o qmi+@sddlZddlmZmZddlmZddlmZddlm Z ddl m Z ddl m Z d d lmZmZeejd ZGd d d ZGdddZdS)N)AsyncClientWrapperSyncClientWrapper)RequestOptions)"ChatCompletionRequestMessageParams)StopConfigurationParams)CreateChatCompletionResponse)ReasoningEffort)AsyncRawChatClient RawChatClient.c@eZdZdefddZedefddZeeeeeeeeeeedd d e j e d e j e d e j e d e j ed e j ede j ede j ede j ede j ede j e de j e de j ede j edefddZdS) ChatClientclient_wrappercCt|d|_dSN)r)r _raw_clientselfrrH/home/ubuntu/.local/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_responseN temperaturetop_preasoning_effort max_tokensstreamstopnseedfrequency_penaltypresence_penaltywiki_groundingrequest_optionsmessagesr r!r"r#r$r%r&r'r(r)r*r+c Cs,|jj||||||||| | | | | d }|jS)a Calls Sarvam LLM API to get the chat completion. Supported model(s): `sarvam-m`. Parameters ---------- messages : typing.Sequence[ChatCompletionRequestMessageParams] A list of messages comprising the conversation so far. 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] 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). 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. 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 this parameter is enabled, then the model uses a RAG based approach to retrieve relevant chunks from Wikipedia and uses them to answer the question. This is particularly useful for queries seeking factual information. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- CreateChatCompletionResponse Successful Response Examples -------- from sarvamai import SarvamAI client = SarvamAI( api_subscription_key="YOUR_API_SUBSCRIPTION_KEY", ) client.chat.completions( messages=[{"content": "content", "role": "assistant"}], ) r,r r!r"r#r$r%r&r'r(r)r*r+r completionsdatarr,r r!r"r#r$r%r&r'r(r)r*r+ _responserrrr/ s WzChatClient.completions)__name__ __module__ __qualname__rrpropertyr rOMITtypingSequencerOptionalfloatr intboolrrrr/rrrrrZ     rc@r )AsyncChatClientrcCrr)r rrrrrrrzAsyncChatClient.__init__rcCr)z Retrieves a raw implementation of this client that returns raw responses. Returns ------- AsyncRawChatClient rrrrrrrz!AsyncChatClient.with_raw_responseNrr,r r!r"r#r$r%r&r'r(r)r*r+c s4|jj||||||||| | | | | d IdH}|jS)a Calls Sarvam LLM API to get the chat completion. Supported model(s): `sarvam-m`. Parameters ---------- messages : typing.Sequence[ChatCompletionRequestMessageParams] A list of messages comprising the conversation so far. 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] 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). 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. 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 this parameter is enabled, then the model uses a RAG based approach to retrieve relevant chunks from Wikipedia and uses them to answer the question. This is particularly useful for queries seeking factual information. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- CreateChatCompletionResponse Successful Response Examples -------- import asyncio from sarvamai import AsyncSarvamAI client = AsyncSarvamAI( api_subscription_key="YOUR_API_SUBSCRIPTION_KEY", ) async def main() -> None: await client.chat.completions( messages=[{"content": "content", "role": "assistant"}], ) asyncio.run(main()) r-Nr.r1rrrr/s"_ zAsyncChatClient.completions)r3r4r5rrr6r rr7r8r9rr:r;r r<r=rrrr/rrrrr?r>r?)r8core.client_wrapperrrcore.request_optionsr(requests.chat_completion_request_messagerrequests.stop_configurationr%types.create_chat_completion_responsertypes.reasoning_effortr raw_clientr r castAnyr7rr?rrrrs     x