a !f@s$ddlmZddlmZmZmZmZmZmZddl m Z ddl Z ddl m Z mZmZmZmZddlmZmZddlmZmZdd lmZmZdd lmZmZdd lmZm Z m!Z!m"Z"m#Z#m$Z$dd l%m&Z&erdd l'm(Z(m)Z)ddgZ*GdddeZ+GdddeZ,GdddZ-GdddZ.dS)) annotations) TYPE_CHECKINGDictListUnionOptionaloverload)LiteralN) NOT_GIVENBodyQueryHeadersNotGiven) required_argsmaybe_transform)SyncAPIResourceAsyncAPIResource)to_raw_response_wrapperasync_to_raw_response_wrapper)Stream AsyncStream)ChatCompletionChatCompletionChunkChatCompletionToolParamChatCompletionMessageParam#ChatCompletionToolChoiceOptionParamcompletion_create_params)make_request_options)OpenAI AsyncOpenAI CompletionsAsyncCompletionscseZdZUded<dddfdd Zeeeeeeeeeeeeeeeeeddded d d d d ddddd ddddd ddd dddddddddZeeeeeeeeeeeeeeeedddedd d d d d ddddd dddd ddd dddddd!d"d#dZeeeeeeeeeeeeeeeedddedd d d$d d ddddd dddd ddd dddddd%d"d&dZed'd(ggd)eeeeeeeeeeeeeeeeddded d d d d ddddd dddd*d ddd dddddd%dd+dZZ S),r!CompletionsWithRawResponsewith_raw_responserNoneclientreturncst|t||_dSN)super__init__r#r$selfr' __class__b/var/www/html/python-backend/venv/lib/python3.9/site-packages/openai/resources/chat/completions.pyr+"s zCompletions.__init__Nfrequency_penalty function_call functions logit_bias max_tokensnpresence_penaltyresponse_formatseedstopstream temperature tool_choicetoolstop_puser extra_headers extra_query extra_bodytimeout List[ChatCompletionMessageParam]Union[str, Literal['gpt-4-1106-preview', 'gpt-4-vision-preview', 'gpt-4', 'gpt-4-0314', 'gpt-4-0613', 'gpt-4-32k', 'gpt-4-32k-0314', 'gpt-4-32k-0613', 'gpt-3.5-turbo-1106', 'gpt-3.5-turbo', 'gpt-3.5-turbo-16k', 'gpt-3.5-turbo-0301', 'gpt-3.5-turbo-0613', 'gpt-3.5-turbo-16k-0613']]Optional[float] | NotGiven0completion_create_params.FunctionCall | NotGiven2List[completion_create_params.Function] | NotGiven#Optional[Dict[str, int]] | NotGivenOptional[int] | NotGiven2completion_create_params.ResponseFormat | NotGiven*Union[Optional[str], List[str]] | NotGiven#Optional[Literal[False]] | NotGiven.ChatCompletionToolChoiceOptionParam | NotGiven(List[ChatCompletionToolParam] | NotGivenstr | NotGivenHeaders | None Query | None Body | None'float | httpx.Timeout | None | NotGivenrmessagesmodelr3r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrErFr(cCsdSa Creates a model response for the given chat conversation. Args: messages: A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). model: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API. 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. [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details) 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: Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. max_tokens: The maximum number of [tokens](/tokenizer) to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. n: How many chat completion choices to generate for each input message. 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. [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details) 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. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in increased latency and appearance of a "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. seed: 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. stop: Up to 4 sequences where the API will stop generating further tokens. stream: If set, partial message deltas will be sent, like in ChatGPT. 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 Python code](https://cookbook.openai.com/examples/how_to_stream_completions). 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) 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 `{"type: "function", "function": {"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. 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. 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 OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids). 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 Nr0r-rYrZr3r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrErFr0r0r1create&s*zCompletions.creater3r4r5r6r7r8r9r:r;r<r>r?r@rArBrCrDrErF Literal[True]zStream[ChatCompletionChunk]rYrZr=r3r4r5r6r7r8r9r:r;r<r>r?r@rArBrCrDrErFr(cCsdSa Creates a model response for the given chat conversation. Args: messages: A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). model: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API. stream: If set, partial message deltas will be sent, like in ChatGPT. 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 Python code](https://cookbook.openai.com/examples/how_to_stream_completions). 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. [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details) 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: Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. max_tokens: The maximum number of [tokens](/tokenizer) to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. n: How many chat completion choices to generate for each input message. 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. [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details) 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. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in increased latency and appearance of a "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. seed: 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. stop: Up to 4 sequences where the API will stop generating further tokens. 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) 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 `{"type: "function", "function": {"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. 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. 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 OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids). 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 Nr0r-rYrZr=r3r4r5r6r7r8r9r:r;r<r>r?r@rArBrCrDrErFr0r0r1r]s*boolz,ChatCompletion | Stream[ChatCompletionChunk]cCsdSrar0rbr0r0r1r]|s*rYrZrYrZr=3Optional[Literal[False]] | Literal[True] | NotGivencCsX|jdt||||||||| | | | | |||||dtjt||||dt| pLdttdSNz/chat/completions)rYrZr3r4r5r6r7r8r9r:r;r<r=r>r?r@rArB)rCrDrErFF)bodyoptionsZcast_tor=Z stream_cls)_postrrCompletionCreateParamsrrrrr\r0r0r1r]'s>/ __name__ __module__ __qualname____annotations__r+rr r]r __classcell__r0r0r.r1r!s @+@+@+cseZdZUded<dddfdd Zeeeeeeeeeeeeeeeeeddded d d d d ddddd ddddd ddd dddddddddZeeeeeeeeeeeeeeeedddedd d d d d ddddd dddd ddd dddddd!d"d#dZeeeeeeeeeeeeeeeedddedd d d$d d ddddd dddd ddd dddddd%d"d&dZed'd(ggd)eeeeeeeeeeeeeeeeddded d d d d ddddd dddd*d ddd dddddd%dd+dZZ S),r"AsyncCompletionsWithRawResponser$r r%r&cst|t||_dSr))r*r+rqr$r,r.r0r1r+{s zAsyncCompletions.__init__Nr2rGrHrIrJrKrLrMrNrOrPrQrRrSrTrUrVrWrrXcsdSr[r0r\r0r0r1r]s*zAsyncCompletions.creater^r_z AsyncStream[ChatCompletionChunk]r`csdSrar0rbr0r0r1r]*s*rcz1ChatCompletion | AsyncStream[ChatCompletionChunk]csdSrar0rbr0r0r1r]s*rYrZrdrecs^|jdt||||||||| | | | | |||||dtjt||||dt| pLdttdIdHSrf)rirrrjrrrrr\r0r0r1r]s>/rkr0r0r.r1r"xs @+@+@+c@seZdZdddddZdS)r#r!r% completionsr(cCst|j|_dSr))rr]r-rsr0r0r1r+sz#CompletionsWithRawResponse.__init__Nrlrmrnr+r0r0r0r1r#sr#c@seZdZdddddZdS)rqr"r%rrcCst|j|_dSr))rr]rtr0r0r1r+sz(AsyncCompletionsWithRawResponse.__init__Nrur0r0r0r1rqsrq)/ __future__rtypingrrrrrrZtyping_extensionsr Zhttpx_typesr r r rr_utilsrrZ _resourcerr _responserrZ _streamingrrZ types.chatrrrrrrZ _base_clientrZ_clientrr __all__r!r"r#rqr0r0r0r1s2     ]]