o FiJ@sddlZddlmZmZddlmZddlmZddlm Z ddl m Z ddl m Z dd lmZdd lmZdd lmZdd lmZd dlmZmZeejdZGdddZGdddZdS)N)AsyncClientWrapperSyncClientWrapper)RequestOptions)"ChatCompletionRequestMessageParams)ChatCompletionToolParams)StopConfigurationParams)ToolChoiceOptionParams)ChatCompletionChunk)CreateChatCompletionResponse)ReasoningEffort)SarvamModelIds)AsyncRawChatClient RawChatClient.c&@eZdZdefddZedefddZej dddddddddddddd d ej e d e d ej ed ej ed ej edej edejddej edej edej edej edej edej edej ej edej edej edejef"ddZej dddddddddddddddd ej e d e d ej ed ej ed ej edej edej ejddej edej edej edej edej edej edej ej edej edej edef"ddZeeeeeeeeeeeeeddd ej e d e d ej ed ej ed ej edej edej edej edej edej edej edej edej edej ej edej edej edejeejeff"d dZdS)! ChatClientclient_wrappercCt|d|_dSN)r)r _raw_clientselfrra/home/aiteam/pcaa-dev/dashboard-backend/venv/lib/python3.10/site-packages/sarvamai/chat/client.py__init__zChatClient.__init__returncC|jS)z Retrieves a raw implementation of this client that returns raw responses. Returns ------- RawChatClient rrrrrwith_raw_response zChatClient.with_raw_response. temperaturetop_preasoning_effort max_tokensstopnseedfrequency_penaltypresence_penaltywiki_groundingtools tool_choicerequest_optionsmessagesmodelr$r%r&r'streamTr(r)r*r+r,r-r.r/r0cCdSNrrr1r2r$r%r&r'r3r(r)r*r+r,r-r.r/r0rrr completions$zChatClient.completionsr$r%r&r'r3r(r)r*r+r,r-r.r/r0FcCr4r5rr6rrrr7:r8NcCs|dur;|jjdid|d|d|d|d|d|ddd |d | d | d | d | d| d|d|d|S|jjdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|}|jS)a~ Parameters ---------- messages : typing.Sequence[ChatCompletionRequestMessageParams] A list of messages comprising the conversation so far. model : SarvamModelIds Model ID used to generate the response, like `sarvam-m`. temperature : typing.Optional[float] 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. top_p : typing.Optional[float] 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. reasoning_effort : typing.Optional[ReasoningEffort] The effort to use for reasoning max_tokens : typing.Optional[int] The maximum number of tokens that can be generated in the chat completion. stream : typing.Optional[bool] If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). When true, returns an Iterator[ChatCompletionChunk] instead of CreateChatCompletionResponse. stop : typing.Optional[StopConfigurationParams] n : typing.Optional[int] 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. seed : typing.Optional[int] 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. frequency_penalty : typing.Optional[float] 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. presence_penalty : typing.Optional[float] 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. wiki_grounding : typing.Optional[bool] If set to true, the model response will be wiki grounded. tools : typing.Optional[typing.Sequence[ChatCompletionToolParams]] A list of tools the model may call. Currently, only functions are supported as a tool. tool_choice : typing.Optional[ToolChoiceOptionParams] Controls which (if any) tool is called by the model. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- CreateChatCompletionResponse or Iterator[ChatCompletionChunk] When stream=False (default): CreateChatCompletionResponse. When stream=True: Iterator yielding ChatCompletionChunk objects. Examples -------- from sarvamai import SarvamAI client = SarvamAI( api_subscription_key="YOUR_API_SUBSCRIPTION_KEY", ) # Non-streaming response = client.chat.completions( messages=[{"role": "user", "content": "Hello"}], model="sarvam-m", ) # Streaming for chunk in client.chat.completions( messages=[{"role": "user", "content": "Hello"}], model="sarvam-m", stream=True, ): print(chunk) Tr1r2r$r%r&r'r3r(r)r*r+r,r-r.r/r0Nrrr7datarr1r2r$r%r&r'r3r(r)r*r+r,r-r.r/r0 _responserrrr7Psp            )__name__ __module__ __qualname__rrpropertyrr!typingoverloadSequencerr Optionalfloatr intLiteralrboolrr rIteratorr r7r OMITUnionrrrrr0                  rc&@r)!AsyncChatClientrcCrr)rrrrrrrrzAsyncChatClient.__init__rcCr)z Retrieves a raw implementation of this client that returns raw responses. Returns ------- AsyncRawChatClient rr rrrr!r"z!AsyncChatClient.with_raw_response.r#r1r2r$r%r&r'r3Tr(r)r*r+r,r-r.r/r0cdSr5rr6rrrr7zAsyncChatClient.completionsr9FcrOr5rr6rrrr7rPNcs|dur?|jjdid|d|d|d|d|d|ddd |d | d | d | d | d| d|d|d|IdHS|jjdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|IdH}|jS)a) Parameters ---------- messages : typing.Sequence[ChatCompletionRequestMessageParams] A list of messages comprising the conversation so far. model : SarvamModelIds Model ID used to generate the response, like `sarvam-m`. temperature : typing.Optional[float] 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. top_p : typing.Optional[float] 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. reasoning_effort : typing.Optional[ReasoningEffort] The effort to use for reasoning max_tokens : typing.Optional[int] The maximum number of tokens that can be generated in the chat completion. stream : typing.Optional[bool] If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). When true, returns an AsyncIterator[ChatCompletionChunk] instead of CreateChatCompletionResponse. stop : typing.Optional[StopConfigurationParams] n : typing.Optional[int] 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. seed : typing.Optional[int] 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. frequency_penalty : typing.Optional[float] 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. presence_penalty : typing.Optional[float] 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. wiki_grounding : typing.Optional[bool] If set to true, the model response will be wiki grounded. tools : typing.Optional[typing.Sequence[ChatCompletionToolParams]] A list of tools the model may call. Currently, only functions are supported as a tool. tool_choice : typing.Optional[ToolChoiceOptionParams] Controls which (if any) tool is called by the model. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- CreateChatCompletionResponse or AsyncIterator[ChatCompletionChunk] When stream=False (default): CreateChatCompletionResponse. When stream=True: AsyncIterator yielding ChatCompletionChunk objects. Examples -------- import asyncio from sarvamai import AsyncSarvamAI client = AsyncSarvamAI( api_subscription_key="YOUR_API_SUBSCRIPTION_KEY", ) async def main() -> None: # Non-streaming response = await client.chat.completions( messages=[{"role": "user", "content": "Hello"}], model="sarvam-m", ) # Streaming async for chunk in client.chat.completions( messages=[{"role": "user", "content": "Hello"}], model="sarvam-m", stream=True, ): print(chunk) asyncio.run(main()) Tr1r2r$r%r&r'r3r(r)r*r+r,r-r.r/r0Nrr:r<rrrr7$st             )r>r?r@rrrArr!rBrCrDrr rErFr rGrHrrIrr r AsyncIteratorr r7r rKrLrrrrrNrMrN)rBcore.client_wrapperrrcore.request_optionsr(requests.chat_completion_request_messagerrequests.chat_completion_toolrrequests.stop_configurationrrequests.tool_choice_optionr types.chat_completion_chunkr %types.create_chat_completion_responser types.reasoning_effortr types.sarvam_model_idsr raw_clientrrcastAnyrKrrNrrrrs          U