gddlmZddlZddlmZmZmZmZmZddl m Z m Z ddl Z ddl Z ddlmZddlmZmZmZmZmZddlmZmZmZdd lmZdd lmZmZdd lm Z m!Z!dd l"m#Z#m$Z$dd l%m&Z&m'Z'm(Z(ddl)m*Z*ddl+m,Z,ddl-m.Z.ddl/m0Z0ddl1m2Z2ddl3m4Z4ddl5m&Z&ddl6m7Z7ddl8m'Z'ddl9m:Z:ddl;mZ>ddgZ?GddeZ@GddeZAGddZBGd d!ZCGd"d#ZDGd$d%ZEd'd&ZFy)() annotationsN)DictListUnionIterableOptional)Literaloverload)_legacy_response) NOT_GIVENBodyQueryHeadersNotGiven) required_argsmaybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)Stream AsyncStream)ChatCompletionAudioParamChatCompletionReasoningEffortcompletion_create_params)make_request_options) ChatModel)ChatCompletion)ChatCompletionChunk)ChatCompletionModality)ChatCompletionToolParam)r)ChatCompletionMessageParam)r) ChatCompletionStreamOptionsParam)$ChatCompletionPredictionContentParam)#ChatCompletionToolChoiceOptionParam CompletionsAsyncCompletionsc"eZdZed dZeddZeeeeeeeeeeeeeeeeeeeeeeeeeeeeeddded ddZeeeeeeeeeeeeeeeeeeeeeeeeeeeeddded dd Zeeeeeeeeeeeeeeeeeeeeeeeeeeeeddded dd Ze ddggd eeeeeeeeeeeeeeeeeeeeeeeeeeeeddded dd Zy)r)ct|Sa This property can be used as a prefix for any HTTP method call to return the 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 V/var/www/openai/venv/lib/python3.12/site-packages/openai/resources/chat/completions.pywith_raw_responsezCompletions.with_raw_response-s*$//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 r1with_streaming_responsez#Completions.with_streaming_response7s055r3N audiofrequency_penalty function_call functions logit_biaslogprobsmax_completion_tokens max_tokensmetadata modalitiesnparallel_tool_calls predictionpresence_penaltyreasoning_effortresponse_formatseed service_tierstopstorestreamstream_options temperature tool_choicetools top_logprobstop_puser extra_headers extra_query extra_bodytimeoutmessagesmodelc"ya-Creates a model response for the given chat conversation. Learn more in the [text generation](https://platform.openai.com/docs/guides/text-generation), [vision](https://platform.openai.com/docs/guides/vision), and [audio](https://platform.openai.com/docs/guides/audio) guides. Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models, [refer to the reasoning guide](https://platform.openai.com/docs/guides/reasoning). Args: messages: A list of messages comprising the conversation so far. Depending on the [model](https://platform.openai.com/docs/models) you use, different message types (modalities) are supported, like [text](https://platform.openai.com/docs/guides/text-generation), [images](https://platform.openai.com/docs/guides/vision), and [audio](https://platform.openai.com/docs/guides/audio). 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. audio: Parameters for audio output. Required when audio output is requested with `modalities: ["audio"]`. [Learn more](https://platform.openai.com/docs/guides/audio). 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. 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`. max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning). max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API. This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with [o1 series models](https://platform.openai.com/docs/guides/reasoning). metadata: Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). modalities: Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default: `["text"]` The `gpt-4o-audio-preview` model can also be used to [generate audio](https://platform.openai.com/docs/guides/audio). To request that this model generate both text and audio responses, you can use: `["text", "audio"]` 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. parallel_tool_calls: Whether to enable [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. prediction: Static predicted output content, such as the content of a text file that is being regenerated. 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. reasoning_effort: **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. response_format: An object specifying the format that the model must output. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs). Setting to `{ "type": "json_object" }` enables JSON mode, which ensures 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. service_tier: Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. When this parameter is set, the response body will include the `service_tier` utilized. stop: Up to 4 sequences where the API will stop generating further tokens. store: Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. 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). stream_options: Options for streaming response. Only set this when you set `stream: true`. 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) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools 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 N#r0rYrZr9r:r;r<r=r>r?r@rArBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQrRrSrTrUrVrWrXs# r1createzCompletions.create@r r3r9r:r;r<r=r>r?r@rArBrCrDrErFrGrHrIrJrKrLrNrOrPrQrRrSrTrUrVrWrXc"ya-Creates a model response for the given chat conversation. Learn more in the [text generation](https://platform.openai.com/docs/guides/text-generation), [vision](https://platform.openai.com/docs/guides/vision), and [audio](https://platform.openai.com/docs/guides/audio) guides. Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models, [refer to the reasoning guide](https://platform.openai.com/docs/guides/reasoning). Args: messages: A list of messages comprising the conversation so far. Depending on the [model](https://platform.openai.com/docs/models) you use, different message types (modalities) are supported, like [text](https://platform.openai.com/docs/guides/text-generation), [images](https://platform.openai.com/docs/guides/vision), and [audio](https://platform.openai.com/docs/guides/audio). 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). audio: Parameters for audio output. Required when audio output is requested with `modalities: ["audio"]`. [Learn more](https://platform.openai.com/docs/guides/audio). 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. 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`. max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning). max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API. This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with [o1 series models](https://platform.openai.com/docs/guides/reasoning). metadata: Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). modalities: Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default: `["text"]` The `gpt-4o-audio-preview` model can also be used to [generate audio](https://platform.openai.com/docs/guides/audio). To request that this model generate both text and audio responses, you can use: `["text", "audio"]` 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. parallel_tool_calls: Whether to enable [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. prediction: Static predicted output content, such as the content of a text file that is being regenerated. 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. reasoning_effort: **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. response_format: An object specifying the format that the model must output. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs). Setting to `{ "type": "json_object" }` enables JSON mode, which ensures 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. service_tier: Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. When this parameter is set, the response body will include the `service_tier` utilized. stop: Up to 4 sequences where the API will stop generating further tokens. store: Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. stream_options: Options for streaming response. Only set this when you set `stream: true`. 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) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools 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]#r0rYrZrMr9r:r;r<r=r>r?r@rArBrCrDrErFrGrHrIrJrKrLrNrOrPrQrRrSrTrUrVrWrXs# r1r_zCompletions.create;r`r3c"yrcr]rds# r1r_zCompletions.create6r`r3rYrZrMc"<t||jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d||||||||||||||d tjt || |!|"t |xsdttSNz/chat/completionsrYrZr9r:r;r<r=r>r?r@rArBrCrDrErFrG) rHrIrJrKrLrMrNrOrPrQrRrSrT)rUrVrWrXF)bodyoptionscast_torM stream_cls) validate_response_format_postrrCompletionCreateParamsrr!rr"r^s# r1r_zCompletions.create1sgR !1zz  UU():  $]    !*,-B!*!**+>!* '(8!"'(8#$(7 $0 "$&4#.#."$0" =@)??C"F)+Q[el#?U12U+ + r3)returnr.)rpr6FrY$Iterable[ChatCompletionMessageParam]rZUnion[str, ChatModel]r9-Optional[ChatCompletionAudioParam] | NotGivenr:Optional[float] | NotGivenr;0completion_create_params.FunctionCall | NotGivenr<6Iterable[completion_create_params.Function] | NotGivenr=#Optional[Dict[str, int]] | NotGivenr>Optional[bool] | NotGivenr?Optional[int] | NotGivenr@rzrA#Optional[Dict[str, str]] | NotGivenrB1Optional[List[ChatCompletionModality]] | NotGivenrCrzrDbool | NotGivenrE9Optional[ChatCompletionPredictionContentParam] | NotGivenrFrurG(ChatCompletionReasoningEffort | NotGivenrH2completion_create_params.ResponseFormat | NotGivenrIrzrJ/Optional[Literal['auto', 'default']] | NotGivenrK*Union[Optional[str], List[str]] | NotGivenrLryrMz#Optional[Literal[False]] | NotGivenrN5Optional[ChatCompletionStreamOptionsParam] | NotGivenrOrurP.ChatCompletionToolChoiceOptionParam | NotGivenrQ,Iterable[ChatCompletionToolParam] | NotGivenrRrzrSrurTstr | NotGivenrUHeaders | NonerV Query | NonerW Body | NonerX'float | httpx.Timeout | None | NotGivenrpr!)FrYrrrZrsrM Literal[True]r9rtr:rur;rvr<rwr=rxr>ryr?rzr@rzrAr{rBr|rCrzrDr}rEr~rFrurGrrHrrIrzrJrrKrrLryrNrrOrurPrrQrrRrzrSrurTrrUrrVrrWrrXrrpzStream[ChatCompletionChunk])FrYrrrZrsrMboolr9rtr:rur;rvr<rwr=rxr>ryr?rzr@rzrAr{rBr|rCrzrDr}rEr~rFrurGrrHrrIrzrJrrKrrLryrNrrOrurPrrQrrRrzrSrurTrrUrrVrrWrrXrrp,ChatCompletion | Stream[ChatCompletionChunk])FrYrrrZrsr9rtr:rur;rvr<rwr=rxr>ryr?rzr@rzrAr{rBr|rCrzrDr}rEr~rFrurGrrHrrIrzrJrrKrrLryrM3Optional[Literal[False]] | Literal[True] | NotGivenrNrrOrurPrrQrrRrzrSrurTrrUrrVrrWrrXrrpr __name__ __module__ __qualname__rr2r7r r r_rr]r3r1r)r),s0066 @I8AJSLU:C.7:C/88AHQ&//8PY7@ENNW)2HQ;D+46?PY2;FO>G1:,5()-$("&;DMx 7x % x = x 6 x Hx Jx 8x ,x  8x -x 6x Fx  $x -!x "N#x $5%x &C'x (L)x *'+x ,F-x .9/x 0)1x 243x 4N5x 607x 8D9x :<;x </=x >*?x @Ax F&Gx H"Ix J Kx L9Mx N Ox x t@I8AJSLU:C.7:C/88AHQ&//8PY7@ENNW)2HQ;D+4PY2;FO>G1:,5()-$("&;DMx 7x % x  x = x 6x Hx Jx 8x ,x  8x -x 6x Fx $!x "-#x $N%x &5'x (C)x *L+x ,'-x .F/x 091x 2)3x 4N5x 607x 8D9x :<;x </=x >*?x @Ax F&Gx H"Ix J Kx L9Mx N %Ox x t@I8AJSLU:C.7:C/88AHQ&//8PY7@ENNW)2HQ;D+4PY2;FO>G1:,5()-$("&;DMx 7x % x  x = x 6x Hx Jx 8x ,x  8x -x 6x Fx $!x "-#x $N%x &5'x (C)x *L+x ,'-x .F/x 091x 2)3x 4N5x 607x 8D9x :<;x </=x >*?x @Ax F&Gx H"Ix J Kx L9Mx N 6Ox x tJ(*IJ @I8AJSLU:C.7:C/88AHQ&//8PY7@ENNW)2HQ;D+4FOPY2;FO>G1:,5()-$("&;DMT 7T % T = T 6 T HT JT 8T ,T  8T -T 6T FT  $T -!T "N#T $5%T &C'T (L)T *'+T ,F-T .9/T 0)1T 2D3T 4N5T 607T 8D9T :<;T </=T >*?T @AT F&GT H"IT J KT L9MT N 6OT KT r3c"eZdZed dZeddZeeeeeeeeeeeeeeeeeeeeeeeeeeeeeddded ddZeeeeeeeeeeeeeeeeeeeeeeeeeeeeddded dd Zeeeeeeeeeeeeeeeeeeeeeeeeeeeeddded dd Ze ddggd eeeeeeeeeeeeeeeeeeeeeeeeeeeeddded dd Zy)r*ct|Sr-)AsyncCompletionsWithRawResponser/s r1r2z"AsyncCompletions.with_raw_responses/t44r3ct|Sr5)%AsyncCompletionsWithStreamingResponser/s r1r7z(AsyncCompletions.with_streaming_responses5T::r3Nr8rYrZc" Kywr\r]r^s# r1r_zAsyncCompletions.create r rac" Kywrcr]rds# r1r_zAsyncCompletions.createrrc" Kywrcr]rds# r1r_zAsyncCompletions.createrrrfc"lKt||jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d||||||||||||||d tjd{t || |!|"t |xsdttd{S757wrh) rmrnrrrorr!rr"r^s# r1r_zAsyncCompletions.createsR !1ZZ ,UU():  $]    !*,-B!*!**+>!* '(8!"'(8#$(7 $0 "$&4#.#."$0" =@)??C""F)+Q[el#?U"#67U + + + "+ s$A8B4:B0 ;0B4+B2,B42B4)rpr)rprrq)FrYrrrZrsrMrr9rtr:rur;rvr<rwr=rxr>ryr?rzr@rzrAr{rBr|rCrzrDr}rEr~rFrurGrrHrrIrzrJrrKrrLryrNrrOrurPrrQrrRrzrSrurTrrUrrVrrWrrXrrpz AsyncStream[ChatCompletionChunk])FrYrrrZrsrMrr9rtr:rur;rvr<rwr=rxr>ryr?rzr@rzrAr{rBr|rCrzrDr}rEr~rFrurGrrHrrIrzrJrrKrrLryrNrrOrurPrrQrrRrzrSrurTrrUrrVrrWrrXrrp1ChatCompletion | AsyncStream[ChatCompletionChunk])FrYrrrZrsr9rtr:rur;rvr<rwr=rxr>ryr?rzr@rzrAr{rBr|rCrzrDr}rEr~rFrurGrrHrrIrzrJrrKrrLryrMrrNrrOrurPrrQrrRrzrSrurTrrUrrVrrWrrXrrprrr]r3r1r*r*s55;; @I8AJSLU:C.7:C/88AHQ&//8PY7@ENNW)2HQ;D+46?PY2;FO>G1:,5()-$("&;DMx 7x % x = x 6 x Hx Jx 8x ,x  8x -x 6x Fx  $x -!x "N#x $5%x &C'x (L)x *'+x ,F-x .9/x 0)1x 243x 4N5x 607x 8D9x :<;x </=x >*?x @Ax F&Gx H"Ix J Kx L9Mx N Ox x t@I8AJSLU:C.7:C/88AHQ&//8PY7@ENNW)2HQ;D+4PY2;FO>G1:,5()-$("&;DMx 7x % x  x = x 6x Hx Jx 8x ,x  8x -x 6x Fx $!x "-#x $N%x &5'x (C)x *L+x ,'-x .F/x 091x 2)3x 4N5x 607x 8D9x :<;x </=x >*?x @Ax F&Gx H"Ix J Kx L9Mx N *Ox x t@I8AJSLU:C.7:C/88AHQ&//8PY7@ENNW)2HQ;D+4PY2;FO>G1:,5()-$("&;DMx 7x % x  x = x 6x Hx Jx 8x ,x  8x -x 6x Fx $!x "-#x $N%x &5'x (C)x *L+x ,'-x .F/x 091x 2)3x 4N5x 607x 8D9x :<;x </=x >*?x @Ax F&Gx H"Ix J Kx L9Mx N ;Ox x tJ(*IJ @I8AJSLU:C.7:C/88AHQ&//8PY7@ENNW)2HQ;D+4FOPY2;FO>G1:,5()-$("&;DMT 7T % T = T 6 T HT JT 8T ,T  8T -T 6T FT  $T -!T "N#T $5%T &C'T (L)T *'+T ,F-T .9/T 0)1T 2D3T 4N5T 607T 8D9T :<;T </=T >*?T @AT F&GT H"IT J KT L9MT N ;OT KT r3ceZdZddZy)r.cZ||_tj|j|_yN) _completionsr to_raw_response_wrapperr_r0 completionss r1__init__z#CompletionsWithRawResponse.__init__s%'&>>     r3Nrr)rpNonerrrrr]r3r1r.r. r3r.ceZdZddZy)rcZ||_tj|j|_yr)rr async_to_raw_response_wrapperr_rs r1rz(AsyncCompletionsWithRawResponse.__init__s%'&DD     r3Nrr*rprrr]r3r1rrrr3rceZdZddZy)r6cF||_t|j|_yr)rrr_rs r1rz)CompletionsWithStreamingResponse.__init__s'2     r3Nrrr]r3r1r6r6rr3r6ceZdZddZy)rcF||_t|j|_yr)rrr_rs r1rz.AsyncCompletionsWithStreamingResponse.__init__s'8     r3Nrrr]r3r1rrrr3rcztj|r&t|tjr t dyy)NzzYou tried to pass a `BaseModel` class to `chat.completions.create()`; You must use `beta.chat.completions.parse()` instead)inspectisclass issubclasspydantic BaseModel TypeError)rHs r1rmrm s9'JHZHZ,[ I  -\'r3)rHobjectrpr)G __future__rrtypingrrrrrtyping_extensionsr r httpxrr _typesr rrrr_utilsrrr_compatr _resourcerr _responserr _streamingrr types.chatrrr _base_clientrtypes.chat_modelr types.chat.chat_completionr! types.chat.chat_completion_chunkr"#types.chat.chat_completion_modalityr#%types.chat.chat_completion_tool_paramr$&types.chat.chat_completion_audio_param(types.chat.chat_completion_message_paramr%+types.chat.chat_completion_reasoning_effort/types.chat.chat_completion_stream_options_paramr&3types.chat.chat_completion_prediction_content_paramr'3types.chat.chat_completion_tool_choice_option_paramr(__all__r)r*r.rr6rrmr]r3r1rs#88/  ?? ':Y- 1)8CILNRX_gf , -Z  /Z  zZ  'Z  z         r3