openai.resources

The resources module aggregates classes and functions for interacting with the OpenAI API into several submodules, each representing a specific resource or feature of the API.

The submodules' classes mirror the structure of the API's endpoints and offer synchronous and asynchronous communication with the API.

Each resource is accessible as an attribute on the OpenAI and AsyncOpenAI clients. To work with a resource, initialize an instance of a client and then access the resource as an attribute on the client instance. For example, to work with the chat resource, create an instance of the OpenAI client and access the attributes and methods on your_client_instance.chat.

Modules:

Name	Description
`audio`	The `audio` module provides classes for audio processing operations like transcription, translation, and speech synthesis. Use the `audio` module by accessing the `OpenAI.audio` attribute on the client object, and then access the attribute for the feature you'd like to use: `OpenAI.audio.transcriptions` - Transcribe spoken audio to text `OpenAI.audio.translations` - Translate spoken audio to English `OpenAI.audio.speech` - Generate spoken audio from text Examples: `from pathlib import Path from openai import OpenAI openai = OpenAI() speech_file_path = Path(__file__).parent / "speech.mp3" # Create text-to-speech audio file with openai.audio.speech.with_streaming_response.create( model="tts-1", voice="alloy", input="The quick brown fox jumps over the lazy dog.", ) as response: response.stream_to_file(speech_file_path)`
`beta`	The `beta` modules provides a unified interface for accessing beta features of the API, encapsulating synchronous and asynchronous access to resources in beta. The module aggregates the beta functionalities related to features like yet considered generally available (GA), offering a simplified entry point for interacting with these resources. It is designed to facilitate easy access to the cutting-edge features still under development, enabling developers to experiment with and leverage new capabilities before they become GA.
`chat`	The `chat` module provides classes for creating and managing chat sessions that leverage OpenAI's language models to generate conversational responses. The module supports both synchronous and asynchronous operations, offering interfaces for direct interaction with the completion endpoints tailored for chat applications. Designed for developers looking to integrate AI-powered chat functionalities into their applications and features like raw and streaming response handling for more flexible integration.
`completions`	The `completions` module provides access to the legacy chat endpoint, `/v1/completions`. Use the `chat.completions` module instead for new applications. You should not use this module for new projects. The legacy `/v1/completions` endpoint this module interacts with no longer receives updates and is expected to be deprecated. Use this module only in applications that require compatibility with the legacy endpoint. You're strongly encouraged to migrate existing applications to the `chat.completions` module⁠—which interacts with the current (non-legacy) `/v1/chat/completions` endpoint—prior to the deprecation of the `/v1/completions` endpoint.
`embeddings`	The `embeddings` module provides classes for creating embeddings from text inputs using OpenAI's models and supports both synchronous and asynchronous operations as well as the handling of raw responses and streaming response capabilities. The module is appropriate for use in applications that require semantic analysis of text, like similarity searches, text clustering, and other natural language processing tasks that can benefit from high-dimensional vector representations of text.
`files`	The `files` module provides classes for uploading, retrieving, listing, and deleting files used across various OpenAI API endpoints. The module supports both synchronous and asynchronous operations, along with handling of raw responses and streaming of file content. Designed for use cases that involve managing large datasets or files for purposes like fine-tuning models or using assistants, this module facilitates the efficient handling of file-related operations on the OpenAI platform.
`fine_tuning`	The `fine_tuning` module provides classes for handling fine-tuning operations, including the initiation, management, and retrieval of fine-tuning jobs. The module supports synchronous and asynchronous operations, offering interfaces for working with jobs directly, as well as with raw or streaming responses. Designed for use in applications requiring custom model training on specific datasets to improve model performance for tailored tasks.
`images`	The `image` module provides functionality for creating variations of images, editing images based on textual prompts, and generating new images from prompts using specified models. The module supports both synchronous and asynchronous operations, with capabilities for handling raw responses and streaming. Suitable for applications requiring dynamic image generation or modification through the OpenAI API, this module leverages models like DALL-E to interpret text prompts into visual content.
`models`	The `models` module facilitates the retrieval, listing, and deletion of models on the OpenAI platform and supports both synchronous and asynchronous operations. The module enables developers to interact with models, providing functionalities like fetching detailed information about a specific model, listing all available models, and deleting fine-tuned models.
`moderations`	The `moderations` module provides functionality to submit text for moderation to determine whether it violates OpenAI's content policy. Moderation is particularly useful for developers looking to ensure the content generated or processed by their applications adheres to OpenAI's content policy. By leveraging the content moderation models provided by OpenAI, applications can automatically classify and filter out text that might be considered harmful or inappropriate.

Classes:

Name	Description
`AsyncAudio`
`AsyncAudioWithRawResponse`
`AsyncAudioWithStreamingResponse`
`AsyncBeta`
`AsyncBetaWithRawResponse`
`AsyncBetaWithStreamingResponse`
`AsyncChat`
`AsyncChatWithRawResponse`
`AsyncChatWithStreamingResponse`
`AsyncCompletions`
`AsyncCompletionsWithRawResponse`
`AsyncCompletionsWithStreamingResponse`
`AsyncEmbeddings`
`AsyncEmbeddingsWithRawResponse`
`AsyncEmbeddingsWithStreamingResponse`
`AsyncFiles`
`AsyncFilesWithRawResponse`
`AsyncFilesWithStreamingResponse`
`AsyncFineTuning`
`AsyncFineTuningWithRawResponse`
`AsyncFineTuningWithStreamingResponse`
`AsyncImages`
`AsyncImagesWithRawResponse`
`AsyncImagesWithStreamingResponse`
`AsyncModels`
`AsyncModelsWithRawResponse`
`AsyncModelsWithStreamingResponse`
`AsyncModerations`
`AsyncModerationsWithRawResponse`
`AsyncModerationsWithStreamingResponse`
`Audio`
`AudioWithRawResponse`
`AudioWithStreamingResponse`
`Beta`
`BetaWithRawResponse`
`BetaWithStreamingResponse`
`Chat`
`ChatWithRawResponse`
`ChatWithStreamingResponse`
`Completions`
`CompletionsWithRawResponse`
`CompletionsWithStreamingResponse`
`Embeddings`
`EmbeddingsWithRawResponse`
`EmbeddingsWithStreamingResponse`
`Files`
`FilesWithRawResponse`
`FilesWithStreamingResponse`
`FineTuning`
`FineTuningWithRawResponse`
`FineTuningWithStreamingResponse`
`Images`
`ImagesWithRawResponse`
`ImagesWithStreamingResponse`
`Models`
`ModelsWithRawResponse`
`ModelsWithStreamingResponse`
`Moderations`
`ModerationsWithRawResponse`
`ModerationsWithStreamingResponse`

AsyncAudio

AsyncAudio(client: AsyncOpenAI)

Methods:

Name	Description
`speech`
`transcriptions`
`translations`
`with_raw_response`
`with_streaming_response`

speech

speech() -> AsyncSpeech

transcriptions

transcriptions() -> AsyncTranscriptions

translations

translations() -> AsyncTranslations

with_raw_response

with_raw_response() -> AsyncAudioWithRawResponse

with_streaming_response

with_streaming_response() -> (
    AsyncAudioWithStreamingResponse
)

AsyncAudioWithRawResponse

AsyncAudioWithRawResponse(audio: AsyncAudio)

Methods:

Name	Description
`speech`
`transcriptions`
`translations`

speech

speech() -> AsyncSpeechWithRawResponse

transcriptions

transcriptions() -> AsyncTranscriptionsWithRawResponse

translations

translations() -> AsyncTranslationsWithRawResponse

AsyncAudioWithStreamingResponse

AsyncAudioWithStreamingResponse(audio: AsyncAudio)

Methods:

Name	Description
`speech`
`transcriptions`
`translations`

speech

speech() -> AsyncSpeechWithStreamingResponse

transcriptions

transcriptions() -> (
    AsyncTranscriptionsWithStreamingResponse
)

translations

translations() -> AsyncTranslationsWithStreamingResponse

AsyncBeta

AsyncBeta(client: AsyncOpenAI)

Methods:

Name	Description
`assistants`
`threads`
`with_raw_response`
`with_streaming_response`

assistants

assistants() -> AsyncAssistants

threads

threads() -> AsyncThreads

with_raw_response

with_raw_response() -> AsyncBetaWithRawResponse

with_streaming_response

with_streaming_response() -> AsyncBetaWithStreamingResponse

AsyncBetaWithRawResponse

AsyncBetaWithRawResponse(beta: AsyncBeta)

Methods:

Name	Description
`assistants`
`threads`

assistants

assistants() -> AsyncAssistantsWithRawResponse

threads

threads() -> AsyncThreadsWithRawResponse

AsyncBetaWithStreamingResponse

AsyncBetaWithStreamingResponse(beta: AsyncBeta)

Methods:

Name	Description
`assistants`
`threads`

assistants

assistants() -> AsyncAssistantsWithStreamingResponse

threads

threads() -> AsyncThreadsWithStreamingResponse

AsyncChat

AsyncChat(client: AsyncOpenAI)

Methods:

Name	Description
`completions`
`with_raw_response`
`with_streaming_response`

completions

completions() -> AsyncCompletions

with_raw_response

with_raw_response() -> AsyncChatWithRawResponse

with_streaming_response

with_streaming_response() -> AsyncChatWithStreamingResponse

AsyncChatWithRawResponse

AsyncChatWithRawResponse(chat: AsyncChat)

Methods:

Name	Description
`completions`

completions

completions() -> AsyncCompletionsWithRawResponse

AsyncChatWithStreamingResponse

AsyncChatWithStreamingResponse(chat: AsyncChat)

Methods:

Name	Description
`completions`

completions

completions() -> AsyncCompletionsWithStreamingResponse

AsyncCompletions

AsyncCompletions(client: AsyncOpenAI)

Methods:

Name	Description
`create`	Creates a completion for the provided prompt and parameters.
`with_raw_response`
`with_streaming_response`

create `async`

create(
    *,
    model: Union[
        str,
        Literal[
            "gpt-3.5-turbo-instruct",
            "davinci-002",
            "babbage-002",
        ],
    ],
    prompt: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
        None,
    ],
    best_of: Optional[int] | NotGiven = NOT_GIVEN,
    echo: Optional[bool] | NotGiven = NOT_GIVEN,
    frequency_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    logit_bias: (
        Optional[Dict[str, int]] | NotGiven
    ) = NOT_GIVEN,
    logprobs: Optional[int] | NotGiven = NOT_GIVEN,
    max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    presence_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    seed: Optional[int] | NotGiven = NOT_GIVEN,
    stop: (
        Union[Optional[str], List[str], None] | NotGiven
    ) = NOT_GIVEN,
    stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
    suffix: Optional[str] | NotGiven = NOT_GIVEN,
    temperature: Optional[float] | NotGiven = NOT_GIVEN,
    top_p: Optional[float] | NotGiven = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Completion

create(
    *,
    model: Union[
        str,
        Literal[
            "gpt-3.5-turbo-instruct",
            "davinci-002",
            "babbage-002",
        ],
    ],
    prompt: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
        None,
    ],
    stream: Literal[True],
    best_of: Optional[int] | NotGiven = NOT_GIVEN,
    echo: Optional[bool] | NotGiven = NOT_GIVEN,
    frequency_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    logit_bias: (
        Optional[Dict[str, int]] | NotGiven
    ) = NOT_GIVEN,
    logprobs: Optional[int] | NotGiven = NOT_GIVEN,
    max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    presence_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    seed: Optional[int] | NotGiven = NOT_GIVEN,
    stop: (
        Union[Optional[str], List[str], None] | NotGiven
    ) = NOT_GIVEN,
    suffix: Optional[str] | NotGiven = NOT_GIVEN,
    temperature: Optional[float] | NotGiven = NOT_GIVEN,
    top_p: Optional[float] | NotGiven = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> AsyncStream[Completion]

create(
    *,
    model: Union[
        str,
        Literal[
            "gpt-3.5-turbo-instruct",
            "davinci-002",
            "babbage-002",
        ],
    ],
    prompt: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
        None,
    ],
    stream: bool,
    best_of: Optional[int] | NotGiven = NOT_GIVEN,
    echo: Optional[bool] | NotGiven = NOT_GIVEN,
    frequency_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    logit_bias: (
        Optional[Dict[str, int]] | NotGiven
    ) = NOT_GIVEN,
    logprobs: Optional[int] | NotGiven = NOT_GIVEN,
    max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    presence_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    seed: Optional[int] | NotGiven = NOT_GIVEN,
    stop: (
        Union[Optional[str], List[str], None] | NotGiven
    ) = NOT_GIVEN,
    suffix: Optional[str] | NotGiven = NOT_GIVEN,
    temperature: Optional[float] | NotGiven = NOT_GIVEN,
    top_p: Optional[float] | NotGiven = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Completion | AsyncStream[Completion]

create(
    *,
    model: Union[
        str,
        Literal[
            "gpt-3.5-turbo-instruct",
            "davinci-002",
            "babbage-002",
        ],
    ],
    prompt: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
        None,
    ],
    best_of: Optional[int] | NotGiven = NOT_GIVEN,
    echo: Optional[bool] | NotGiven = NOT_GIVEN,
    frequency_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    logit_bias: (
        Optional[Dict[str, int]] | NotGiven
    ) = NOT_GIVEN,
    logprobs: Optional[int] | NotGiven = NOT_GIVEN,
    max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    presence_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    seed: Optional[int] | NotGiven = NOT_GIVEN,
    stop: (
        Union[Optional[str], List[str], None] | NotGiven
    ) = NOT_GIVEN,
    stream: (
        Optional[Literal[False]] | Literal[True] | NotGiven
    ) = NOT_GIVEN,
    suffix: Optional[str] | NotGiven = NOT_GIVEN,
    temperature: Optional[float] | NotGiven = NOT_GIVEN,
    top_p: Optional[float] | NotGiven = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Completion | AsyncStream[Completion]

Creates a completion for the provided prompt and parameters.

Parameters:

Name	Type	Description	Default
`model`	`Union[str, Literal['gpt-3.5-turbo-instruct', 'davinci-002', 'babbage-002']]`	ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.	required
`prompt`	`Union[str, List[str], Iterable[int], Iterable[Iterable[int]], None]`	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.	required
`best_of`	`Optional[int] \| NotGiven`	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`.	`NOT_GIVEN`
`echo`	`Optional[bool] \| NotGiven`	Echo back the prompt in addition to the completion	`NOT_GIVEN`
`frequency_penalty`	`Optional[float] \| NotGiven`	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.	`NOT_GIVEN`
`logit_bias`	`Optional[Dict[str, int]] \| NotGiven`	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 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.	`NOT_GIVEN`
`logprobs`	`Optional[int] \| NotGiven`	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.	`NOT_GIVEN`
`max_tokens`	`Optional[int] \| NotGiven`	The maximum number of tokens 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 for counting tokens.	`NOT_GIVEN`
`n`	`Optional[int] \| NotGiven`	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`.	`NOT_GIVEN`
`presence_penalty`	`Optional[float] \| NotGiven`	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.	`NOT_GIVEN`
`seed`	`Optional[int] \| NotGiven`	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.	`NOT_GIVEN`
`stop`	`Union[Optional[str], List[str], None] \| NotGiven`	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.	`NOT_GIVEN`
`stream`	`Optional[Literal[False]] \| Literal[True] \| NotGiven`	Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a `data: [DONE]` message. Example Python code.	`NOT_GIVEN`
`suffix`	`Optional[str] \| NotGiven`	The suffix that comes after a completion of inserted text.	`NOT_GIVEN`
`temperature`	`Optional[float] \| NotGiven`	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.	`NOT_GIVEN`
`top_p`	`Optional[float] \| NotGiven`	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.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> AsyncCompletionsWithRawResponse

with_streaming_response

with_streaming_response() -> (
    AsyncCompletionsWithStreamingResponse
)

AsyncCompletionsWithRawResponse

AsyncCompletionsWithRawResponse(
    completions: AsyncCompletions,
)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = async_to_raw_response_wrapper(create)

AsyncCompletionsWithStreamingResponse

AsyncCompletionsWithStreamingResponse(
    completions: AsyncCompletions,
)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = async_to_streamed_response_wrapper(create)

AsyncEmbeddings

AsyncEmbeddings(client: AsyncOpenAI)

Methods:

Name	Description
`create`	Creates an embedding vector representing the input text.
`with_raw_response`
`with_streaming_response`

create `async`

create(
    *,
    input: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
    ],
    model: Union[
        str,
        Literal[
            "text-embedding-ada-002",
            "text-embedding-3-small",
            "text-embedding-3-large",
        ],
    ],
    dimensions: int | NotGiven = NOT_GIVEN,
    encoding_format: (
        Literal["float", "base64"] | NotGiven
    ) = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> CreateEmbeddingResponse

Creates an embedding vector representing the input text.

Parameters:

Name	Type	Description	Default
`input`	`Union[str, List[str], Iterable[int], Iterable[Iterable[int]]]`	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 for counting tokens.	required
`model`	`Union[str, Literal['text-embedding-ada-002', 'text-embedding-3-small', 'text-embedding-3-large']]`	ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.	required
`dimensions`	`int \| NotGiven`	The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models.	`NOT_GIVEN`
`encoding_format`	`Literal['float', 'base64'] \| NotGiven`	The format to return the embeddings in. Can be either `float` or `base64`.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> AsyncEmbeddingsWithRawResponse

with_streaming_response

with_streaming_response() -> (
    AsyncEmbeddingsWithStreamingResponse
)

AsyncEmbeddingsWithRawResponse

AsyncEmbeddingsWithRawResponse(embeddings: AsyncEmbeddings)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = async_to_raw_response_wrapper(create)

AsyncEmbeddingsWithStreamingResponse

AsyncEmbeddingsWithStreamingResponse(
    embeddings: AsyncEmbeddings,
)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = async_to_streamed_response_wrapper(create)

AsyncFiles

AsyncFiles(client: AsyncOpenAI)

Methods:

Name	Description
`content`	Returns the contents of the specified file.
`create`	Upload a file that can be used across various endpoints.
`delete`	Delete a file.
`list`	Returns a list of files that belong to the user's organization.
`retrieve`	Returns information about a specific file.
`retrieve_content`	Returns the contents of the specified file.
`wait_for_processing`	Waits for the given file to be processed, default timeout is 30 mins.
`with_raw_response`
`with_streaming_response`

content `async`

content(
    file_id: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> HttpxBinaryResponseContent

Returns the contents of the specified file.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

create `async`

create(
    *,
    file: FileTypes,
    purpose: Literal["fine-tune", "assistants"],
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> FileObject

Upload a file that can be used across various endpoints.

The size of all the files uploaded by one organization can be up to 100 GB.

The size of individual files can be a maximum of 512 MB or 2 million tokens for Assistants. See the Assistants Tools guide to learn more about the types of files supported. The Fine-tuning API only supports .jsonl files.

Please contact us if you need to increase these storage limits.

Parameters:

Name	Type	Description	Default
`file`	`FileTypes`	The File object (not file name) to be uploaded.	required
`purpose`	`Literal['fine-tune', 'assistants']`	The intended purpose of the uploaded file. Use "fine-tune" for Fine-tuning and "assistants" for Assistants and Messages. This allows us to validate the format of the uploaded file is correct for fine-tuning.	required
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

delete `async`

delete(
    file_id: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> FileDeleted

Delete a file.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

list

list(
    *,
    purpose: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> AsyncPaginator[FileObject, AsyncPage[FileObject]]

Returns a list of files that belong to the user's organization.

Parameters:

Name	Type	Description	Default
`purpose`	`str \| NotGiven`	Only return files with the given purpose.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

retrieve `async`

retrieve(
    file_id: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> FileObject

Returns information about a specific file.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

retrieve_content `async`

retrieve_content(
    file_id: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> str

Returns the contents of the specified file.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

wait_for_processing `async`

wait_for_processing(
    id: str,
    *,
    poll_interval: float = 5.0,
    max_wait_seconds: float = 30 * 60
) -> FileObject

Waits for the given file to be processed, default timeout is 30 mins.

with_raw_response

with_raw_response() -> AsyncFilesWithRawResponse

with_streaming_response

with_streaming_response() -> (
    AsyncFilesWithStreamingResponse
)

AsyncFilesWithRawResponse

AsyncFilesWithRawResponse(files: AsyncFiles)

Attributes:

Name	Type	Description
`content`
`create`
`delete`
`list`
`retrieve`
`retrieve_content`

content `instance-attribute`

content = async_to_raw_response_wrapper(content)

create `instance-attribute`

create = async_to_raw_response_wrapper(create)

delete `instance-attribute`

delete = async_to_raw_response_wrapper(delete)

list `instance-attribute`

list = async_to_raw_response_wrapper(list)

retrieve `instance-attribute`

retrieve = async_to_raw_response_wrapper(retrieve)

retrieve_content `instance-attribute`

retrieve_content = async_to_raw_response_wrapper(
    retrieve_content
)

AsyncFilesWithStreamingResponse

AsyncFilesWithStreamingResponse(files: AsyncFiles)

Attributes:

Name	Type	Description
`content`
`create`
`delete`
`list`
`retrieve`
`retrieve_content`

content `instance-attribute`

content = async_to_custom_streamed_response_wrapper(
    content, AsyncStreamedBinaryAPIResponse
)

create `instance-attribute`

create = async_to_streamed_response_wrapper(create)

delete `instance-attribute`

delete = async_to_streamed_response_wrapper(delete)

list `instance-attribute`

list = async_to_streamed_response_wrapper(list)

retrieve `instance-attribute`

retrieve = async_to_streamed_response_wrapper(retrieve)

retrieve_content `instance-attribute`

retrieve_content = async_to_streamed_response_wrapper(
    retrieve_content
)

AsyncFineTuning

AsyncFineTuning(client: AsyncOpenAI)

Methods:

Name	Description
`jobs`
`with_raw_response`
`with_streaming_response`

jobs

jobs() -> AsyncJobs

with_raw_response

with_raw_response() -> AsyncFineTuningWithRawResponse

with_streaming_response

with_streaming_response() -> (
    AsyncFineTuningWithStreamingResponse
)

AsyncFineTuningWithRawResponse

AsyncFineTuningWithRawResponse(
    fine_tuning: AsyncFineTuning,
)

Methods:

Name	Description
`jobs`

jobs

jobs() -> AsyncJobsWithRawResponse

AsyncFineTuningWithStreamingResponse

AsyncFineTuningWithStreamingResponse(
    fine_tuning: AsyncFineTuning,
)

Methods:

Name	Description
`jobs`

jobs

jobs() -> AsyncJobsWithStreamingResponse

AsyncImages

AsyncImages(client: AsyncOpenAI)

Methods:

Name	Description
`create_variation`	Creates a variation of a given image.
`edit`	Creates an edited or extended image given an original image and a prompt.
`generate`	Creates an image given a prompt.
`with_raw_response`
`with_streaming_response`

create_variation `async`

create_variation(
    *,
    image: FileTypes,
    model: (
        Union[str, Literal["dall-e-2"], None] | NotGiven
    ) = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    response_format: (
        Optional[Literal["url", "b64_json"]] | NotGiven
    ) = NOT_GIVEN,
    size: (
        Optional[Literal["256x256", "512x512", "1024x1024"]]
        | NotGiven
    ) = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ImagesResponse

Creates a variation of a given image.

Parameters:

Name	Type	Description	Default
`image`	`FileTypes`	The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.	required
`model`	`Union[str, Literal['dall-e-2'], None] \| NotGiven`	The model to use for image generation. Only `dall-e-2` is supported at this time.	`NOT_GIVEN`
`n`	`Optional[int] \| NotGiven`	The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported.	`NOT_GIVEN`
`response_format`	`Optional[Literal['url', 'b64_json']] \| NotGiven`	The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated.	`NOT_GIVEN`
`size`	`Optional[Literal['256x256', '512x512', '1024x1024']] \| NotGiven`	The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

edit `async`

edit(
    *,
    image: FileTypes,
    prompt: str,
    mask: FileTypes | NotGiven = NOT_GIVEN,
    model: (
        Union[str, Literal["dall-e-2"], None] | NotGiven
    ) = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    response_format: (
        Optional[Literal["url", "b64_json"]] | NotGiven
    ) = NOT_GIVEN,
    size: (
        Optional[Literal["256x256", "512x512", "1024x1024"]]
        | NotGiven
    ) = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ImagesResponse

Creates an edited or extended image given an original image and a prompt.

Parameters:

Name	Type	Description	Default
`image`	`FileTypes`	The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask.	required
`prompt`	`str`	A text description of the desired image(s). The maximum length is 1000 characters.	required
`mask`	`FileTypes \| NotGiven`	An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.	`NOT_GIVEN`
`model`	`Union[str, Literal['dall-e-2'], None] \| NotGiven`	The model to use for image generation. Only `dall-e-2` is supported at this time.	`NOT_GIVEN`
`n`	`Optional[int] \| NotGiven`	The number of images to generate. Must be between 1 and 10.	`NOT_GIVEN`
`response_format`	`Optional[Literal['url', 'b64_json']] \| NotGiven`	The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated.	`NOT_GIVEN`
`size`	`Optional[Literal['256x256', '512x512', '1024x1024']] \| NotGiven`	The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

generate `async`

generate(
    *,
    prompt: str,
    model: (
        Union[str, Literal["dall-e-2", "dall-e-3"], None]
        | NotGiven
    ) = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    quality: (
        Literal["standard", "hd"] | NotGiven
    ) = NOT_GIVEN,
    response_format: (
        Optional[Literal["url", "b64_json"]] | NotGiven
    ) = NOT_GIVEN,
    size: (
        Optional[
            Literal[
                "256x256",
                "512x512",
                "1024x1024",
                "1792x1024",
                "1024x1792",
            ]
        ]
        | NotGiven
    ) = NOT_GIVEN,
    style: (
        Optional[Literal["vivid", "natural"]] | NotGiven
    ) = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ImagesResponse

Creates an image given a prompt.

Parameters:

Name	Type	Description	Default
`prompt`	`str`	A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`.	required
`model`	`Union[str, Literal['dall-e-2', 'dall-e-3'], None] \| NotGiven`	The model to use for image generation.	`NOT_GIVEN`
`n`	`Optional[int] \| NotGiven`	The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported.	`NOT_GIVEN`
`quality`	`Literal['standard', 'hd'] \| NotGiven`	The quality of the image that will be generated. `hd` creates images with finer details and greater consistency across the image. This param is only supported for `dall-e-3`.	`NOT_GIVEN`
`response_format`	`Optional[Literal['url', 'b64_json']] \| NotGiven`	The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated.	`NOT_GIVEN`
`size`	`Optional[Literal['256x256', '512x512', '1024x1024', '1792x1024', '1024x1792']] \| NotGiven`	The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`. Must be one of `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3` models.	`NOT_GIVEN`
`style`	`Optional[Literal['vivid', 'natural']] \| NotGiven`	The style of the generated images. Must be one of `vivid` or `natural`. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for `dall-e-3`.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> AsyncImagesWithRawResponse

with_streaming_response

with_streaming_response() -> (
    AsyncImagesWithStreamingResponse
)

AsyncImagesWithRawResponse

AsyncImagesWithRawResponse(images: AsyncImages)

Attributes:

Name	Type	Description
`create_variation`
`edit`
`generate`

create_variation `instance-attribute`

create_variation = async_to_raw_response_wrapper(
    create_variation
)

edit `instance-attribute`

edit = async_to_raw_response_wrapper(edit)

generate `instance-attribute`

generate = async_to_raw_response_wrapper(generate)

AsyncImagesWithStreamingResponse

AsyncImagesWithStreamingResponse(images: AsyncImages)

Attributes:

Name	Type	Description
`create_variation`
`edit`
`generate`

create_variation `instance-attribute`

create_variation = async_to_streamed_response_wrapper(
    create_variation
)

edit `instance-attribute`

edit = async_to_streamed_response_wrapper(edit)

generate `instance-attribute`

generate = async_to_streamed_response_wrapper(generate)

AsyncModels

AsyncModels(client: AsyncOpenAI)

Methods:

Name	Description
`delete`	Delete a fine-tuned model.
`list`	Lists the currently available models, and provides basic information about each
`retrieve`	Retrieves a model instance, providing basic information about the model such as
`with_raw_response`
`with_streaming_response`

delete `async`

delete(
    model: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ModelDeleted

Delete a fine-tuned model.

You must have the Owner role in your organization to delete a model.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

list

list(
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> AsyncPaginator[Model, AsyncPage[Model]]

Lists the currently available models, and provides basic information about each one such as the owner and availability.

retrieve `async`

retrieve(
    model: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Model

Retrieves a model instance, providing basic information about the model such as the owner and permissioning.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> AsyncModelsWithRawResponse

with_streaming_response

with_streaming_response() -> (
    AsyncModelsWithStreamingResponse
)

AsyncModelsWithRawResponse

AsyncModelsWithRawResponse(models: AsyncModels)

Attributes:

Name	Type	Description
`delete`
`list`
`retrieve`

delete `instance-attribute`

delete = async_to_raw_response_wrapper(delete)

list `instance-attribute`

list = async_to_raw_response_wrapper(list)

retrieve `instance-attribute`

retrieve = async_to_raw_response_wrapper(retrieve)

AsyncModelsWithStreamingResponse

AsyncModelsWithStreamingResponse(models: AsyncModels)

Attributes:

Name	Type	Description
`delete`
`list`
`retrieve`

delete `instance-attribute`

delete = async_to_streamed_response_wrapper(delete)

list `instance-attribute`

list = async_to_streamed_response_wrapper(list)

retrieve `instance-attribute`

retrieve = async_to_streamed_response_wrapper(retrieve)

AsyncModerations

AsyncModerations(client: AsyncOpenAI)

Methods:

Name	Description
`create`	Classifies if text is potentially harmful.
`with_raw_response`
`with_streaming_response`

create `async`

create(
    *,
    input: Union[str, List[str]],
    model: (
        Union[
            str,
            Literal[
                "text-moderation-latest",
                "text-moderation-stable",
            ],
        ]
        | NotGiven
    ) = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ModerationCreateResponse

Classifies if text is potentially harmful.

Parameters:

Name	Type	Description	Default
`input`	`Union[str, List[str]]`	The input text to classify	required
`model`	`Union[str, Literal['text-moderation-latest', 'text-moderation-stable']] \| NotGiven`	Two content moderations models are available: `text-moderation-stable` and `text-moderation-latest`. The default is `text-moderation-latest` which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use `text-moderation-stable`, we will provide advanced notice before updating the model. Accuracy of `text-moderation-stable` may be slightly lower than for `text-moderation-latest`.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> AsyncModerationsWithRawResponse

with_streaming_response

with_streaming_response() -> (
    AsyncModerationsWithStreamingResponse
)

AsyncModerationsWithRawResponse

AsyncModerationsWithRawResponse(
    moderations: AsyncModerations,
)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = async_to_raw_response_wrapper(create)

AsyncModerationsWithStreamingResponse

AsyncModerationsWithStreamingResponse(
    moderations: AsyncModerations,
)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = async_to_streamed_response_wrapper(create)

Audio

Audio(client: OpenAI)

Methods:

Name	Description
`speech`
`transcriptions`
`translations`
`with_raw_response`
`with_streaming_response`

speech

speech() -> Speech

transcriptions

transcriptions() -> Transcriptions

translations

translations() -> Translations

with_raw_response

with_raw_response() -> AudioWithRawResponse

with_streaming_response

with_streaming_response() -> AudioWithStreamingResponse

AudioWithRawResponse

AudioWithRawResponse(audio: Audio)

Methods:

Name	Description
`speech`
`transcriptions`
`translations`

speech

speech() -> SpeechWithRawResponse

transcriptions

transcriptions() -> TranscriptionsWithRawResponse

translations

translations() -> TranslationsWithRawResponse

AudioWithStreamingResponse

AudioWithStreamingResponse(audio: Audio)

Methods:

Name	Description
`speech`
`transcriptions`
`translations`

speech

speech() -> SpeechWithStreamingResponse

transcriptions

transcriptions() -> TranscriptionsWithStreamingResponse

translations

translations() -> TranslationsWithStreamingResponse

Beta

Beta(client: OpenAI)

Methods:

Name	Description
`assistants`
`threads`
`with_raw_response`
`with_streaming_response`

assistants

assistants() -> Assistants

threads

threads() -> Threads

with_raw_response

with_raw_response() -> BetaWithRawResponse

with_streaming_response

with_streaming_response() -> BetaWithStreamingResponse

BetaWithRawResponse

BetaWithRawResponse(beta: Beta)

Methods:

Name	Description
`assistants`
`threads`

assistants

assistants() -> AssistantsWithRawResponse

threads

threads() -> ThreadsWithRawResponse

BetaWithStreamingResponse

BetaWithStreamingResponse(beta: Beta)

Methods:

Name	Description
`assistants`
`threads`

assistants

assistants() -> AssistantsWithStreamingResponse

threads

threads() -> ThreadsWithStreamingResponse

Chat

Chat(client: OpenAI)

Methods:

Name	Description
`completions`
`with_raw_response`
`with_streaming_response`

completions

completions() -> Completions

with_raw_response

with_raw_response() -> ChatWithRawResponse

with_streaming_response

with_streaming_response() -> ChatWithStreamingResponse

ChatWithRawResponse

ChatWithRawResponse(chat: Chat)

Methods:

Name	Description
`completions`

completions

completions() -> CompletionsWithRawResponse

ChatWithStreamingResponse

ChatWithStreamingResponse(chat: Chat)

Methods:

Name	Description
`completions`

completions

completions() -> CompletionsWithStreamingResponse

Completions

Completions(client: OpenAI)

Methods:

Name	Description
`create`	Creates a completion for the provided prompt and parameters.
`with_raw_response`
`with_streaming_response`

create

create(
    *,
    model: Union[
        str,
        Literal[
            "gpt-3.5-turbo-instruct",
            "davinci-002",
            "babbage-002",
        ],
    ],
    prompt: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
        None,
    ],
    best_of: Optional[int] | NotGiven = NOT_GIVEN,
    echo: Optional[bool] | NotGiven = NOT_GIVEN,
    frequency_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    logit_bias: (
        Optional[Dict[str, int]] | NotGiven
    ) = NOT_GIVEN,
    logprobs: Optional[int] | NotGiven = NOT_GIVEN,
    max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    presence_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    seed: Optional[int] | NotGiven = NOT_GIVEN,
    stop: (
        Union[Optional[str], List[str], None] | NotGiven
    ) = NOT_GIVEN,
    stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
    suffix: Optional[str] | NotGiven = NOT_GIVEN,
    temperature: Optional[float] | NotGiven = NOT_GIVEN,
    top_p: Optional[float] | NotGiven = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Completion

create(
    *,
    model: Union[
        str,
        Literal[
            "gpt-3.5-turbo-instruct",
            "davinci-002",
            "babbage-002",
        ],
    ],
    prompt: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
        None,
    ],
    stream: Literal[True],
    best_of: Optional[int] | NotGiven = NOT_GIVEN,
    echo: Optional[bool] | NotGiven = NOT_GIVEN,
    frequency_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    logit_bias: (
        Optional[Dict[str, int]] | NotGiven
    ) = NOT_GIVEN,
    logprobs: Optional[int] | NotGiven = NOT_GIVEN,
    max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    presence_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    seed: Optional[int] | NotGiven = NOT_GIVEN,
    stop: (
        Union[Optional[str], List[str], None] | NotGiven
    ) = NOT_GIVEN,
    suffix: Optional[str] | NotGiven = NOT_GIVEN,
    temperature: Optional[float] | NotGiven = NOT_GIVEN,
    top_p: Optional[float] | NotGiven = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Stream[Completion]

create(
    *,
    model: Union[
        str,
        Literal[
            "gpt-3.5-turbo-instruct",
            "davinci-002",
            "babbage-002",
        ],
    ],
    prompt: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
        None,
    ],
    stream: bool,
    best_of: Optional[int] | NotGiven = NOT_GIVEN,
    echo: Optional[bool] | NotGiven = NOT_GIVEN,
    frequency_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    logit_bias: (
        Optional[Dict[str, int]] | NotGiven
    ) = NOT_GIVEN,
    logprobs: Optional[int] | NotGiven = NOT_GIVEN,
    max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    presence_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    seed: Optional[int] | NotGiven = NOT_GIVEN,
    stop: (
        Union[Optional[str], List[str], None] | NotGiven
    ) = NOT_GIVEN,
    suffix: Optional[str] | NotGiven = NOT_GIVEN,
    temperature: Optional[float] | NotGiven = NOT_GIVEN,
    top_p: Optional[float] | NotGiven = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Completion | Stream[Completion]

create(
    *,
    model: Union[
        str,
        Literal[
            "gpt-3.5-turbo-instruct",
            "davinci-002",
            "babbage-002",
        ],
    ],
    prompt: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
        None,
    ],
    best_of: Optional[int] | NotGiven = NOT_GIVEN,
    echo: Optional[bool] | NotGiven = NOT_GIVEN,
    frequency_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    logit_bias: (
        Optional[Dict[str, int]] | NotGiven
    ) = NOT_GIVEN,
    logprobs: Optional[int] | NotGiven = NOT_GIVEN,
    max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    presence_penalty: (
        Optional[float] | NotGiven
    ) = NOT_GIVEN,
    seed: Optional[int] | NotGiven = NOT_GIVEN,
    stop: (
        Union[Optional[str], List[str], None] | NotGiven
    ) = NOT_GIVEN,
    stream: (
        Optional[Literal[False]] | Literal[True] | NotGiven
    ) = NOT_GIVEN,
    suffix: Optional[str] | NotGiven = NOT_GIVEN,
    temperature: Optional[float] | NotGiven = NOT_GIVEN,
    top_p: Optional[float] | NotGiven = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Completion | Stream[Completion]

Creates a completion for the provided prompt and parameters.

Parameters:

Name	Type	Description	Default
`model`	`Union[str, Literal['gpt-3.5-turbo-instruct', 'davinci-002', 'babbage-002']]`	ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.	required
`prompt`	`Union[str, List[str], Iterable[int], Iterable[Iterable[int]], None]`	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.	required
`best_of`	`Optional[int] \| NotGiven`	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`.	`NOT_GIVEN`
`echo`	`Optional[bool] \| NotGiven`	Echo back the prompt in addition to the completion	`NOT_GIVEN`
`frequency_penalty`	`Optional[float] \| NotGiven`	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.	`NOT_GIVEN`
`logit_bias`	`Optional[Dict[str, int]] \| NotGiven`	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 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.	`NOT_GIVEN`
`logprobs`	`Optional[int] \| NotGiven`	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.	`NOT_GIVEN`
`max_tokens`	`Optional[int] \| NotGiven`	The maximum number of tokens 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 for counting tokens.	`NOT_GIVEN`
`n`	`Optional[int] \| NotGiven`	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`.	`NOT_GIVEN`
`presence_penalty`	`Optional[float] \| NotGiven`	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.	`NOT_GIVEN`
`seed`	`Optional[int] \| NotGiven`	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.	`NOT_GIVEN`
`stop`	`Union[Optional[str], List[str], None] \| NotGiven`	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.	`NOT_GIVEN`
`stream`	`Optional[Literal[False]] \| Literal[True] \| NotGiven`	Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a `data: [DONE]` message. Example Python code.	`NOT_GIVEN`
`suffix`	`Optional[str] \| NotGiven`	The suffix that comes after a completion of inserted text.	`NOT_GIVEN`
`temperature`	`Optional[float] \| NotGiven`	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.	`NOT_GIVEN`
`top_p`	`Optional[float] \| NotGiven`	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.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> CompletionsWithRawResponse

with_streaming_response

with_streaming_response() -> (
    CompletionsWithStreamingResponse
)

CompletionsWithRawResponse

CompletionsWithRawResponse(completions: Completions)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = to_raw_response_wrapper(create)

CompletionsWithStreamingResponse

CompletionsWithStreamingResponse(completions: Completions)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = to_streamed_response_wrapper(create)

Embeddings

Embeddings(client: OpenAI)

Methods:

Name	Description
`create`	Creates an embedding vector representing the input text.
`with_raw_response`
`with_streaming_response`

create

create(
    *,
    input: Union[
        str,
        List[str],
        Iterable[int],
        Iterable[Iterable[int]],
    ],
    model: Union[
        str,
        Literal[
            "text-embedding-ada-002",
            "text-embedding-3-small",
            "text-embedding-3-large",
        ],
    ],
    dimensions: int | NotGiven = NOT_GIVEN,
    encoding_format: (
        Literal["float", "base64"] | NotGiven
    ) = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> CreateEmbeddingResponse

Creates an embedding vector representing the input text.

Parameters:

Name	Type	Description	Default
`input`	`Union[str, List[str], Iterable[int], Iterable[Iterable[int]]]`	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 for counting tokens.	required
`model`	`Union[str, Literal['text-embedding-ada-002', 'text-embedding-3-small', 'text-embedding-3-large']]`	ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.	required
`dimensions`	`int \| NotGiven`	The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models.	`NOT_GIVEN`
`encoding_format`	`Literal['float', 'base64'] \| NotGiven`	The format to return the embeddings in. Can be either `float` or `base64`.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> EmbeddingsWithRawResponse

with_streaming_response

with_streaming_response() -> (
    EmbeddingsWithStreamingResponse
)

EmbeddingsWithRawResponse

EmbeddingsWithRawResponse(embeddings: Embeddings)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = to_raw_response_wrapper(create)

EmbeddingsWithStreamingResponse

EmbeddingsWithStreamingResponse(embeddings: Embeddings)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = to_streamed_response_wrapper(create)

Files

Files(client: OpenAI)

Methods:

Name	Description
`content`	Returns the contents of the specified file.
`create`	Upload a file that can be used across various endpoints.
`delete`	Delete a file.
`list`	Returns a list of files that belong to the user's organization.
`retrieve`	Returns information about a specific file.
`retrieve_content`	Returns the contents of the specified file.
`wait_for_processing`	Waits for the given file to be processed, default timeout is 30 mins.
`with_raw_response`
`with_streaming_response`

content

content(
    file_id: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> HttpxBinaryResponseContent

Returns the contents of the specified file.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

create

create(
    *,
    file: FileTypes,
    purpose: Literal["fine-tune", "assistants"],
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> FileObject

Upload a file that can be used across various endpoints.

The size of all the files uploaded by one organization can be up to 100 GB.

The size of individual files can be a maximum of 512 MB or 2 million tokens for Assistants. See the Assistants Tools guide to learn more about the types of files supported. The Fine-tuning API only supports .jsonl files.

Please contact us if you need to increase these storage limits.

Parameters:

Name	Type	Description	Default
`file`	`FileTypes`	The File object (not file name) to be uploaded.	required
`purpose`	`Literal['fine-tune', 'assistants']`	The intended purpose of the uploaded file. Use "fine-tune" for Fine-tuning and "assistants" for Assistants and Messages. This allows us to validate the format of the uploaded file is correct for fine-tuning.	required
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

delete

delete(
    file_id: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> FileDeleted

Delete a file.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

list

list(
    *,
    purpose: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> SyncPage[FileObject]

Returns a list of files that belong to the user's organization.

Parameters:

Name	Type	Description	Default
`purpose`	`str \| NotGiven`	Only return files with the given purpose.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

retrieve

retrieve(
    file_id: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> FileObject

Returns information about a specific file.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

retrieve_content

retrieve_content(
    file_id: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> str

Returns the contents of the specified file.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

wait_for_processing

wait_for_processing(
    id: str,
    *,
    poll_interval: float = 5.0,
    max_wait_seconds: float = 30 * 60
) -> FileObject

Waits for the given file to be processed, default timeout is 30 mins.

with_raw_response

with_raw_response() -> FilesWithRawResponse

with_streaming_response

with_streaming_response() -> FilesWithStreamingResponse

FilesWithRawResponse

FilesWithRawResponse(files: Files)

Attributes:

Name	Type	Description
`content`
`create`
`delete`
`list`
`retrieve`
`retrieve_content`

content `instance-attribute`

content = to_raw_response_wrapper(content)

create `instance-attribute`

create = to_raw_response_wrapper(create)

delete `instance-attribute`

delete = to_raw_response_wrapper(delete)

list `instance-attribute`

list = to_raw_response_wrapper(list)

retrieve `instance-attribute`

retrieve = to_raw_response_wrapper(retrieve)

retrieve_content `instance-attribute`

retrieve_content = to_raw_response_wrapper(retrieve_content)

FilesWithStreamingResponse

FilesWithStreamingResponse(files: Files)

Attributes:

Name	Type	Description
`content`
`create`
`delete`
`list`
`retrieve`
`retrieve_content`

content `instance-attribute`

content = to_custom_streamed_response_wrapper(
    content, StreamedBinaryAPIResponse
)

create `instance-attribute`

create = to_streamed_response_wrapper(create)

delete `instance-attribute`

delete = to_streamed_response_wrapper(delete)

list `instance-attribute`

list = to_streamed_response_wrapper(list)

retrieve `instance-attribute`

retrieve = to_streamed_response_wrapper(retrieve)

retrieve_content `instance-attribute`

retrieve_content = to_streamed_response_wrapper(
    retrieve_content
)

FineTuning

FineTuning(client: OpenAI)

Methods:

Name	Description
`jobs`
`with_raw_response`
`with_streaming_response`

jobs

jobs() -> Jobs

with_raw_response

with_raw_response() -> FineTuningWithRawResponse

with_streaming_response

with_streaming_response() -> (
    FineTuningWithStreamingResponse
)

FineTuningWithRawResponse

FineTuningWithRawResponse(fine_tuning: FineTuning)

Methods:

Name	Description
`jobs`

jobs

jobs() -> JobsWithRawResponse

FineTuningWithStreamingResponse

FineTuningWithStreamingResponse(fine_tuning: FineTuning)

Methods:

Name	Description
`jobs`

jobs

jobs() -> JobsWithStreamingResponse

Images

Images(client: OpenAI)

Methods:

Name	Description
`create_variation`	Creates a variation of a given image.
`edit`	Creates an edited or extended image given an original image and a prompt.
`generate`	Creates an image given a prompt.
`with_raw_response`
`with_streaming_response`

create_variation

create_variation(
    *,
    image: FileTypes,
    model: (
        Union[str, Literal["dall-e-2"], None] | NotGiven
    ) = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    response_format: (
        Optional[Literal["url", "b64_json"]] | NotGiven
    ) = NOT_GIVEN,
    size: (
        Optional[Literal["256x256", "512x512", "1024x1024"]]
        | NotGiven
    ) = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ImagesResponse

Creates a variation of a given image.

Parameters:

Name	Type	Description	Default
`image`	`FileTypes`	The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.	required
`model`	`Union[str, Literal['dall-e-2'], None] \| NotGiven`	The model to use for image generation. Only `dall-e-2` is supported at this time.	`NOT_GIVEN`
`n`	`Optional[int] \| NotGiven`	The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported.	`NOT_GIVEN`
`response_format`	`Optional[Literal['url', 'b64_json']] \| NotGiven`	The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated.	`NOT_GIVEN`
`size`	`Optional[Literal['256x256', '512x512', '1024x1024']] \| NotGiven`	The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

edit

edit(
    *,
    image: FileTypes,
    prompt: str,
    mask: FileTypes | NotGiven = NOT_GIVEN,
    model: (
        Union[str, Literal["dall-e-2"], None] | NotGiven
    ) = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    response_format: (
        Optional[Literal["url", "b64_json"]] | NotGiven
    ) = NOT_GIVEN,
    size: (
        Optional[Literal["256x256", "512x512", "1024x1024"]]
        | NotGiven
    ) = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ImagesResponse

Creates an edited or extended image given an original image and a prompt.

Parameters:

Name	Type	Description	Default
`image`	`FileTypes`	The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask.	required
`prompt`	`str`	A text description of the desired image(s). The maximum length is 1000 characters.	required
`mask`	`FileTypes \| NotGiven`	An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.	`NOT_GIVEN`
`model`	`Union[str, Literal['dall-e-2'], None] \| NotGiven`	The model to use for image generation. Only `dall-e-2` is supported at this time.	`NOT_GIVEN`
`n`	`Optional[int] \| NotGiven`	The number of images to generate. Must be between 1 and 10.	`NOT_GIVEN`
`response_format`	`Optional[Literal['url', 'b64_json']] \| NotGiven`	The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated.	`NOT_GIVEN`
`size`	`Optional[Literal['256x256', '512x512', '1024x1024']] \| NotGiven`	The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

generate

generate(
    *,
    prompt: str,
    model: (
        Union[str, Literal["dall-e-2", "dall-e-3"], None]
        | NotGiven
    ) = NOT_GIVEN,
    n: Optional[int] | NotGiven = NOT_GIVEN,
    quality: (
        Literal["standard", "hd"] | NotGiven
    ) = NOT_GIVEN,
    response_format: (
        Optional[Literal["url", "b64_json"]] | NotGiven
    ) = NOT_GIVEN,
    size: (
        Optional[
            Literal[
                "256x256",
                "512x512",
                "1024x1024",
                "1792x1024",
                "1024x1792",
            ]
        ]
        | NotGiven
    ) = NOT_GIVEN,
    style: (
        Optional[Literal["vivid", "natural"]] | NotGiven
    ) = NOT_GIVEN,
    user: str | NotGiven = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ImagesResponse

Creates an image given a prompt.

Parameters:

Name	Type	Description	Default
`prompt`	`str`	A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`.	required
`model`	`Union[str, Literal['dall-e-2', 'dall-e-3'], None] \| NotGiven`	The model to use for image generation.	`NOT_GIVEN`
`n`	`Optional[int] \| NotGiven`	The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported.	`NOT_GIVEN`
`quality`	`Literal['standard', 'hd'] \| NotGiven`	The quality of the image that will be generated. `hd` creates images with finer details and greater consistency across the image. This param is only supported for `dall-e-3`.	`NOT_GIVEN`
`response_format`	`Optional[Literal['url', 'b64_json']] \| NotGiven`	The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated.	`NOT_GIVEN`
`size`	`Optional[Literal['256x256', '512x512', '1024x1024', '1792x1024', '1024x1792']] \| NotGiven`	The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`. Must be one of `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3` models.	`NOT_GIVEN`
`style`	`Optional[Literal['vivid', 'natural']] \| NotGiven`	The style of the generated images. Must be one of `vivid` or `natural`. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for `dall-e-3`.	`NOT_GIVEN`
`user`	`str \| NotGiven`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> ImagesWithRawResponse

with_streaming_response

with_streaming_response() -> ImagesWithStreamingResponse

ImagesWithRawResponse

ImagesWithRawResponse(images: Images)

Attributes:

Name	Type	Description
`create_variation`
`edit`
`generate`

create_variation `instance-attribute`

create_variation = to_raw_response_wrapper(create_variation)

edit `instance-attribute`

edit = to_raw_response_wrapper(edit)

generate `instance-attribute`

generate = to_raw_response_wrapper(generate)

ImagesWithStreamingResponse

ImagesWithStreamingResponse(images: Images)

Attributes:

Name	Type	Description
`create_variation`
`edit`
`generate`

create_variation `instance-attribute`

create_variation = to_streamed_response_wrapper(
    create_variation
)

edit `instance-attribute`

edit = to_streamed_response_wrapper(edit)

generate `instance-attribute`

generate = to_streamed_response_wrapper(generate)

Models

Models(client: OpenAI)

Methods:

Name	Description
`delete`	Delete a fine-tuned model.
`list`	Lists the currently available models, and provides basic information about each
`retrieve`	Retrieves a model instance, providing basic information about the model such as
`with_raw_response`
`with_streaming_response`

delete

delete(
    model: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ModelDeleted

Delete a fine-tuned model.

You must have the Owner role in your organization to delete a model.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

list

list(
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> SyncPage[Model]

Lists the currently available models, and provides basic information about each one such as the owner and availability.

retrieve

retrieve(
    model: str,
    *,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> Model

Retrieves a model instance, providing basic information about the model such as the owner and permissioning.

Parameters:

Name	Type	Description	Default
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> ModelsWithRawResponse

with_streaming_response

with_streaming_response() -> ModelsWithStreamingResponse

ModelsWithRawResponse

ModelsWithRawResponse(models: Models)

Attributes:

Name	Type	Description
`delete`
`list`
`retrieve`

delete `instance-attribute`

delete = to_raw_response_wrapper(delete)

list `instance-attribute`

list = to_raw_response_wrapper(list)

retrieve `instance-attribute`

retrieve = to_raw_response_wrapper(retrieve)

ModelsWithStreamingResponse

ModelsWithStreamingResponse(models: Models)

Attributes:

Name	Type	Description
`delete`
`list`
`retrieve`

delete `instance-attribute`

delete = to_streamed_response_wrapper(delete)

list `instance-attribute`

list = to_streamed_response_wrapper(list)

retrieve `instance-attribute`

retrieve = to_streamed_response_wrapper(retrieve)

Moderations

Moderations(client: OpenAI)

Methods:

Name	Description
`create`	Classifies if text is potentially harmful.
`with_raw_response`
`with_streaming_response`

create

create(
    *,
    input: Union[str, List[str]],
    model: (
        Union[
            str,
            Literal[
                "text-moderation-latest",
                "text-moderation-stable",
            ],
        ]
        | NotGiven
    ) = NOT_GIVEN,
    extra_headers: Headers | None = None,
    extra_query: Query | None = None,
    extra_body: Body | None = None,
    timeout: float | Timeout | None | NotGiven = NOT_GIVEN
) -> ModerationCreateResponse

Classifies if text is potentially harmful.

Parameters:

Name	Type	Description	Default
`input`	`Union[str, List[str]]`	The input text to classify	required
`model`	`Union[str, Literal['text-moderation-latest', 'text-moderation-stable']] \| NotGiven`	Two content moderations models are available: `text-moderation-stable` and `text-moderation-latest`. The default is `text-moderation-latest` which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use `text-moderation-stable`, we will provide advanced notice before updating the model. Accuracy of `text-moderation-stable` may be slightly lower than for `text-moderation-latest`.	`NOT_GIVEN`
`extra_headers`	`Headers \| None`	Send extra headers	`None`
`extra_query`	`Query \| None`	Add additional query parameters to the request	`None`
`extra_body`	`Body \| None`	Add additional JSON properties to the request	`None`
`timeout`	`float \| Timeout \| None \| NotGiven`	Override the client-level default timeout for this request, in seconds	`NOT_GIVEN`

with_raw_response

with_raw_response() -> ModerationsWithRawResponse

with_streaming_response

with_streaming_response() -> (
    ModerationsWithStreamingResponse
)

ModerationsWithRawResponse

ModerationsWithRawResponse(moderations: Moderations)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = to_raw_response_wrapper(create)

ModerationsWithStreamingResponse

ModerationsWithStreamingResponse(moderations: Moderations)

Attributes:

Name	Type	Description
`create`

create `instance-attribute`

create = to_streamed_response_wrapper(create)

openai.resources

AsyncAudio

speech

transcriptions

translations

with_raw_response

with_streaming_response

AsyncAudioWithRawResponse

speech

transcriptions

translations

AsyncAudioWithStreamingResponse

speech

transcriptions

translations

AsyncBeta

assistants

threads

with_raw_response

with_streaming_response

AsyncBetaWithRawResponse

assistants

threads

AsyncBetaWithStreamingResponse

assistants

threads

AsyncChat

completions

with_raw_response

with_streaming_response

AsyncChatWithRawResponse

completions

AsyncChatWithStreamingResponse

completions

AsyncCompletions

create async

with_raw_response

with_streaming_response

AsyncCompletionsWithRawResponse

create instance-attribute

AsyncCompletionsWithStreamingResponse

create instance-attribute

AsyncEmbeddings

create async

with_raw_response

with_streaming_response

AsyncEmbeddingsWithRawResponse

create instance-attribute

AsyncEmbeddingsWithStreamingResponse

create instance-attribute

AsyncFiles

content async

create async

delete async

list

retrieve async

retrieve_content async

wait_for_processing async

with_raw_response

with_streaming_response

AsyncFilesWithRawResponse

content instance-attribute

create instance-attribute

delete instance-attribute

list instance-attribute

retrieve instance-attribute

retrieve_content instance-attribute

AsyncFilesWithStreamingResponse

content instance-attribute

create instance-attribute

delete instance-attribute

list instance-attribute

retrieve instance-attribute

retrieve_content instance-attribute

AsyncFineTuning

jobs

with_raw_response

with_streaming_response

AsyncFineTuningWithRawResponse

jobs

create `async`

create `instance-attribute`

create `instance-attribute`

create `async`

create `instance-attribute`

create `instance-attribute`

content `async`

create `async`

delete `async`

retrieve `async`

retrieve_content `async`

wait_for_processing `async`

content `instance-attribute`

create `instance-attribute`

delete `instance-attribute`

list `instance-attribute`

retrieve `instance-attribute`

retrieve_content `instance-attribute`

content `instance-attribute`

create `instance-attribute`

delete `instance-attribute`

list `instance-attribute`

retrieve `instance-attribute`

retrieve_content `instance-attribute`

create_variation `async`

edit `async`

generate `async`

create_variation `instance-attribute`

edit `instance-attribute`

generate `instance-attribute`

create_variation `instance-attribute`

edit `instance-attribute`

generate `instance-attribute`

delete `async`

retrieve `async`

delete `instance-attribute`

list `instance-attribute`

retrieve `instance-attribute`

delete `instance-attribute`

list `instance-attribute`

retrieve `instance-attribute`

create `async`

create `instance-attribute`

create `instance-attribute`