g~dZddlmZddlmZmZddlmZddlm Z m Z ddl m Z ddl mZmZmZmZmZGd d eZy ) zACode generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.)BaseSDK)modelsutils) HookContext)OptionalNullableUNSET)eventstreaming)AnyListMappingOptionalUnionc+ eZdZdZdededdededddededddddeeejeejfde e de e d e e d e ed e ed e eej ej"fd e ede eej$ej&fde eeej(eej*fde eej,ej.fde e de e de ede ede ej2de e de ede ee e fde ej8ej:f(dZdededdededddededddddeeejeejfde e de e d e e d e ed e ed e eej ej"fd e ede eej$ej&fde eeej(eej*fde eej,ej.fde e de e de ede ede ej2de e de ede ee e fde ej>ej:f(dZ dededdededddededddddeeejBeejDfde e de e d e e d e ed e ed e eejFejHfd e ede eej$ej&fde eeej(eej*fde eejJejLfde e de e de ede ede ej2de e de ede ee e fde ejNf(dZ(dededdededddededddddeeejBeejDfde e de e d e e d e ed e ed e eejFejHfd e ede eej$ej&fde eeej(eej*fde eejJejLfde e de e de ede ede ej2de e de ede ee e fde ejNf(dZ)y)ChatzChat Completion API.azureaiNT)model temperaturetop_p max_tokensstreamstop random_seedresponse_formattools tool_choicepresence_penaltyfrequency_penaltyn safe_promptretries server_url timeout_ms http_headersmessagesrrrrrrrrrrrrrr r!r"r#r$returncd}d}||jj}||}tj|||||||t j |t tjt j | ttjt j | tt tjt j | ttj| | |||jdd||ddddd||jjfd | }|tk(r2|jj tur|jj }d}t#|tj$r|gd f}|j't)d g|jj |gdd|}d}t j*|ddrt-j.|ddSt j*|ddrOt j0|}t j2|tj4}tj6|t j*|ddgdr7t j0|}tj8d|j:|||j<j?d}t j0|}tj8d|j:d|d|j:||) Stream chat completion Mistral AI provides the ability to stream responses back to a client in order to allow partial results for certain requests. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON. :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content. :param model: The ID of the model to use for this request. :param temperature: What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 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. The default value varies depending on the model you are targeting. Call the `/models` endpoint to retrieve the appropriate value. :param top_p: 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. :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length. :param stream: :param stop: Stop generation if this token is detected. Or if one of these tokens is detected when providing an array :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results. :param response_format: :param tools: :param tool_choice: :param presence_penalty: presence_penalty determines how much the model penalizes the repetition of words or phrases. A higher presence penalty encourages the model to use a wider variety of words and phrases, making the output more diverse and creative. :param frequency_penalty: frequency_penalty penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition. :param n: Number of completions to return for each request, input tokens are only billed once. :param safe_prompt: Whether to inject a safety prompt before all conversations. :param retries: Override the default retry configuration for this method :param server_url: Override the default server URL for this method :param timeout_ms: Override the default request timeout configuration for this method in milliseconds :param http_headers: Additional headers to set or replace on requests. Nrrrrrrrr%rrrrrrr POST/chat/completions#streamTF user-agenttext/event-streamcRtjdddtjSNFjsonrserialize_request_bodyrChatCompletionStreamRequestrequestsI/var/www/openai/venv/lib/python3.12/site-packages/mistralai_azure/chat.pyzChat.stream..q!(D(Dvv/Q/Q)methodpathbase_url url_variablesr5request_body_requiredrequest_has_path_paramsrequest_has_query_paramsuser_agent_headeraccept_header_valuer$securityget_serialized_bodyr#429500502503504 stream_chat operation_id oauth2_scopessecurity_source4224XX5XXhook_ctxr5error_status_codesr retry_config200cJtj|tjSNrunmarshal_jsonrCompletionEventraws r6r7zChat.stream..E00f6L6LMr9[DONE]sentinelrRapplication/jsondatarSrT*API error occurred Content-Type$Unexpected response received (code: , type: )) sdk_configurationr#rr3rget_pydantic_modelr MessagesrResponseFormatrTool%ChatCompletionStreamRequestToolChoice_build_requestrDr rX isinstance RetryConfig do_requestrmatch_responser EventStreamstream_to_textr]HTTPValidationErrorDataHTTPValidationErrorSDKError status_codeheadersgetselfr%rrrrrrrrrrrrrr r!r"r#r$r=r>reqrXhttp_resrg http_res_text content_typer5s @r6rz Chat.streamsp  //::J  !!H44#!#--hV__8MN!44&*?*?!@**52B4 CT2UV00Xf&R&RS./#' ,!!+'"&$)%)* 3%++44!"!" & e %%22%?00== gu00 1#%HIL?? * $ 6 6 ? ? 4%#     %1D E!--M!    %1C D!00:M'' v7U7UVD,,$7 7   5%.# >!00:M//$h&:&:M8  ''++N; ,,X6 oo283G3G2HQ]P^^_ `      r9cjKd}d}||jj}||}tj|||||||t j |t tjt j | ttjt j | tt tjt j | ttj| | |||jdd||ddddd||jjfd | }|tk(r2|jj tur|jj }d}t#|tj$r|gd f}|j't)d g|jj |gdd|d{}d}t j*|ddrt-j.|ddSt j*|ddrWt j0|d{}t j2|tj4}tj6|t j*|ddgdr?t j0|d{}tj8d|j:|||j<j?d}t j0|d{}tj8d|j:d|d|j:||7h777?w)r(Nr)r*r+TFr,r-cRtjdddtjSr/r1r4sr6r7z#Chat.stream_async..r8r9r:rFrLrMrQrUrYcJtj|tjSr[r\r_s r6r7z#Chat.stream_async..&rar9rbrcrRrerfrSrTrhrirjrkrlrm) rnr#rr3rror rprrqrrrrs_build_request_asyncrDr rXrurvdo_request_asyncrrxr EventStreamAsyncstream_to_text_asyncr]r{r|r}r~rrrs @r6 stream_asynczChat.stream_asyncsp  //::J  !!H44#!#--hV__8MN!44&*?*?!@**52B4 CT2UV00Xf&R&RS./#' ,''+'"&$)%)* 3%++44!"!( & e %%22%?00== gu00 1#%HIL.. * $ 6 6 ? ? 4%/      %1D E!22M!    %1C D"'"<""'"<"L3L)A%L3'L,(A/L3L/AL31L128L3,L3/L31L3Fc.d}d}||jj}||}tj|||||||t j |t tjt j | ttjt j | tt tjt j | ttj| | |||jdd||ddddd||jjfd | }|tk(r2|jj tur|jj }d}t#|tj$r|gd f}|j't)d g|jj |gd|}d}t j*|ddr5t j,|j.ttj0St j*|ddrDt j,|j.tj2}tj4|t j*|ddgdr7t j6|}tj8d|j:|||j<j?d}t j6|}tj8d|j:d|d|j:||). Chat Completion :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content. :param model: The ID of the model to use for this request. :param temperature: What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 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. The default value varies depending on the model you are targeting. Call the `/models` endpoint to retrieve the appropriate value. :param top_p: 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. :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length. :param stream: Whether to stream back partial progress. If set, tokens will be sent as data-only server-side events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON. :param stop: Stop generation if this token is detected. Or if one of these tokens is detected when providing an array :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results. :param response_format: :param tools: :param tool_choice: :param presence_penalty: presence_penalty determines how much the model penalizes the repetition of words or phrases. A higher presence penalty encourages the model to use a wider variety of words and phrases, making the output more diverse and creative. :param frequency_penalty: frequency_penalty penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition. :param n: Number of completions to return for each request, input tokens are only billed once. :param safe_prompt: Whether to inject a safety prompt before all conversations. :param retries: Override the default retry configuration for this method :param server_url: Override the default server URL for this method :param timeout_ms: Override the default request timeout configuration for this method in milliseconds :param http_headers: Additional headers to set or replace on requests. Nr)r*/chat/completionsTFr,recRtjdddtjSr/rr2rChatCompletionRequestr4sr6r7zChat.complete..!(D(Dvv/K/K)r9r:rF(chat_completion_v1_chat_completions_postrMrQrVr5rWrXrYrRrfrSrTrhrirjrkrlrm) rnr#rrrror ChatCompletionRequestMessagesrrqrrrChatCompletionRequestToolChoicertrDr rXrurvrwrrxr]textChatCompletionResponser{r|rzr}r~rrrs @r6completez Chat.complete<s|  //::J  !!H..#!#--$vCCD"44&*?*?!@**52B4 CT2UV00Xf&L&LM./#+ 0!!$'"&$)%)* 2%++44!"!" & e %%22%?00== gu00 1#%HIL?? G $ 6 6 ? ? 4%#     %1C D'' x(E(EF    %1C D'' v7U7UVD,,$7 7   5%.# >!00:M//$h&:&:M8  ''++N; ,,X6 oo283G3G2HQ]P^^_ `      r9ctKd}d}||jj}||}tj|||||||t j |t tjt j | ttjt j | tt tjt j | ttj| | |||jdd||ddddd||jjfd | }|tk(r2|jj tur|jj }d}t#|tj$r|gd f}|j't)d g|jj |gd|d{}d}t j*|ddr5t j,|j.ttj0St j*|ddrDt j,|j.tj2}tj4|t j*|ddgdr?t j6|d{}tj8d|j:|||j<j?d}t j6|d{}tj8d|j:d|d|j:||7q77<w)rNr)r*rTFr,recRtjdddtjSr/rr4sr6r7z%Chat.complete_async..Brr9r:rFrrMrQrrYrRrfrSrTrhrirjrkrlrm) rnr#rrrror rrrqrrrrrrDr rXrurvrrrxr]rrr{r|rr}r~rrrs @r6complete_asynczChat.complete_asyncs|  //::J  !!H..#!#--$vCCD"44&*?*?!@**52B4 CT2UV00Xf&L&LM./#+ 0''$'"&$)%)* 2%++44!"!( & e %%22%?00== gu00 1#%HIL.. G $ 6 6 ? ? 4%/      %1C D'' x(E(EF    %1C D'' v7U7UVD,,$7 7   5%.# >"'"<"*>>?@U &c*U " &'')G)GG H U  $v{{#T&*>*>%?? @ U " <<EEG  #U .#5//U 0$E?1U 2 C 3U 4d^5U 6"%"3"347U 8SM9U :SM;U <wsCx01=U > .,,V-C-CD E?U v(1/4!%,1!%CG-2   ,0-1#(&*7<$($(48=U V__-tF4L4L/MMNU  $ U &e, U  U %S)U U uV[[&*>*>>?@U &c*U " &'')G)GG H U  $v{{#T&*>*>%?? @ U " <<EEG  #U .#5//U 0$E?1U 2 C 3U 4d^5U 6"%"3"347U 8SM9U :SM;U <wsCx01=U > .11&2H2HI J?U |(1/4!%,1!& -2   ,0-1#(&*7<$($(48MY  55 6 >> ? A Y  $Y &e,Y Y %S)Y Y  0099;  Y $&c*%Y &" &'')G)GG H 'Y , $v{{#T&*>*>%?? @ -Y 2 66??A  3Y >#5/?Y @$E?AY B C CY Dd^EY F"%"3"34GY HSMIY JSMKY LwsCx01MY N &// 0OY D(1/4!%,1!& -2   ,0-1#(&*7<$($(48MY  55 6 >> ? A Y  $Y &e,Y Y %S)Y Y  0099;  Y $&c*%Y &" &'')G)GG H 'Y , $v{{#T&*>*>%?? @ -Y 2 66??A  3Y >#5/?Y @$E?AY B C CY Dd^EY F"%"3"34GY HSMIY JSMKY LwsCx01MY N &// 0OY r9rN)rbasesdkrmistralai_azurerrmistralai_azure._hooksrmistralai_azure.typesrr mistralai_azure.utilsr typingr r r rrrrr9r6rs+G).9066e  7e  r9