# This file was auto-generated by Fern from our API Definition. import typing from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ..core.request_options import RequestOptions from ..requests.chat_completion_request_message import ChatCompletionRequestMessageParams from ..requests.stop_configuration import StopConfigurationParams from ..types.create_chat_completion_response import CreateChatCompletionResponse from ..types.reasoning_effort import ReasoningEffort from .raw_client import AsyncRawChatClient, RawChatClient # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class ChatClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._raw_client = RawChatClient(client_wrapper=client_wrapper) @property def with_raw_response(self) -> RawChatClient: """ Retrieves a raw implementation of this client that returns raw responses. Returns ------- RawChatClient """ return self._raw_client def completions( self, *, messages: typing.Sequence[ChatCompletionRequestMessageParams], temperature: typing.Optional[float] = OMIT, top_p: typing.Optional[float] = OMIT, reasoning_effort: typing.Optional[ReasoningEffort] = OMIT, max_tokens: typing.Optional[int] = OMIT, stream: typing.Optional[bool] = OMIT, stop: typing.Optional[StopConfigurationParams] = OMIT, n: typing.Optional[int] = OMIT, seed: typing.Optional[int] = OMIT, frequency_penalty: typing.Optional[float] = OMIT, presence_penalty: typing.Optional[float] = OMIT, wiki_grounding: typing.Optional[bool] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> CreateChatCompletionResponse: """ 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"}], ) """ _response = self._raw_client.completions( messages=messages, temperature=temperature, top_p=top_p, reasoning_effort=reasoning_effort, max_tokens=max_tokens, stream=stream, stop=stop, n=n, seed=seed, frequency_penalty=frequency_penalty, presence_penalty=presence_penalty, wiki_grounding=wiki_grounding, request_options=request_options, ) return _response.data class AsyncChatClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._raw_client = AsyncRawChatClient(client_wrapper=client_wrapper) @property def with_raw_response(self) -> AsyncRawChatClient: """ Retrieves a raw implementation of this client that returns raw responses. Returns ------- AsyncRawChatClient """ return self._raw_client async def completions( self, *, messages: typing.Sequence[ChatCompletionRequestMessageParams], temperature: typing.Optional[float] = OMIT, top_p: typing.Optional[float] = OMIT, reasoning_effort: typing.Optional[ReasoningEffort] = OMIT, max_tokens: typing.Optional[int] = OMIT, stream: typing.Optional[bool] = OMIT, stop: typing.Optional[StopConfigurationParams] = OMIT, n: typing.Optional[int] = OMIT, seed: typing.Optional[int] = OMIT, frequency_penalty: typing.Optional[float] = OMIT, presence_penalty: typing.Optional[float] = OMIT, wiki_grounding: typing.Optional[bool] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> CreateChatCompletionResponse: """ 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()) """ _response = await self._raw_client.completions( messages=messages, temperature=temperature, top_p=top_p, reasoning_effort=reasoning_effort, max_tokens=max_tokens, stream=stream, stop=stop, n=n, seed=seed, frequency_penalty=frequency_penalty, presence_penalty=presence_penalty, wiki_grounding=wiki_grounding, request_options=request_options, ) return _response.data