o hW@shddlmZddlmZmZmZmZmZmZddl m Z ddl Z ddl m Z mZmZmZmZddlmZmZddlmZdd lmZmZdd lmZmZmZmZdd lm Z m!Z!dd l"m#Z#dd l$m%Z%ddl&m'Z'ddl(m)Z)ddl*m+Z+ddl,m-Z-ddl.m/Z/ddgZ0GdddeZ1GdddeZ2GdddZ3GdddZ4GdddZ5GdddZ6dS)) annotations)DictListUnionIterableOptionaloverload)LiteralN) NOT_GIVENBodyQueryHeadersNotGiven)maybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_raw_response_wrapperto_streamed_response_wrapperasync_to_raw_response_wrapper"async_to_streamed_response_wrapper)Stream AsyncStream)completion_create_params)make_request_options)ChatCompletion)ChatCompletionChunk)ChatCompletionToolParam)ChatCompletionMessageParam)#ChatCompletionToolChoiceOptionParam CompletionsAsyncCompletionsc@8eZdZedGddZedHddZeeeeeeeeeeeeeeeeeeeeeeeddded dId;d<Zeeeeeeeeeeeeeeeeeeeeeeddded=dJd@d<Zeeeeeeeeeeeeeeeeeeeeeeddded=dKdCd<Zeeeeeeeeeeeeeeeeeeeeeeddded dLdFd<ZdS)Mr"returnCompletionsWithRawResponsecCt|Sa  This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content. For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers )r&selfr+s/var/www/html/construction_image-detection-poc/venv/lib/python3.10/site-packages/groq/resources/chat/completions.pywith_raw_response$zCompletions.with_raw_response CompletionsWithStreamingResponsecCr'z An alternative to `.with_raw_response` that doesn't eagerly read the response body. For more information, see https://www.github.com/groq/groq-python#with_streaming_response )r/r)r+r+r,with_streaming_response.z#Completions.with_streaming_responseNfrequency_penalty function_call functions logit_biaslogprobsmax_completion_tokens max_tokensnparallel_tool_callspresence_penaltyreasoning_formatresponse_formatseed service_tierstopstream temperature tool_choicetools top_logprobstop_puser extra_headers extra_query extra_bodytimeoutmessages$Iterable[ChatCompletionMessageParam]modelstrr4Optional[float] | NotGivenr5:Optional[completion_create_params.FunctionCall] | NotGivenr6@Optional[Iterable[completion_create_params.Function]] | NotGivenr7#Optional[Dict[str, int]] | NotGivenr8Optional[bool] | NotGivenr9Optional[int] | NotGivenr:r;r<r=r>7Optional[Literal['hidden', 'raw', 'parsed']] | NotGivenr?r?r@rArBrCrDrErFrGrHrIrJrKrLrMr+r+r,create7#zCompletions.creater4r5r6r7r8r9r:r;r<r=r>r?r@rArBrDrErFrGrHrIrJrKrLrM Literal[True]Stream[ChatCompletionChunk]cCrdrer+rfr+r+r,rg\rhbool,ChatCompletion | Stream[ChatCompletionChunk]cCrdrer+rfr+r+r,rgrh]Union[str, Literal['gemma-7b-it', 'llama3-70b-8192', 'llama3-8b-8192', 'mixtral-8x7b-32768']]3Optional[Literal[False]] | Literal[True] | NotGivenc Cs|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d||||||||dtjt||||dt|pPdttdS)9 Creates a model response for the given chat conversation. Args: messages: A list of messages comprising the conversation so far. model: ID of the model to use. For details on which models are compatible with the Chat API, see available [models](/docs/models) frequency_penalty: 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. function_call: Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. functions: Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for. logit_bias: This is not yet supported by any of our models. Modify the likelihood of specified tokens appearing in the completion. logprobs: This is not yet supported by any of our models. Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. max_completion_tokens: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. max_tokens: Deprecated in favor of `max_completion_tokens`. The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. n: How many chat completion choices to generate for each input message. Note that the current moment, only n=1 is supported. Other values will result in a 400 response. parallel_tool_calls: Whether to enable parallel function calling during tool use. presence_penalty: 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. reasoning_format: Specifies how to output reasoning tokens response_format: An object specifying the format that the model must output. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. seed: 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. service_tier: The service tier to use for the request. Defaults to `on_demand`. - `auto` will automatically select the highest tier available within the rate limits of your organization. - `flex` uses the flex tier, which will succeed or fail quickly. stop: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. stream: If set, partial message deltas will be sent. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example code](/docs/text-chat#streaming-a-chat-completion). temperature: 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 tool_choice: Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools are present. tools: A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. top_logprobs: This is not yet supported by any of our models. An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. top_p: 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. user: A unique identifier representing your end-user, which can help us monitor and detect abuse. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds /openai/v1/chat/completionsrNrPr4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrErFrGrHrIrJrKrLrMFbodyoptionscast_torC stream_cls)_postrrCompletionCreateParamsrrrrrfr+r+r,rgsp     )r%r&)r%r/:rNrOrPrQr4rRr5rSr6rTr7rUr8rVr9rWr:rWr;rWr<rVr=rRr>rXr?rYr@rWrArZrBr[rCr\rDrRrEr]rFr^rGrWrHrRrIr_rJr`rKrarLrbrMrcr%r):rNrOrPrQr4rRr5rSr6rTr7rUr8rVr9rWr:rWr;rWr<rVr=rRr>rXr?rYr@rWrArZrBr[rCrjrDrRrEr]rFr^rGrWrHrRrIr_rJr`rKrarLrbrMrcr%rk):rNrOrPrQr4rRr5rSr6rTr7rUr8rVr9rWr:rWr;rWr<rVr=rRr>rXr?rYr@rWrArZrBr[rCrlrDrRrEr]rFr^rGrWrHrRrIr_rJr`rKrarLrbrMrcr%rm):rNrOrPrnr4rRr5rSr6rTr7rUr8rVr9rWr:rWr;rWr<rVr=rRr>rXr?rYr@rWrArZrBr[rCrorDrRrEr]rFr^rGrWrHrRrIr_rJr`rKrarLrbrMrcr%rm __name__ __module__ __qualname__rr-r1rr rgr+r+r+r,r"#  $$)c@r$)Mr#r%AsyncCompletionsWithRawResponsecCr'r()rr)r+r+r,r-kr.z"AsyncCompletions.with_raw_response%AsyncCompletionsWithStreamingResponsecCr'r0)rr)r+r+r,r1ur2z(AsyncCompletions.with_streaming_responseNr3rNrOrPrQr4rRr5rSr6rTr7rUr8rVr9rWr:r;r<r=r>rXr?rYr@rArZrBr[rCr\rDrEr]rFr^rGrHrIr_rJr`rKrarLrbrMrcrcdSrer+rfr+r+r,rg~#zAsyncCompletions.createrirj AsyncStream[ChatCompletionChunk]crrer+rfr+r+r,rgrrl1ChatCompletion | AsyncStream[ChatCompletionChunk]crrer+rfr+r+r,rgrrnroc s|jdtid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d||||||||dtjIdHt||||dt|pTdttdIdHS)rprqrNrPr4r5r6r7r8r9r:r;r<r=r>r?r@rArBrrNrsFrt)ryrrrzrrrrrfr+r+r,rgsr      )r%r)r%rr{):rNrOrPrQr4rRr5rSr6rTr7rUr8rVr9rWr:rWr;rWr<rVr=rRr>rXr?rYr@rWrArZrBr[rCrjrDrRrEr]rFr^rGrWrHrRrIr_rJr`rKrarLrbrMrcr%r):rNrOrPrQr4rRr5rSr6rTr7rUr8rVr9rWr:rWr;rWr<rVr=rRr>rXr?rYr@rWrArZrBr[rCrlrDrRrEr]rFr^rGrWrHrRrIr_rJr`rKrarLrbrMrcr%r):rNrOrPrnr4rRr5rSr6rTr7rUr8rVr9rWr:rWr;rWr<rVr=rRr>rXr?rYr@rWrArZrBr[rCrorDrRrEr]rFr^rGrWrHrRrIr_rJr`rKrarLrbrMrcr%rr|r+r+r+r,r#jrc@eZdZdddZdS) r& completionsr"r%NonecC||_t|j|_dSre) _completionsrrgr*rr+r+r,__init__ z#CompletionsWithRawResponse.__init__Nrr"r%rr}r~rrr+r+r+r,r&r&c@r) rrr#r%rcCrre)rrrgrr+r+r,rrz(AsyncCompletionsWithRawResponse.__init__Nrr#r%rrr+r+r+r,rrrc@r) r/rr"r%rcCrre)rrrgrr+r+r,rrz)CompletionsWithStreamingResponse.__init__Nrrr+r+r+r,r/rr/c@r) rrr#r%rcCrre)rrrgrr+r+r,rrz.AsyncCompletionsWithStreamingResponse.__init__Nrrr+r+r+r,rrr)7 __future__rtypingrrrrrrtyping_extensionsr httpx_typesr r r rr_utilsrr_compatr _resourcerr _responserrrr _streamingrr types.chatr _base_clientrtypes.chat.chat_completionr types.chat.chat_completion_chunkr%types.chat.chat_completion_tool_paramr(types.chat.chat_completion_message_paramr 3types.chat.chat_completion_tool_choice_option_paramr!__all__r"r#r&rr/rr+r+r+r,s8           II