a
    _g<                     @  sL  d dl mZ d dlmZmZmZmZmZ d dlm	Z	m
Z
 d dlZddlmZ ddlmZ ddlmZmZmZmZmZ dd	lmZmZmZ dd
lmZ ddlmZmZ ddlm Z m!Z! ddl"m#Z#m$Z$ ddl%m&Z& ddl'm(Z( ddl)m*Z* ddgZ+G dd deZ,G dd deZ-G dd dZ.G dd dZ/G dd dZ0G dd dZ1dS )    )annotations)DictListUnionIterableOptional)LiteraloverloadN   )_legacy_response)completion_create_params)	NOT_GIVENBodyQueryHeadersNotGiven)required_argsmaybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)StreamAsyncStream)make_request_options)
Completion) ChatCompletionStreamOptionsParamCompletionsAsyncCompletionsc                   @  s  e Zd ZeddddZeddddZeeeeeeeeeeeeeeeeeddded	d
dddddddddddddddddddddddddZeeeeeeeeeeeeeeeedddedd
ddddddddddddddddddddddd d!dZeeeeeeeeeeeeeeeedddedd
dd"dddddddddddddddddddd#d d$dZe	d%d&gg d'eeeeeeeeeeeeeeeeddded	d
dddddddddddd(dddddddddd#dd)dZdS )*r   CompletionsWithRawResponsereturnc                 C  s   t | S a  
        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/openai/openai-python#accessing-raw-response-data-eg-headers
        )r!   self r'   j/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/openai/resources/completions.pywith_raw_response    s    zCompletions.with_raw_response CompletionsWithStreamingResponsec                 C  s   t | S z
        An alternative to `.with_raw_response` that doesn't eagerly read the response body.

        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
        )r*   r%   r'   r'   r(   with_streaming_response*   s    z#Completions.with_streaming_responseNbest_ofechofrequency_penalty
logit_biaslogprobs
max_tokensnpresence_penaltyseedstopstreamstream_optionssuffixtemperaturetop_puserextra_headersextra_query
extra_bodytimeoutKUnion[str, Literal['gpt-3.5-turbo-instruct', 'davinci-002', 'babbage-002']]CUnion[str, List[str], Iterable[int], Iterable[Iterable[int]], None]Optional[int] | NotGivenOptional[bool] | NotGivenOptional[float] | NotGiven#Optional[Dict[str, int]] | NotGiven0Union[Optional[str], List[str], None] | NotGiven#Optional[Literal[False]] | NotGiven5Optional[ChatCompletionStreamOptionsParam] | NotGivenOptional[str] | NotGivenstr | NotGivenHeaders | NoneQuery | NoneBody | None'float | httpx.Timeout | None | NotGivenr   modelpromptr.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   r#   c                C  s   dS u  
        Creates a completion for the provided prompt and parameters.

        Args:
          model: ID of the model to use. You can use the
              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
              see all of your available models, or see our
              [Model overview](https://platform.openai.com/docs/models) for descriptions of
              them.

          prompt: The prompt(s) to generate completions for, encoded as a string, array of
              strings, array of tokens, or array of token arrays.

              Note that <|endoftext|> is the document separator that the model sees during
              training, so if a prompt is not specified the model will generate as if from the
              beginning of a new document.

          best_of: Generates `best_of` completions server-side and returns the "best" (the one with
              the highest log probability per token). Results cannot be streamed.

              When used with `n`, `best_of` controls the number of candidate completions and
              `n` specifies how many to return – `best_of` must be greater than `n`.

              **Note:** Because this parameter generates many completions, it can quickly
              consume your token quota. Use carefully and ensure that you have reasonable
              settings for `max_tokens` and `stop`.

          echo: Echo back the prompt in addition to the completion

          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/text-generation)

          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 GPT
              tokenizer) to an associated bias value from -100 to 100. You can use this
              [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
              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.

              As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
              from being generated.

          logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as
              well the chosen tokens. For example, if `logprobs` is 5, the API will return a
              list of the 5 most likely tokens. The API will always return the `logprob` of
              the sampled token, so there may be up to `logprobs+1` elements in the response.

              The maximum value for `logprobs` is 5.

          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the
              completion.

              The token count of your prompt plus `max_tokens` cannot exceed 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 completions to generate for each prompt.

              **Note:** Because this parameter generates many completions, it can quickly
              consume your token quota. Use carefully and ensure that you have reasonable
              settings for `max_tokens` and `stop`.

          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/text-generation)

          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.

          stop: Up to 4 sequences where the API will stop generating further tokens. The
              returned text will not contain the stop sequence.

          stream: Whether to stream back partial progress. If set, 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).

          stream_options: Options for streaming response. Only set this when you set `stream: true`.

          suffix: The suffix that comes after a completion of inserted text.

              This parameter is only supported for `gpt-3.5-turbo-instruct`.

          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.

          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
        Nr'   r&   rR   rS   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   r'   r'   r(   create3   s     zCompletions.creater.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r9   r:   r;   r<   r=   r>   r?   r@   rA   Literal[True]zStream[Completion]rR   rS   r8   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r9   r:   r;   r<   r=   r>   r?   r@   rA   r#   c                C  s   dS u  
        Creates a completion for the provided prompt and parameters.

        Args:
          model: ID of the model to use. You can use the
              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
              see all of your available models, or see our
              [Model overview](https://platform.openai.com/docs/models) for descriptions of
              them.

          prompt: The prompt(s) to generate completions for, encoded as a string, array of
              strings, array of tokens, or array of token arrays.

              Note that <|endoftext|> is the document separator that the model sees during
              training, so if a prompt is not specified the model will generate as if from the
              beginning of a new document.

          stream: Whether to stream back partial progress. If set, 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).

          best_of: Generates `best_of` completions server-side and returns the "best" (the one with
              the highest log probability per token). Results cannot be streamed.

              When used with `n`, `best_of` controls the number of candidate completions and
              `n` specifies how many to return – `best_of` must be greater than `n`.

              **Note:** Because this parameter generates many completions, it can quickly
              consume your token quota. Use carefully and ensure that you have reasonable
              settings for `max_tokens` and `stop`.

          echo: Echo back the prompt in addition to the completion

          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/text-generation)

          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 GPT
              tokenizer) to an associated bias value from -100 to 100. You can use this
              [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
              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.

              As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
              from being generated.

          logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as
              well the chosen tokens. For example, if `logprobs` is 5, the API will return a
              list of the 5 most likely tokens. The API will always return the `logprob` of
              the sampled token, so there may be up to `logprobs+1` elements in the response.

              The maximum value for `logprobs` is 5.

          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the
              completion.

              The token count of your prompt plus `max_tokens` cannot exceed 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 completions to generate for each prompt.

              **Note:** Because this parameter generates many completions, it can quickly
              consume your token quota. Use carefully and ensure that you have reasonable
              settings for `max_tokens` and `stop`.

          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/text-generation)

          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.

          stop: Up to 4 sequences where the API will stop generating further tokens. The
              returned text will not contain the stop sequence.

          stream_options: Options for streaming response. Only set this when you set `stream: true`.

          suffix: The suffix that comes after a completion of inserted text.

              This parameter is only supported for `gpt-3.5-turbo-instruct`.

          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.

          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
        Nr'   r&   rR   rS   r8   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r9   r:   r;   r<   r=   r>   r?   r@   rA   r'   r'   r(   rV      s     boolzCompletion | Stream[Completion]c                C  s   dS rZ   r'   r[   r'   r'   r(   rV   e  s     rR   rS   rR   rS   r8   3Optional[Literal[False]] | Literal[True] | NotGivenc                C  sX   | j dt|||||||||	|
||||||||dtjt||||dt|pLdtt dS Nz/completions)rR   rS   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   )r>   r?   r@   rA   F)bodyoptionsZcast_tor8   Z
stream_cls)_postr   r   CompletionCreateParamsr   r   r   rU   r'   r'   r(   rV     s>    
__name__
__module____qualname__r   r)   r,   r	   r   rV   r   r'   r'   r'   r(   r      s   	@ @ @ c                   @  s  e Zd ZeddddZeddddZeeeeeeeeeeeeeeeeeddded	d
dddddddddddddddddddddddddZeeeeeeeeeeeeeeeedddedd
ddddddddddddddddddddddd d!dZeeeeeeeeeeeeeeeedddedd
dd"dddddddddddddddddddd#d d$dZe	d%d&gg d'eeeeeeeeeeeeeeeeddded	d
dddddddddddd(dddddddddd#dd)dZdS )*r    AsyncCompletionsWithRawResponser"   c                 C  s   t | S r$   )rh   r%   r'   r'   r(   r)   >  s    z"AsyncCompletions.with_raw_response%AsyncCompletionsWithStreamingResponsec                 C  s   t | S r+   )ri   r%   r'   r'   r(   r,   H  s    z(AsyncCompletions.with_streaming_responseNr-   rB   rC   rD   rE   rF   rG   rH   rI   rJ   rK   rL   rM   rN   rO   rP   r   rQ   c                  s   dS rT   r'   rU   r'   r'   r(   rV   Q  s     zAsyncCompletions.createrW   rX   zAsyncStream[Completion]rY   c                  s   dS rZ   r'   r[   r'   r'   r(   rV     s     r\   z$Completion | AsyncStream[Completion]c                  s   dS rZ   r'   r[   r'   r'   r(   rV     s     rR   rS   r]   r^   c                  sd   | j dt|||||||||	|
||||||||dtjI d H t||||dt|pRdtt dI d H S r_   )rb   r   r   rc   r   r   r   rU   r'   r'   r(   rV     s>    rd   r'   r'   r'   r(   r    =  s   	@ @ @ c                   @  s   e Zd ZdddddZdS )r!   r   Nonecompletionsr#   c                 C  s   || _ t|j| _d S N)_completionsr   Zto_raw_response_wrapperrV   r&   rl   r'   r'   r(   __init__\  s    z#CompletionsWithRawResponse.__init__Nre   rf   rg   rp   r'   r'   r'   r(   r!   [  s   r!   c                   @  s   e Zd ZdddddZdS )rh   r    rj   rk   c                 C  s   || _ t|j| _d S rm   )rn   r   Zasync_to_raw_response_wrapperrV   ro   r'   r'   r(   rp   e  s    z(AsyncCompletionsWithRawResponse.__init__Nrq   r'   r'   r'   r(   rh   d  s   rh   c                   @  s   e Zd ZdddddZdS )r*   r   rj   rk   c                 C  s   || _ t|j| _d S rm   )rn   r   rV   ro   r'   r'   r(   rp   n  s    z)CompletionsWithStreamingResponse.__init__Nrq   r'   r'   r'   r(   r*   m  s   r*   c                   @  s   e Zd ZdddddZdS )ri   r    rj   rk   c                 C  s   || _ t|j| _d S rm   )rn   r   rV   ro   r'   r'   r(   rp   w  s    z.AsyncCompletionsWithStreamingResponse.__init__Nrq   r'   r'   r'   r(   ri   v  s   ri   )2
__future__r   typingr   r   r   r   r   Ztyping_extensionsr   r	   Zhttpx r   typesr   _typesr   r   r   r   r   _utilsr   r   r   Z_compatr   Z	_resourcer   r   	_responser   r   Z
_streamingr   r   Z_base_clientr   Ztypes.completionr   Z/types.chat.chat_completion_stream_options_paramr   __all__r   r    r!   rh   r*   ri   r'   r'   r'   r(   <module>   s:       "    "			