o Fi@s6ddlZddlZddlmZddlmZddlmZmZddl m Z m Z ddl m Z ddlmZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlmZddl m!Z!ddl"m#Z#ddl$m%Z%ddl&m'Z'ddl(m)Z)ddl*m+Z+e,ej-dZ.GdddZ/GdddZ0dS)N)JSONDecodeError)ApiError)AsyncClientWrapperSyncClientWrapper)AsyncHttpResponse HttpResponse) parse_obj_as)RequestOptions)'convert_and_respect_annotation_metadata)BadRequestError)ForbiddenError)InternalServerError)TooManyRequestsError)UnprocessableEntityError)"ChatCompletionRequestMessageParams)ChatCompletionToolParams)StopConfigurationParams)ToolChoiceOptionParams)ChatCompletionChunk)CreateChatCompletionResponse)ReasoningEffort)SarvamModelIds.c&@zeZdZdefddZejdddddddddddddd dejede dej e d ej e d ej e d ej e d ejd dej edej e dej e dej e dej e dej edej ejedej edej edejef"ddZejddddddddddddddddejede dej e d ej e d ej e d ej e d ej ejddej edej e dej e dej e dej e dej edej ejedej edej edeef"ddZeeeeeeeeeeeeedddejede dej e d ej e d ej e d ej e d ej edej edej e dej e dej e dej e dej edej ejedej edej edejeeejeff"ddZeeeeeeeeeeeedd dejede dej e d ej e d ej e d ej e dej edej e dej e dej e dej e dej edej ejedej edej edejef dd ZdS)! RawChatClientclient_wrappercC ||_dSN_client_wrapperselfrr"e/home/aiteam/pcaa-dev/dashboard-backend/venv/lib/python3.10/site-packages/sarvamai/chat/raw_client.py__init__  zRawChatClient.__init__. temperaturetop_preasoning_effort max_tokensstopnseedfrequency_penaltypresence_penaltywiki_groundingtools tool_choicerequest_optionsmessagesmodelr'r(r)r*streamTr+r,r-r.r/r0r1r2r3returncCdSrr"r!r4r5r'r(r)r*r6r+r,r-r.r/r0r1r2r3r"r"r# completions#zRawChatClient.completionsr'r(r)r*r6r+r,r-r.r/r0r1r2r3FcCr8rr"r9r"r"r#r:9r;NcCsz|dur|j|||||||| | | | | |||dS|jjjd|jjdt|tjt dd||||||t|t dd| | | | | t|tjt ddt|t ddddd i|t d }zd |jkrbd krwnntttt|d }t||dWS|jdkrtt|jttjtjttjtj|d d|jdkrtt|jttjtjttjtj|d d|jdkrtt|jttjtjttjtj|d d|jdkrtt|jttjtjttjtj|d d|jdkrtt|jttjtjttjtj|d d|}Wnty1t|jt|j|jdwt|jt|j|d)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 HttpResponse. 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 ------- HttpResponse[CreateChatCompletionResponse] or Iterator[ChatCompletionChunk] When stream=False (default): HttpResponse wrapping CreateChatCompletionResponse. When stream=True: Iterator yielding ChatCompletionChunk objects. Tr4r5r'r(r)r*r+r,r-r.r/r0r1r2r3v1/chat/completionsPOSTwriteobject_ annotation directionr4r5r'r(r)r*r6r+r,r-r.r/r0r1r2 content-typeapplication/jsonbase_urlmethodjsonheadersr3omit,type_rBresponsedatarLbody status_coderLrW) _completions_streamr httpx_clientrequestget_environmentbaser typingSequencerrrrOMITr]castrr rKrr dictrLOptionalAnyr rrrrrtextr!r4r5r'r(r)r*r6r+r,r-r.r/r0r1r2r3 _response_data_response_jsonr"r"r#r:OsZ   #                ccs|jjjd|jjdt|tjtdd|||||dt|t dd|| | | | t| tjt ddt|t dddddi|t d |}d |j krKd ksnn|z|}Wn tyb|j}Ynwt|j t|j|d |D]@}|swqr|d r|td d}|dkrWddSzt|}tttt|d}|VWqrtjyYqrwqrWddS1swYdSNr>r?r@rATrErFrGrHrNrOr\zdata: z[DONE]rP)rr_r6rarbr rcrdrrrrrer]readrK ExceptionrjrrgrL iter_lines startswithlenstriploadsrfrr rr!r4r5r'r(r)r*r+r,r-r.r/r0r1r2r3rl_body_line _data_str _chunk_json_chunkr"r"r#r^%s   "      2  "z!RawChatClient._completions_stream)__name__ __module__ __qualname__rr$rcoverloadrdrrrhfloatrintLiteralrboolrrr Iteratorrr:rrreUnionr^r"r"r"r#r                  \     rc&@r)!AsyncRawChatClientrcCrrrr r"r"r#r$yr%zAsyncRawChatClient.__init__.r&r4r5r'r(r)r*r6Tr+r,r-r.r/r0r1r2r3r7cdSrr"r9r"r"r#r:|zAsyncRawChatClient.completionsr<Fcrrr"r9r"r"r#r:rNcs|dur|j|||||||| | | | | |||dS|jjjd|jjdt|tjt dd||||||t|t dd| | | | | t|tjt ddt|t ddddd i|t d Id H}zd |jkrfd kr{nntttt|d}t||dWS|jdkrtt|jttjtjttjtj|dd|jdkrtt|jttjtjttjtj|dd|jdkrtt|jttjtjttjtj|dd|jdkrtt|jttjtjttjtj|dd|jdkrtt|jttjtjttjtj|dd|}Wnty5t|jt|j|jdwt|jt|j|d)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 AsyncHttpResponse. 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 ------- AsyncHttpResponse[CreateChatCompletionResponse] or AsyncIterator[ChatCompletionChunk] When stream=False (default): AsyncHttpResponse wrapping CreateChatCompletionResponse. When stream=True: AsyncIterator yielding ChatCompletionChunk objects. Tr=r>r?r@rArErFrGrHNrNrOrPrRrUrVrXrYrZr[r\) r^rr_r`rarbr rcrdrrrrrer]rfrr rKrr rgrLrhrir rrrrrrjrkr"r"r#r:sZ    #                cCs|jjjd|jjdt|tjtdd|||||dt|t dd|| | | | t| tjt ddt|t dddddi|t d 4IdH}d |j krOd ksun|IdHz|}Wn tyi|j}Ynwt|j t|j|d |2zG3dHW}|sqy|d r|td d}|dkrWdIdHdSzt|}tttt|d}|VWqytjyYqywqy6WdIdHdS1IdHswYdSro)rr_r6rarbr rcrdrrrrrer]areadrKrqrjrrgrL aiter_linesrsrtrurvrfrr rrwr"r"r#r^~s   "     2  .z&AsyncRawChatClient._completions_stream)r}r~rrr$rcrrdrrrhrrrrrrrrr AsyncIteratorrr:rrrerr^r"r"r"r#rxrr)1rKrc 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.chat_completion_toolrrequests.stop_configurationrrequests.tool_choice_optionrtypes.chat_completion_chunkr%types.create_chat_completion_responsertypes.reasoning_effortrtypes.sarvam_model_idsrrfrirerrr"r"r"r#s6                  [