCrur$)rvr async_to_raw_response_wrapperrTrxr'r'r(ry7rzz(AsyncCompletionsWithRawResponse.__init__Nrsrr!rtr|r'r'r'r(rl6r}rlc@rr) r+rsrr!rtcC||_t|j|_dSr$)rvrrTrxr'r'r(ry@ z)CompletionsWithStreamingResponse.__init__Nr{r|r'r'r'r(r+?r}r+c@rr) rmrsrr!rtcCrr$)rvrrTrxr'r'r(ryIrz.AsyncCompletionsWithStreamingResponse.__init__Nrr|r'r'r'r(rmHr}rm)/ __future__rtypingrrrrrrtyping_extensionsr httpxr typesr r _typesrrrrr_utilsrrr_compatr _resourcerr _responserr _streamingrr _base_clientr__all__rrr"rlr+rmr'r'r'r(s8