File: //usr/local/lib/python3.10/dist-packages/openai/resources/__pycache__/completions.cpython-310.pyc
o
���g<� � @ sL d dl mZ d dlmZmZmZmZmZ d dlm Z m
Z
d dl Z ddl m
Z
ddlmZ ddlmZmZmZmZmZ dd lmZmZmZ dd
lmZ dd l m Z m Z dd l m Z m!Z! dd
l"m#Z#m$Z$ ddl%m&Z& ddl'm(Z( ddl)m*Z* ddgZ+G dd� de �Z,G dd� de �Z-G dd� d�Z.G dd� d�Z/G dd� d�Z0G dd � d �Z1dS ) � )� 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 @ � e Zd Zed<dd��Zed=dd��Zeeeeeeeeeeeeeeeeeddded �d>d0d1��Zeeeeeeeeeeeeeeeeddded2�d?d5d1��Zeeeeeeeeeeeeeeeeddded2�d@d8d1��Ze d
d gg d9��eeeeeeeeeeeeeeeeddded �dAd;d1��ZdS )Br �return�CompletionsWithRawResponsec C � 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( �G/usr/local/lib/python3.10/dist-packages/openai/resources/completions.py�with_raw_response � z Completions.with_raw_response� CompletionsWithStreamingResponsec C r$ �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* � 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�timeout�model�KUnion[str, Literal['gpt-3.5-turbo-instruct', 'davinci-002', 'babbage-002']]�prompt�CUnion[str, List[str], Iterable[int], Iterable[Iterable[int]], None]r1 �Optional[int] | NotGivenr2 �Optional[bool] | NotGivenr3 �Optional[float] | NotGivenr4 �#Optional[Dict[str, int]] | NotGivenr5 r6 r7 r8 r9 r: �0Union[Optional[str], List[str], None] | NotGivenr; �#Optional[Literal[False]] | NotGivenr< �5Optional[ChatCompletionStreamOptionsParam] | NotGivenr= �Optional[str] | NotGivenr> r? r@ �str | NotGivenrA �Headers | NonerB � Query | NonerC � Body | NonerD �'float | httpx.Timeout | None | NotGivenr c C � dS �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' rE rG r1 r2 r3 r4 r5 r6 r7 r8 r9 r: r; r< r= r> r? r@ rA rB rC rD r( r( r) �create3 � zCompletions.create�r1 r2 r3 r4 r5 r6 r7 r8 r9 r: r< r= r> r? r@ rA rB rC rD �
Literal[True]�Stream[Completion]c C rV �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' rE rG r; r1 r2 r3 r4 r5 r6 r7 r8 r9 r: r< r= r> r? r@ rA rB rC rD r( r( r) rY � rZ �bool� Completion | Stream[Completion]c C rV r^ r( r_ r( r( r) rY e rZ �rE rG r; �3Optional[Literal[False]] | Literal[True] | NotGivenc C s� | j dti d|�d|�d|�d|�d|�d|�d|�d |�d
| �d |
�d | �d
| �d|
�d|�d|�d|�d|�d|i�tj�t||||d�t|
pJdtt d�S �Nz /completionsrE rG r1 r2 r3 r4 r5 r6 r7 r8 r9 r: r; r< r= r> r? r@ )rA rB rC rD F)�body�options�cast_tor; �
stream_cls)�_postr r �CompletionCreateParamsr r r rX r( r( r) rY � sb �������� �
� � �
���������)r" r# )r" r, �.rE rF rG rH r1 rI r2 rJ r3 rK r4 rL r5 rI r6 rI r7 rI r8 rK r9 rI r: rM r; rN r< rO r= rP r> rK r? rK r@ rQ rA rR rB rS rC rT rD rU r" r ).rE rF rG rH r; r\ r1 rI r2 rJ r3 rK r4 rL r5 rI r6 rI r7 rI r8 rK r9 rI r: rM r< rO r= rP r> rK r? rK r@ rQ rA rR rB rS rC rT rD rU r" r] ).rE rF rG rH r; r` r1 rI r2 rJ r3 rK r4 rL r5 rI r6 rI r7 rI r8 rK r9 rI r: rM r< rO r= rP r> rK r? rK r@ rQ rA rR rB rS rC rT rD rU r" ra ).rE rF rG rH r1 rI r2 rJ r3 rK r4 rL r5 rI r6 rI r7 rI r8 rK r9 rI r: rM r; rc r< rO r= rP r> rK r? rK r@ rQ rA rR rB rS rC rT rD rU r" ra �
�__name__�
__module__� __qualname__r r* r. r r
rY r r( r( r( r) r � � � � �c @ r! )Br r" � AsyncCompletionsWithRawResponsec C r$ r% )rq r& r( r( r) r* > r+ z"AsyncCompletions.with_raw_response�%AsyncCompletionsWithStreamingResponsec C r$ r- )rr r& r( r( r) r. H r/ z(AsyncCompletions.with_streaming_responseNr0 rE rF rG rH r1 rI r2 rJ r3 rK r4 rL r5 r6 r7 r8 r9 r: rM r; rN r< rO r= rP r> r? r@ rQ rA rR rB rS rC rT rD rU r c � � �dS rW r( rX r( r( r) rY Q � � zAsyncCompletions.creater[ r\ �AsyncStream[Completion]c � rs r^ r( r_ r( r( r) rY � rt r` �$Completion | AsyncStream[Completion]c � rs r^ r( r_ r( r( r) rY � rt rb rc c � s� �| j dti d|�d|�d|�d|�d|�d|�d|�d |�d
| �d |
�d | �d
| �d|
�d|�d|�d|�d|�d|i�tj�I d H t||||d�t|
pNdtt d�I d H S rd )ri r r rj r r r rX r( r( r) rY sd � �������� �
� � �
�������� �)r" rq )r" rr rk ).rE rF rG rH r; r\ r1 rI r2 rJ r3 rK r4 rL r5 rI r6 rI r7 rI r8 rK r9 rI r: rM r< rO r= rP r> rK r? rK r@ rQ rA rR rB rS rC rT rD rU r" ru ).rE rF rG rH r; r` r1 rI r2 rJ r3 rK r4 rL r5 rI r6 rI r7 rI r8 rK r9 rI r: rM r< rO r= rP r> rK r? rK r@ rQ rA rR rB rS rC rT rD rU r" rv ).rE rF rG rH r1 rI r2 rJ r3 rK r4 rL r5 rI r6 rI r7 rI r8 rK r9 rI r: rM r; rc r< rO r= rP r> rK r? rK r@ rQ rA rR rB rS rC rT rD rU r" rv rl r( r( r( r) r = rp c @ � e Zd Zddd�ZdS ) r# � completionsr r" �Nonec C � || _ t�|j�| _d S �N)� _completionsr �to_raw_response_wrapperrY �r' rx r( r( r) �__init__\ �
�z#CompletionsWithRawResponse.__init__N�rx r r" ry �rm rn ro r r( r( r( r) r# [ � r# c @ rw ) rq rx r r" ry c C rz r{ )r| r � async_to_raw_response_wrapperrY r~ r( r( r) r e r� z(AsyncCompletionsWithRawResponse.__init__N�rx r r" ry r� r( r( r( r) rq d r� rq c @ rw ) r, rx r r" ry c C � || _ t|j�| _d S r{ )r| r rY r~ r( r( r) r n �
�z)CompletionsWithStreamingResponse.__init__Nr� r� r( r( r( r) r, m r� r, c @ rw ) rr rx r r" ry c C r� r{ )r| r rY r~ r( r( r) r w r� z.AsyncCompletionsWithStreamingResponse.__init__Nr� r� r( r( r( r) rr v r� rr )2�
__future__r �typingr r r r r �typing_extensionsr r �httpx� r �typesr �_typesr
r r r r �_utilsr r r �_compatr � _resourcer r � _responser r �
_streamingr r � _base_clientr �types.completionr �/types.chat.chat_completion_stream_options_paramr �__all__r r r# rq r, rr r( r( r( r) �<module> s< " "