,:j<ddlmZddlmZmZmZmZmZmZddl m Z ddl Z ddl m Z mZmZmZmZddlmZmZddlmZmZdd lmZmZdd lmZmZdd lmZm Z m!Z!m"Z"m#Z#m$Z$dd l%m&Z&erdd l'm(Z(m)Z)ddgZ*GddeZ+GddeZ,GddZ-GddZ.y)) annotations) TYPE_CHECKINGDictListUnionOptionaloverload)LiteralN) NOT_GIVENBodyQueryHeadersNotGiven) required_argsmaybe_transform)SyncAPIResourceAsyncAPIResource)to_raw_response_wrapperasync_to_raw_response_wrapper)Stream AsyncStream)ChatCompletionChatCompletionChunkChatCompletionToolParamChatCompletionMessageParam#ChatCompletionToolChoiceOptionParamcompletion_create_params)make_request_options)OpenAI AsyncOpenAI CompletionsAsyncCompletionsceZdZUded<dfd Zeeeeeeeeeeeeeeeeeddded ddZeeeeeeeeeeeeeeeeddded  dd Zeeeeeeeeeeeeeeeeddded  dd Zeddggd eeeeeeeeeeeeeeeeddded dd ZxZ S)r"CompletionsWithRawResponsewith_raw_responsecDt||t||_yN)super__init__r%r&selfclient __class__s c/var/www/html/tokenscope/api/venv/lib/python3.12/site-packages/openai/resources/chat/completions.pyr*zCompletions.__init__"s  !;D!ANfrequency_penalty function_call functions logit_bias max_tokensnpresence_penaltyresponse_formatseedstopstream temperature tool_choicetoolstop_puser extra_headers extra_query extra_bodytimeoutmessagesmodelcya 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/gpt/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. max_tokens: The maximum number of [tokens](/tokenizer) to generate 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. 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) response_format: An object specifying the format that the model must output. 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 increased latency and appearance of a "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. 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,rFrGr2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrEs r/createzCompletions.create&R r0r2r3r4r5r6r7r8r9r:r;r=r>r?r@rArBrCrDrEcya 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/gpt/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. max_tokens: The maximum number of [tokens](/tokenizer) to generate 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. 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) response_format: An object specifying the format that the model must output. 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 increased latency and appearance of a "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. 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 NrJr,rFrGr<r2r3r4r5r6r7r8r9r:r;r=r>r?r@rArBrCrDrEs r/rLzCompletions.createrMr0cyrPrJrQs r/rLzCompletions.create|rMr0rFrGr<c |jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|itjt ||||t | xsdt tSNz/chat/completionsrFrGr2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rA)rBrCrDrEF)bodyoptionscast_tor< stream_cls)_postrrCompletionCreateParamsrrrrrKs r/rLzCompletions.create's6^zz  U():$]     !* !*'(8&DDf";"; U!"U#$D%()??+.)+Q[el#?U12=  r0)r-r returnNone.rF List[ChatCompletionMessageParam]rGUnion[str, Literal['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-1106', 'gpt-3.5-turbo', 'gpt-3.5-turbo-16k', 'gpt-3.5-turbo-0301', 'gpt-3.5-turbo-0613', 'gpt-3.5-turbo-16k-0613']]r2Optional[float] | NotGivenr30completion_create_params.FunctionCall | NotGivenr42List[completion_create_params.Function] | NotGivenr5#Optional[Dict[str, int]] | NotGivenr6Optional[int] | NotGivenr7rer8rar92completion_create_params.ResponseFormat | NotGivenr:rer;*Union[Optional[str], List[str]] | NotGivenr<z#Optional[Literal[False]] | NotGivenr=rar>.ChatCompletionToolChoiceOptionParam | NotGivenr?(List[ChatCompletionToolParam] | NotGivenr@rarAstr | NotGivenrBHeaders | NonerC Query | NonerD Body | NonerE'float | httpx.Timeout | None | NotGivenr\r).rFr_rGr`r< Literal[True]r2rar3rbr4rcr5rdr6rer7rer8rar9rfr:rer;rgr=rar>rhr?rir@rarArjrBrkrCrlrDrmrErnr\zStream[ChatCompletionChunk]).rFr_rGr`r<boolr2rar3rbr4rcr5rdr6rer7rer8rar9rfr:rer;rgr=rar>rhr?rir@rarArjrBrkrCrlrDrmrErnr\,ChatCompletion | Stream[ChatCompletionChunk]).rFr_rGr`r2rar3rbr4rcr5rdr6rer7rer8rar9rfr:rer;rgr<3Optional[Literal[False]] | Literal[True] | NotGivenr=rar>rhr?rir@rarArjrBrkrCrlrDrmrErnr\rq __name__ __module__ __qualname____annotations__r*r r rLr __classcell__r.s@r/r"r"s11B09BJSHQ:C/8&/7@NW)2;D6?2;FO:C,5()-$("&;DYh 3h  h .6/h 0H1h 2F3h 485h 6-7h 8 $9h :5;h <L=h >'?h @9Ah B4Ch D0Eh FDGh H8Ih J*Kh LMh R&Sh T"Uh V Wh X9Yh Z [h h T29BJSHQ:C/8&/7@NW)2;D2;FO:C,5()-$("&;DYh 3h  h ./h 061h 2H3h 4F5h 687h 8-9h : $;h <5=h >L?h @'Ah B9Ch D0Eh FDGh H8Ih J*Kh LMh R&Sh T"Uh V Wh X9Yh Z %[h h T29BJSHQ:C/8&/7@NW)2;D2;FO:C,5()-$("&;DYh 3h  h ./h 061h 2H3h 4F5h 687h 8-9h : $;h <5=h >L?h @'Ah B9Ch D0Eh FDGh H8Ih J*Kh LMh R&Sh T"Uh V Wh X9Yh Z 6[h h TJ(*IJ09BJSHQ:C/8&/7@NW)2;DFO2;FO:C,5()-$("&;DYM 3M  M .6/M 0H1M 2F3M 485M 6-7M 8 $9M :5;M <L=M >'?M @9AM BDCM D0EM FDGM H8IM J*KM LMM R&SM T"UM V WM X9YM Z 6[M KM r0ceZdZUded<dfd Zeeeeeeeeeeeeeeeeeddded ddZeeeeeeeeeeeeeeeeddded  dd Zeeeeeeeeeeeeeeeeddded  dd Zeddggd eeeeeeeeeeeeeeeeddded dd ZxZ S)r#AsyncCompletionsWithRawResponser&cDt||t||_yr()r)r*r{r&r+s r/r*zAsyncCompletions.__init__{s  !@!Fr0Nr1rFrGc KywrIrJrKs r/rLzAsyncCompletions.create R rNc KywrPrJrQs r/rLzAsyncCompletions.create*r~rc KywrPrJrQs r/rLzAsyncCompletions.creater~rrSc *K|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|itjt ||||t | xsdt td{S7wrU)rZrrr[rrrrrKs r/rLzAsyncCompletions.createsD^ZZ  U():$]     !* !*'(8&DDf";"; U!"U#$D%()??+.)+Q[el#?U"#67=     sB B B B)r-r!r\r]r^).rFr_rGr`r<ror2rar3rbr4rcr5rdr6rer7rer8rar9rfr:rer;rgr=rar>rhr?rir@rarArjrBrkrCrlrDrmrErnr\z AsyncStream[ChatCompletionChunk]).rFr_rGr`r<rpr2rar3rbr4rcr5rdr6rer7rer8rar9rfr:rer;rgr=rar>rhr?rir@rarArjrBrkrCrlrDrmrErnr\1ChatCompletion | AsyncStream[ChatCompletionChunk]).rFr_rGr`r2rar3rbr4rcr5rdr6rer7rer8rar9rfr:rer;rgr<rrr=rar>rhr?rir@rarArjrBrkrCrlrDrmrErnr\rrsrys@r/r#r#xs66G09BJSHQ:C/8&/7@NW)2;D6?2;FO:C,5()-$("&;DYh 3h  h .6/h 0H1h 2F3h 485h 6-7h 8 $9h :5;h <L=h >'?h @9Ah B4Ch D0Eh FDGh H8Ih J*Kh LMh R&Sh T"Uh V Wh X9Yh Z [h h T29BJSHQ:C/8&/7@NW)2;D2;FO:C,5()-$("&;DYh 3h  h ./h 061h 2H3h 4F5h 687h 8-9h : $;h <5=h >L?h @'Ah B9Ch D0Eh FDGh H8Ih J*Kh LMh R&Sh T"Uh V Wh X9Yh Z *[h h T29BJSHQ:C/8&/7@NW)2;D2;FO:C,5()-$("&;DYh 3h  h ./h 061h 2H3h 4F5h 687h 8-9h : $;h <5=h >L?h @'Ah B9Ch D0Eh FDGh H8Ih J*Kh LMh R&Sh T"Uh V Wh X9Yh Z ;[h h TJ(*IJ09BJSHQ:C/8&/7@NW)2;DFO2;FO:C,5()-$("&;DYM 3M  M .6/M 0H1M 2F3M 485M 6-7M 8 $9M :5;M <L=M >'?M @9AM BDCM D0EM FDGM H8IM J*KM LMM R&SM T"UM V WM X9YM Z ;[M KM r0ceZdZddZy)r%c8t|j|_yr()rrLr, completionss r/r*z#CompletionsWithRawResponse.__init__s-     r0N)rr"r\r]rtrurvr*rJr0r/r%r% r0r%ceZdZddZy)r{c8t|j|_yr()rrLrs r/r*z(AsyncCompletionsWithRawResponse.__init__s3     r0N)rr#r\r]rrJr0r/r{r{rr0r{)/ __future__rtypingrrrrrr typing_extensionsr httpx_typesr r rrr_utilsrr _resourcerr _responserr _streamingrr types.chatrrrrrr _base_clientr_clientr r!__all__r"r#r%r{rJr0r/rs{#GG% ??4:O-1. , -V  /V  rV  'V  r    r0