File: //usr/local/lib/python3.10/dist-packages/openai/resources/__pycache__/embeddings.cpython-310.pyc
o
���g/ � @ sP d dl mZ d dlZd dlZd dlmZmZmZmZ d dl m
Z
d dl Z ddl m
Z
ddlmZ ddlmZmZmZmZmZ dd lmZmZ dd
lmZ dd lm 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 ) � )� annotationsN)�List�Union�Iterable�cast)�Literal� )�_legacy_response)�embedding_create_params)� NOT_GIVEN�Body�Query�Headers�NotGiven)�is_given�maybe_transform)�cached_property)�numpy� has_numpy)�SyncAPIResource�AsyncAPIResource)� to_streamed_response_wrapper�"async_to_streamed_response_wrapper)�make_request_options)�EmbeddingModel)�CreateEmbeddingResponse�
Embeddings�AsyncEmbeddingsc @ �D e Zd Zed dd��Zed dd��Zeeeddded �d!d d �ZdS )"r �return�EmbeddingsWithRawResponsec 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% �F/usr/local/lib/python3.10/dist-packages/openai/resources/embeddings.py�with_raw_response � z Embeddings.with_raw_response� EmbeddingsWithStreamingResponsec 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"Embeddings.with_streaming_responseN��
dimensions�encoding_format�user�
extra_headers� extra_query�
extra_body�timeout�input�=Union[str, List[str], Iterable[int], Iterable[Iterable[int]]]�model�Union[str, EmbeddingModel]r. �int | NotGivenr/ �%Literal['float', 'base64'] | NotGivenr0 �str | NotGivenr1 �Headers | Noner2 � Query | Noner3 � Body | Noner4 �'float | httpx.Timeout | None | NotGivenr c
sV ||||� d�}
t � �sd|
d< d
� fdd� } | jd t|
tj�t|||| | d
�td �S )�c
Creates an embedding vector representing the input text.
Args:
input: Input text to embed, encoded as a string or array of tokens. To embed multiple
inputs in a single request, pass an array of strings or array of token arrays.
The input must not exceed the max input tokens for the model (8192 tokens for
`text-embedding-ada-002`), cannot be an empty string, and any array must be 2048
dimensions or less.
[Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
for counting tokens. Some models may also impose a limit on total number of
tokens summed across inputs.
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.
dimensions: The number of dimensions the resulting output embeddings should have. Only
supported in `text-embedding-3` and later models.
encoding_format: The format to return the embeddings in. Can be either `float` or
[`base64`](https://pypi.org/project/pybase64/).
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
�r5 r7 r0 r. r/ �base64r/ �objr r c �n t � �r| S | jD ]+}tt|j�}t|t�sq t� s't�dt �
|��� � |_q t j
t �
|�dd�� � |_q | S �N�f�float32)�dtype�r �datar �object� embedding�
isinstance�strr �arrayrB � b64decode�tolist�np�
frombuffer�rC rL rJ �r/ r% r& �parserm �
��z!Embeddings.create.<locals>.parser� /embeddings�r1 r2 r3 r4 � post_parser��body�options�cast_toN�rC r r r �r �_postr r
�EmbeddingCreateParamsr r � r$ r5 r7 r. r/ r0 r1 r2 r3 r4 �paramsrV r% rU r& �create/ s* 5�
��zEmbeddings.create)r r )r r) �r5 r6 r7 r8 r. r9 r/ r: r0 r; r1 r< r2 r= r3 r> r4 r? r r ��__name__�
__module__� __qualname__r r' r+ r re r% r% r% r& r �
�c @ r )"r r � AsyncEmbeddingsWithRawResponsec C r! r" )rl r# r% r% r& r' � r( z!AsyncEmbeddings.with_raw_response�$AsyncEmbeddingsWithStreamingResponsec C r! r* )rm r# r% r% r& r+ � r, z'AsyncEmbeddings.with_streaming_responseNr- r5 r6 r7 r8 r. r9 r/ r: r0 r; r1 r< r2 r= r3 r> r4 r? r c
� s^ �||||� d�}
t � �sd|
d< d
� fdd� } | jd t|
tj�t|||| | d
�td �I d H S )r@ rA rB r/ rC r r c rD rE rI rT rU r% r& rV � rW z&AsyncEmbeddings.create.<locals>.parserrX rY r[ Nr_ r` rc r% rU r& re � s, �5�
� �zAsyncEmbeddings.create)r rl )r rm rf rg r% r% r% r& r � rk c @ � e Zd Zddd�ZdS ) r �
embeddingsr r �Nonec C � || _ t�|j�| _d S �N)� _embeddingsr �to_raw_response_wrapperre �r$ ro r% r% r& �__init__ �
�z"EmbeddingsWithRawResponse.__init__N�ro r r rp �rh ri rj rv r% r% r% r& r � r c @ rn ) rl ro r r rp c C rq rr )rs r � async_to_raw_response_wrapperre ru r% r% r& rv rw z'AsyncEmbeddingsWithRawResponse.__init__N�ro r r rp ry r% r% r% r& rl
rz rl c @ rn ) r) ro r r rp c C � || _ t|j�| _d S rr )rs r re ru r% r% r& rv �
�z(EmbeddingsWithStreamingResponse.__init__Nrx ry r% r% r% r& r) rz r) c @ rn ) rm ro r r rp c C r} rr )rs r re ru r% r% r& rv r~ z-AsyncEmbeddingsWithStreamingResponse.__init__Nr| ry r% r% r% r& rm rz rm )2�
__future__r rO rB �typingr r r r �typing_extensionsr �httpx� r �typesr
�_typesr r r
r r �_utilsr r �_compatr �_extrasr rR r � _resourcer r � _responser r � _base_clientr �types.embedding_modelr � types.create_embedding_responser �__all__r r r rl r) rm r% r% r% r& �<module> s0 ss