o qmiE@sddlZddlmZddlmZddlmZmZddlm Z m Z ddl m Z ddl mZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlmZddlm Z ddl!m"Z"e#ej$dZ%GdddZ&GdddZ'dS)N)JSONDecodeError)ApiError)AsyncClientWrapperSyncClientWrapper)AsyncHttpResponse HttpResponse) parse_obj_as)RequestOptions)'convert_and_respect_annotation_metadata)BadRequestError)ForbiddenError)InternalServerError)TooManyRequestsError)UnprocessableEntityError)"ChatCompletionRequestMessageParams)StopConfigurationParams)CreateChatCompletionResponse)ReasoningEffort.c@eZdZdefddZeeeeeeeeeeedd dejedej e dej e d ej e d ej e d ej e d ej ed ej e dej e dej e dej e dej e dej edeefddZdS) RawChatClientclient_wrappercC ||_dSN_client_wrapperselfrrL/home/ubuntu/.local/lib/python3.10/site-packages/sarvamai/chat/raw_client.py__init__ zRawChatClient.__init__N temperaturetop_preasoning_effort max_tokensstreamstopnseedfrequency_penaltypresence_penaltywiki_groundingrequest_optionsmessagesr#r$r%r&r'r(r)r*r+r,r-r.returnc Cs*|jjjd|jjdt|tjtdd|||||t|t dd|| | | | dd ddi| t d }zd |j kr;d krPnnt t tt |d }t||d WS|j dkrptt|jt tjtjttjtj|d d|j dkrtt|jt tjtjttjtj|d d|j dkrtt|jt tjtjttjtj|d d|j dkrtt|jt tjtjttjtj|d d|j dkrtt|jt tjtjttjtj|d d|}Wnty t|j t|j|jdwt|j t|j|d)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 ------- HttpResponse[CreateChatCompletionResponse] Successful Response v1/chat/completionsPOSTwriteobject_ annotation directionsarvam-m r/r#r$r%r&r'r(r)r*r+r,r-model content-typeapplication/jsonbase_urlmethodjsonheadersr.omit,type_r5responsedatarAbody status_coderArL)r httpx_clientrequestget_environmentbaser typingSequencerrOMITrRcastrr r@rr dictrAOptionalAnyr rrrrrtextrr/r#r$r%r&r'r(r)r*r+r,r-r. _response_data_response_jsonrrr completionssL                  zRawChatClient.completions)__name__ __module__ __qualname__rr rYrWrXrr\floatrintboolrr rrrcrrrrrV     rc@r)AsyncRawChatClientrcCrrrrrrrr r!zAsyncRawChatClient.__init__Nr"r/r#r$r%r&r'r(r)r*r+r,r-r.r0c s2|jjjd|jjdt|tjtdd|||||t|t dd|| | | | dd ddi| t d Id H}zd |j kr?d krTnnt t tt |d }t||dWS|j dkrttt|jt tjtjttjtj|d d|j dkrtt|jt tjtjttjtj|d d|j dkrtt|jt tjtjttjtj|d d|j dkrtt|jt tjtjttjtj|d d|j dkrtt|jt tjtjttjtj|d d|}Wnty t|j t|j|jdwt|j t|j|d)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 ------- AsyncHttpResponse[CreateChatCompletionResponse] Successful Response r1r2r3r4r8r9r;r<r=NrCrDrErGrJrKrMrNrOrPrQ)rrSrTrUrVr rWrXrrrYrRrZrr r@rr r[rAr\r]r rrrrrr^r_rrrrcsL                   zAsyncRawChatClient.completions)rdrerfrr rYrWrXrr\rgrrhrirr rrrcrrrrrkrjrk)(rW json.decoderrcore.api_errorrcore.client_wrapperrrcore.http_responserrcore.pydantic_utilitiesr core.request_optionsr core.serializationr errors.bad_request_errorr errors.forbidden_errorr errors.internal_server_errorrerrors.too_many_requests_errorr!errors.unprocessable_entity_errorr(requests.chat_completion_request_messagerrequests.stop_configurationr%types.create_chat_completion_responsertypes.reasoning_effortrrZr]rYrrkrrrrs*              5