fjddlmZddlmZmZmZmZmZmZddl m Z ddl Z ddl m Z ddlmZmZmZmZmZddlmZmZmZdd lmZdd lmZmZdd lmZmZdd l m!Z!m"Z"dd l#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)ddl*m+Z+ddgZ,GddeZ-GddeZ.GddZ/GddZ0GddZ1GddZ2dS)) annotations)DictListUnionIterableOptionaloverload)LiteralN)_legacy_response) NOT_GIVENBodyQueryHeadersNotGiven) required_argsmaybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)Stream AsyncStream)ChatCompletionChatCompletionChunkChatCompletionToolParamChatCompletionMessageParam#ChatCompletionToolChoiceOptionParamcompletion_create_params)make_request_options CompletionsAsyncCompletionscveZdZed>dZed?dZeeeeeeeeeeeeeeeeeeedddedd@d3Zeeeeeeeeeeeeeeeeeeddded4dAd7Zeeeeeeeeeeeeeeeeeeddded4dBd:Ze dd ggd;eeeeeeeeeeeeeeeeeedddeddCd=ZdS)Dr#returnCompletionsWithRawResponsec t|SN)r'selfs uC:\Users\Terasoftware\OneDrive\Desktop\faahhh\fyndo\fyndo\venv\Lib\site-packages\openai/resources/chat/completions.pywith_raw_responsezCompletions.with_raw_response%s)$/// CompletionsWithStreamingResponsec t|Sr))r/r*s r,with_streaming_responsez#Completions.with_streaming_response)s/555r.Nfrequency_penalty function_call functions logit_biaslogprobs max_tokensnpresence_penaltyresponse_formatseedstopstream temperature tool_choicetools top_logprobstop_puser extra_headers extra_query extra_bodytimeoutmessages$Iterable[ChatCompletionMessageParam]model\Union[str, Literal['gpt-4-0125-preview', 'gpt-4-turbo-preview', 'gpt-4-1106-preview', 'gpt-4-vision-preview', 'gpt-4', 'gpt-4-0314', 'gpt-4-0613', 'gpt-4-32k', 'gpt-4-32k-0314', 'gpt-4-32k-0613', 'gpt-3.5-turbo', 'gpt-3.5-turbo-16k', 'gpt-3.5-turbo-0301', 'gpt-3.5-turbo-0613', 'gpt-3.5-turbo-1106', 'gpt-3.5-turbo-0125', 'gpt-3.5-turbo-16k-0613']]r3Optional[float] | NotGivenr40completion_create_params.FunctionCall | NotGivenr56Iterable[completion_create_params.Function] | NotGivenr6#Optional[Dict[str, int]] | NotGivenr7Optional[bool] | NotGivenr8Optional[int] | NotGivenr9r:r;2completion_create_params.ResponseFormat | NotGivenr<r=*Union[Optional[str], List[str]] | NotGivenr>#Optional[Literal[False]] | NotGivenr?r@.ChatCompletionToolChoiceOptionParam | NotGivenrA,Iterable[ChatCompletionToolParam] | NotGivenrBrCrDstr | NotGivenrEHeaders | NonerF Query | NonerG Body | NonerH'float | httpx.Timeout | None | NotGivenrcdSa Creates a model response for the given chat conversation. Args: messages: A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). model: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API. 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) function_call: Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. functions: Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for. 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 tokenizer) to an associated bias value from -100 to 100. 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. logprobs: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. This option is currently not available on the `gpt-4-vision-preview` model. max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by 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 chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. 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) response_format: An object specifying the format that the model must output. Compatible with [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. seed: This feature is in Beta. 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. stream: If set, partial message deltas will be sent, like in ChatGPT. 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). 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. tool_choice: Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. tools: A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. 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+rIrKr3r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrErFrGrHs r,createzCompletions.create- x r.r3r4r5r6r7r8r9r:r;r<r=r?r@rArBrCrDrErFrGrH Literal[True]Stream[ChatCompletionChunk]cdSa Creates a model response for the given chat conversation. Args: messages: A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). model: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API. stream: If set, partial message deltas will be sent, like in ChatGPT. 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). 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) function_call: Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. functions: Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for. 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 tokenizer) to an associated bias value from -100 to 100. 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. logprobs: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. This option is currently not available on the `gpt-4-vision-preview` model. max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by 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 chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. 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) response_format: An object specifying the format that the model must output. Compatible with [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. seed: This feature is in Beta. 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. 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. tool_choice: Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. tools: A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. 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+rIrKr>r3r4r5r6r7r8r9r:r;r<r=r?r@rArBrCrDrErFrGrHs r,razCompletions.createrbr.bool,ChatCompletion | Stream[ChatCompletionChunk]cdSrgr_rhs r,razCompletions.createrbr.rIrKr>3Optional[Literal[False]] | Literal[True] | NotGivenc *|dtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d||||dtjt ||||t |pdt tSNz/chat/completionsrIrKr3r4r5r6r7r8r9r:r;r<r=r>r?r@rA)rBrCrD)rErFrGrHF)bodyoptionscast_tor> stream_cls)_postrr!CompletionCreateParamsr"rrrr`s r,razCompletions.creategsVhzz  U():$]     !* !*'(8&DDf"; ";!"U#$%1" ),)?/2)+Q[el#?U12A! ! ! r.)r&r')r&r/2rIrJrKrLr3rMr4rNr5rOr6rPr7rQr8rRr9rRr:rMr;rSr<rRr=rTr>rUr?rMr@rVrArWrBrRrCrMrDrXrErYrFrZrGr[rHr\r&r)2rIrJrKrLr>rdr3rMr4rNr5rOr6rPr7rQr8rRr9rRr:rMr;rSr<rRr=rTr?rMr@rVrArWrBrRrCrMrDrXrErYrFrZrGr[rHr\r&re)2rIrJrKrLr>rir3rMr4rNr5rOr6rPr7rQr8rRr9rRr:rMr;rSr<rRr=rTr?rMr@rVrArWrBrRrCrMrDrXrErYrFrZrGr[rHr\r&rj)2rIrJrKrLr3rMr4rNr5rOr6rPr7rQr8rRr9rRr:rMr;rSr<rRr=rTr>rmr?rMr@rVrArWrBrRrCrMrDrXrErYrFrZrGr[rHr\r&rj __name__ __module__ __qualname__rr-r1r r rarr_r.r,r#r#$sK000_0666_669BJSLU:C.7/8&/7@NW)2;D6?2;FO>G1:,5()-$("&;Dc{ { { { { X{ z89BJSLU:C.7/8&/7@NW)2;D2;FO>G1:,5()-$("&;Dc{ { { { { X{ z89BJSLU:C.7/8&/7@NW)2;D2;FO>G1:,5()-$("&;Dc{ { { { { X{ z]J(*I*I*IJJ69BJSLU:C.7/8&/7@NW)2;DFO2;FO>G1:,5()-$("&;DcT T T T T KJT T T r.cveZdZed>dZed?dZeeeeeeeeeeeeeeeeeeedddedd@d3Zeeeeeeeeeeeeeeeeeeddded4dAd7Zeeeeeeeeeeeeeeeeeeddded4dBd:Ze dd ggd;eeeeeeeeeeeeeeeeeedddeddCd=ZdS)Dr$r&AsyncCompletionsWithRawResponsec t|Sr))r|r*s r,r-z"AsyncCompletions.with_raw_responses.t444r.%AsyncCompletionsWithStreamingResponsec t|Sr))r~r*s r,r1z(AsyncCompletions.with_streaming_responses4T:::r.Nr2rIrJrKrLr3rMr4rNr5rOr6rPr7rQr8rRr9r:r;rSr<r=rTr>rUr?r@rVrArWrBrCrDrXrErYrFrZrGr[rHr\rc KdSr^r_r`s r,razAsyncCompletions.createx r.rcrd AsyncStream[ChatCompletionChunk]c KdSrgr_rhs r,razAsyncCompletions.createrr.ri1ChatCompletion | AsyncStream[ChatCompletionChunk]c KdSrgr_rhs r,razAsyncCompletions.createDrr.rlrmc FK|dtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d||||dtjd{Vt ||||t |pdt td{VSro)rtrr!rur"rrrr`s r,razAsyncCompletions.createshZZ ,U():$]     !* !*'(8&DDf"; ";!"U#$%1" ),)?/2)+Q[el#?U"#67A ! ! ! ! ! ! ! ! ! r.)r&r|)r&r~rv)2rIrJrKrLr>rdr3rMr4rNr5rOr6rPr7rQr8rRr9rRr:rMr;rSr<rRr=rTr?rMr@rVrArWrBrRrCrMrDrXrErYrFrZrGr[rHr\r&r)2rIrJrKrLr>rir3rMr4rNr5rOr6rPr7rQr8rRr9rRr:rMr;rSr<rRr=rTr?rMr@rVrArWrBrRrCrMrDrXrErYrFrZrGr[rHr\r&r)2rIrJrKrLr3rMr4rNr5rOr6rPr7rQr8rRr9rRr:rMr;rSr<rRr=rTr>rmr?rMr@rVrArWrBrRrCrMrDrXrErYrFrZrGr[rHr\r&rrwr_r.r,r$r$sK555_5;;;_;69BJSLU:C.7/8&/7@NW)2;D6?2;FO>G1:,5()-$("&;Dc{ { { { { X{ z89BJSLU:C.7/8&/7@NW)2;D2;FO>G1:,5()-$("&;Dc{ { { { { X{ z89BJSLU:C.7/8&/7@NW)2;D2;FO>G1:,5()-$("&;Dc{ { { { { X{ z]J(*I*I*IJJ69BJSLU:C.7/8&/7@NW)2;DFO2;FO>G1:,5()-$("&;DcT T T T T KJT T T r.ceZdZddZdS)r' completionsr#r&NonecP||_tj|j|_dSr)) _completionsr to_raw_response_wrapperrar+rs r,__init__z#CompletionsWithRawResponse.__init__[s('&>     r.Nrr#r&rrxryrzrr_r.r,r'r'Z(      r.r'ceZdZddZdS)r|rr$r&rcP||_tj|j|_dSr))rr async_to_raw_response_wrapperrars r,rz(AsyncCompletionsWithRawResponse.__init__ds('&D     r.Nrr$r&rrr_r.r,r|r|crr.r|ceZdZddZdS)r/rr#r&rcF||_t|j|_dSr))rrrars r,rz)CompletionsWithStreamingResponse.__init__ms%'2     r.Nrrr_r.r,r/r/lrr.r/ceZdZddZdS)r~rr$r&rcF||_t|j|_dSr))rrrars r,rz.AsyncCompletionsWithStreamingResponse.__init__vs%'8     r.Nrrr_r.r,r~r~urr.r~)3 __future__rtypingrrrrrr typing_extensionsr httpxr _typesr rrrr_utilsrrr_compatr _resourcerr _responserr _streamingrr types.chatrrrrr r! _base_clientr"__all__r#r$r'r|r/r~r_r.r,rs#"""""BBBBBBBBBBBBBBBB%%%%%% ?????????????? '&&&&&::::::::YYYYYYYY-------- , -X  X  X  X  X  /X  X  X  vX  X  X  X  X  'X  X  X  v                                  r.