o ?Hhq@sddlmZddlmZmZmZmZmZmZm Z ddl m Z ddl m Z ddlZddlmZddlmZmZmZmZmZdd lmZmZdd lmZdd lmZmZdd lm Z m!Z!dd l"m#Z#ddl$m%Z%ddl&m'Z'ddl(m)Z)m*Z+m,Z-m.Z/ddl0m1Z1ddl2m3Z3m4Z4ddl5m6Z6m7Z7ddl8m9Z9ddl:m;Z;ddlm?Z?ddl@mAZAddlBmCZCddlDmEZEddlFmGZGddlHmIZIddgZJGdddeZKGd ddeZLGd!d"d"ZMGd#d$d$ZNGd%d&d&ZOGd'd(d(ZPdS))) annotations)DictListTypeUnionIterableOptionalcast)partial)LiteralN)_legacy_response) NOT_GIVENBodyQueryHeadersNotGiven)maybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)Stream)completion_create_params)make_request_options)ResponseFormatTvalidate_input_toolsparse_chat_completiontype_to_response_format_param) ChatModel)ChatCompletionStreamManager AsyncChatCompletionStreamManager)MetadataReasoningEffort)ChatCompletion)ChatCompletionChunk)ParsedChatCompletion)ChatCompletionToolParam)ChatCompletionAudioParam)ChatCompletionMessageParam) ChatCompletionStreamOptionsParam)$ChatCompletionPredictionContentParam)#ChatCompletionToolChoiceOptionParam CompletionsAsyncCompletionsc!@eZdZedMddZedNddZeeeeeeeeeeeeeeeeeeeeeeeeeeeeddded dOdGdHZeeeeeeeeeeeeeeeeeeeeeeeeeeeeddded dPdKdLZdS)Qr/returnCompletionsWithRawResponsecCt|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 )r3selfr8f/home/air/sanwanet/gpt-api/venv/lib/python3.10/site-packages/openai/resources/beta/chat/completions.pywith_raw_response+zCompletions.with_raw_response CompletionsWithStreamingResponsecCr4z 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 )r<r6r8r8r9with_streaming_response5z#Completions.with_streaming_responseN audioresponse_formatfrequency_penalty function_call functions logit_biaslogprobsmax_completion_tokens max_tokensmetadata modalitiesnparallel_tool_calls predictionpresence_penaltyreasoning_effortseed service_tierstopstorestream_options temperature tool_choicetools top_logprobstop_puserweb_search_options extra_headers extra_query extra_bodytimeoutmessages$Iterable[ChatCompletionMessageParam]modelUnion[str, ChatModel]rA-Optional[ChatCompletionAudioParam] | NotGivenrB type[ResponseFormatT] | NotGivenrCOptional[float] | NotGivenrD0completion_create_params.FunctionCall | NotGivenrE6Iterable[completion_create_params.Function] | NotGivenrF#Optional[Dict[str, int]] | NotGivenrGOptional[bool] | NotGivenrHOptional[int] | NotGivenrIrJOptional[Metadata] | NotGivenrK3Optional[List[Literal['text', 'audio']]] | NotGivenrLrMbool | NotGivenrN9Optional[ChatCompletionPredictionContentParam] | NotGivenrOrP$Optional[ReasoningEffort] | NotGivenrQrR/Optional[Literal['auto', 'default']] | NotGivenrS0Union[Optional[str], List[str], None] | NotGivenrTrU5Optional[ChatCompletionStreamOptionsParam] | NotGivenrVrW.ChatCompletionToolChoiceOptionParam | NotGivenrX,Iterable[ChatCompletionToolParam] | NotGivenrYrZr[str | NotGivenr\4completion_create_params.WebSearchOptions | NotGivenr]Headers | Noner^ Query | Noner_ Body | Noner`'float | httpx.Timeout | None | NotGiven%ParsedChatCompletion[ResponseFormatT]c"$stddi|p i}d fdd }#|jd tid |d |d |d |d|d|d|d| d| d| d| d| d|d|d|d|d|t||||d|||||||dtjt|| |!|"|#dttt t t ddS)!aWrapper over the `client.chat.completions.create()` method that provides richer integrations with Python specific types & returns a `ParsedChatCompletion` object, which is a subclass of the standard `ChatCompletion` class. You can pass a pydantic model to this method and it will automatically convert the model into a JSON schema, send it to the API and parse the response content back into the given model. This method will also automatically parse `function` tool calls if: - You use the `openai.pydantic_function_tool()` helper method - You mark your tool schema with `"strict": True` Example usage: ```py from pydantic import BaseModel from openai import OpenAI class Step(BaseModel): explanation: str output: str class MathResponse(BaseModel): steps: List[Step] final_answer: str client = OpenAI() completion = client.beta.chat.completions.parse( model="gpt-4o-2024-08-06", messages=[ {"role": "system", "content": "You are a helpful math tutor."}, {"role": "user", "content": "solve 8x + 31 = 2"}, ], response_format=MathResponse, ) message = completion.choices[0].message if message.parsed: print(message.parsed.steps) print("answer: ", message.parsed.final_answer) ``` X-Stainless-Helper-Methodbeta.chat.completions.parseraw_completionr&r2r}ct|dSN)rBchat_completion input_tools_parse_chat_completionrrBrXr8r9parser z!Completions.parse..parser/chat/completionsrarcrArCrDrErFrGrHrIrJrKrLrMrNrOrPF)rBrQrRrSrTstreamrUrVrWrXrYrZr[r\r]r^r_r` post_parserbodyoptionscast_torNrr&r2r}) _validate_input_tools_postr_type_to_response_formatrCompletionCreateParamsrr rr(rr&$r7rarcrArBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQrRrSrTrUrVrWrXrYrZr[r\r]r^r_r`rr8rr9parse>sR     !$ zCompletions.parseJcompletion_create_params.ResponseFormat | type[ResponseFormatT] | NotGiven,ChatCompletionStreamManager[ResponseFormatT]c"$Csddi|pi}t|jjjjfid|d|d|dddt|d |d |d |d |d | d| d| d| d| d|d|d|d|d|d|d|d|d|d|d|d|d|d|d |d!|d"|d#|d$| d%|!d&|"}#t|#||d'S)(aWrapper over the `client.chat.completions.create(stream=True)` method that provides a more granular event API and automatic accumulation of each delta. This also supports all of the parsing utilities that `.parse()` does. Unlike `.create(stream=True)`, the `.stream()` method requires usage within a context manager to prevent accidental leakage of the response: ```py with client.beta.chat.completions.stream( model="gpt-4o-2024-08-06", messages=[...], ) as stream: for event in stream: if event.type == "content.delta": print(event.delta, flush=True, end="") ``` When the context manager is entered, a `ChatCompletionStream` instance is returned which, like `.create(stream=True)` is an iterator. The full list of events that are yielded by the iterator are outlined in [these docs](https://github.com/openai/openai-python/blob/main/helpers.md#chat-completions-events). When the context manager exits, the response will be closed, however the `stream` instance is still available outside the context manager. r~beta.chat.completions.streamrarcrArTrBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQrRrTrSrUrVrWrXrYrZr[r\r]r^r_r`rBr)r _clientchat completionscreaterr"$r7rarcrArBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQrRrSrTrUrVrWrXrYrZr[r\r]r^r_r` api_requestr8r8r9rs?       !"#$&zCompletions.stream)r2r3)r2r<FrarbrcrdrArerBrfrCrgrDrhrErirFrjrGrkrHrlrIrlrJrmrKrnrLrlrMrorNrprOrgrPrqrQrlrRrrrSrsrTrkrUrtrVrgrWrurXrvrYrlrZrgr[rwr\rxr]ryr^rzr_r{r`r|r2r})FrarbrcrdrArerBrrCrgrDrhrErirFrjrGrkrHrlrIrlrJrmrKrnrLrlrMrorNrprOrgrPrqrQrlrRrrrSrsrTrkrUrtrVrgrWrurXrvrYrlrZrgr[rwr\rxr]ryr^rzr_r{r`r|r2r __name__ __module__ __qualname__rr:r>rrrr8r8r8r9r/*   c!@r1)Qr0r2AsyncCompletionsWithRawResponsecCr4r5)rr6r8r8r9r:Br;z"AsyncCompletions.with_raw_response%AsyncCompletionsWithStreamingResponsecCr4r=)rr6r8r8r9r>Lr?z(AsyncCompletions.with_streaming_responseNr@rarbrcrdrArerBrfrCrgrDrhrErirFrjrGrkrHrlrIrJrmrKrnrLrMrorNrprOrPrqrQrRrrrSrsrTrUrtrVrWrurXrvrYrZr[rwr\rxr]ryr^rzr_r{r`r|r}c"$stddi|p i}d fdd }#|jd tid |d |d |d |d|d|d|d| d| d| d| d| d|d|d|d|d|t||||d|||||||dtjIdHt|| |!|"|#dttt t t ddIdHS)!aWrapper over the `client.chat.completions.create()` method that provides richer integrations with Python specific types & returns a `ParsedChatCompletion` object, which is a subclass of the standard `ChatCompletion` class. You can pass a pydantic model to this method and it will automatically convert the model into a JSON schema, send it to the API and parse the response content back into the given model. This method will also automatically parse `function` tool calls if: - You use the `openai.pydantic_function_tool()` helper method - You mark your tool schema with `"strict": True` Example usage: ```py from pydantic import BaseModel from openai import AsyncOpenAI class Step(BaseModel): explanation: str output: str class MathResponse(BaseModel): steps: List[Step] final_answer: str client = AsyncOpenAI() completion = await client.beta.chat.completions.parse( model="gpt-4o-2024-08-06", messages=[ {"role": "system", "content": "You are a helpful math tutor."}, {"role": "user", "content": "solve 8x + 31 = 2"}, ], response_format=MathResponse, ) message = completion.choices[0].message if message.parsed: print(message.parsed.steps) print("answer: ", message.parsed.final_answer) ``` r~rrr&r2r}crrrrrr8r9rrz&AsyncCompletions.parse..parserrrarcrArCrDrErFrGrHrIrJrKrLrMrNrOrPF)rBrQrRrTrSrrUrVrWrXrYrZr[r\Nrrr) rrrrrrrr rr(rr&rr8rr9rUsR     !$  zAsyncCompletions.parser1AsyncChatCompletionStreamManager[ResponseFormatT]c"$Cst|ddi|p i}|jjjjd)id|d|d|dddt|d |d |d |d |d | d| d| d| d| d|d|d|d|d|d|d|d|d|d|d|d|d|d|d |d!|d"|d#| d$|!d%|"d&|}#t|#||d'S)*aWrapper over the `client.chat.completions.create(stream=True)` method that provides a more granular event API and automatic accumulation of each delta. This also supports all of the parsing utilities that `.parse()` does. Unlike `.create(stream=True)`, the `.stream()` method requires usage within a context manager to prevent accidental leakage of the response: ```py async with client.beta.chat.completions.stream( model="gpt-4o-2024-08-06", messages=[...], ) as stream: async for event in stream: if event.type == "content.delta": print(event.delta, flush=True, end="") ``` When the context manager is entered, an `AsyncChatCompletionStream` instance is returned which, like `.create(stream=True)` is an async iterator. The full list of events that are yielded by the iterator are outlined in [these docs](https://github.com/openai/openai-python/blob/main/helpers.md#chat-completions-events). When the context manager exits, the response will be closed, however the `stream` instance is still available outside the context manager. r~rrarcrArTrBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQrRrSrTrUrVrWrXrYrZr[r]r^r_r`r\rNr8)rrrrrrr#rr8r8r9rs>      !"#%zAsyncCompletions.stream)r2r)r2rr)FrarbrcrdrArerBrrCrgrDrhrErirFrjrGrkrHrlrIrlrJrmrKrnrLrlrMrorNrprOrgrPrqrQrlrRrrrSrsrTrkrUrtrVrgrWrurXrvrYrlrZrgr[rwr\rxr]ryr^rzr_r{r`r|r2rrr8r8r8r9r0Arc@eZdZdddZdS) r3rr/r2NonecC||_t|j|_dSN) _completionsr to_raw_response_wrapperrr7rr8r8r9__init__Z z#CompletionsWithRawResponse.__init__Nrr/r2rrrrrr8r8r8r9r3Yr3c@r) rrr0r2rcCrr)rr async_to_raw_response_wrapperrrr8r8r9rcrz(AsyncCompletionsWithRawResponse.__init__Nrr0r2rrr8r8r8r9rbrrc@r) r<rr/r2rcC||_t|j|_dSr)rrrrr8r8r9rl z)CompletionsWithStreamingResponse.__init__Nrrr8r8r8r9r<krr<c@r) rrr0r2rcCrr)rrrrr8r8r9rurz.AsyncCompletionsWithStreamingResponse.__init__Nrrr8r8r8r9rtrr)Q __future__rtypingrrrrrrr functoolsr typing_extensionsr httpxr _typesrrrrr_utilsrr_compatr _resourcerr _responserr _streamingr types.chatr _base_clientr lib._parsingrrrrrr rtypes.chat_modelr!lib.streaming.chatr"r#types.shared_paramsr$r%types.chat.chat_completionr& types.chat.chat_completion_chunkr'!types.chat.parsed_chat_completionr(%types.chat.chat_completion_tool_paramr)&types.chat.chat_completion_audio_paramr*(types.chat.chat_completion_message_paramr+/types.chat.chat_completion_stream_options_paramr,3types.chat.chat_completion_prediction_content_paramr-3types.chat.chat_completion_tool_choice_option_paramr.__all__r/r0r3rr<rr8r8r8r9sL $