Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.

Edits

interface Edits

Given a prompt and an instruction, the model will return an edited version of the prompt.

Embeddings

interface Embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

Files

interface Files

Files are used to upload documents that can be used across features like Answers, Searches, and Classifications

FineTunes

interface FineTunes

Manage fine-tuning jobs to tailor a model to your specific training data.

FineTuning

interface FineTuning

Manage fine-tuning jobs to tailor a model to your specific training data.

Images

interface Images

Given a prompt and/or an input image, the model will generate a new image.

LoggingConfig

class LoggingConfig(val logLevel: LogLevel = LogLevel.Headers, val logger: Logger = Logger.Simple, val sanitize: Boolean = true)

Defines the configuration parameters for logging.

Messages

interface Messages

Create messages within threads

Models

interface Models

List and describe the various models available in the API. You can refer to the Models documentation to understand what models are available and the differences between them.

Moderations

interface Moderations

Given an input text, outputs if the model classifies it as violating OpenAI's content policy.

OpenAI

interface OpenAI : Completions, Files, Edits, Embeddings, Models, Moderations, FineTunes, Images, Chat, Audio, FineTuning, Assistants, Threads, Runs, Messages, VectorStores, Closeable

OpenAI API.

OpenAIConfig

class OpenAIConfig(val token: String, val logging: LoggingConfig = LoggingConfig(), val timeout: Timeout = Timeout(socket = 30.seconds), val organization: String? = null, val headers: Map<String, String> = emptyMap(), val host: OpenAIHost = OpenAIHost.OpenAI, val proxy: ProxyConfig? = null, val retry: RetryStrategy = RetryStrategy(), val engine: HttpClientEngine? = null, val httpClientConfig: HttpClientConfig<*>.() -> Unit = {})

OpenAI client configuration.

OpenAIHost

class OpenAIHost(val baseUrl: String, val queryParams: Map<String, String> = emptyMap())

A class to configure the OpenAI host. It provides a mechanism to customize the base URL and additional query parameters used in OpenAI API requests.

ProxyConfig

interface ProxyConfig

Proxy configuration.

RetryStrategy

class RetryStrategy(val maxRetries: Int = 3, val base: Double = 2.0, val maxDelay: Duration = 60.seconds)

Specifies the retry strategy

Runs

interface Runs

Represents an execution run on a thread.

Threads

interface Threads

Create threads that assistants can interact with.

VectorStores

interface VectorStores

Vector stores are used to store files for use by the file_search tool.

Functions

OpenAI

fun OpenAI(config: OpenAIConfig): OpenAI

fun OpenAI(token: String, logging: LoggingConfig = LoggingConfig(), timeout: Timeout = Timeout(socket = 30.seconds), organization: String? = null, headers: Map<String, String> = emptyMap(), host: OpenAIHost = OpenAIHost.OpenAI, proxy: ProxyConfig? = null, retry: RetryStrategy = RetryStrategy(), httpClientConfig: HttpClientConfig<*>.() -> Unit = {}): OpenAI

Creates an instance of OpenAI.