All Classes and Interfaces
Class
Description
Represents an assistant that can call the model and use tools.
Build assistants that can call models and use tools to perform tasks.
Could be either
AssistantsResponseFormat.StringResponseFormat or ResponseFormatCould be either
AssistantsToolChoice.StringToolChoice or ToolChoiceAn interface which is used to subscribe to assistant events emitted when streaming a Run.
Turn audio into text or text into audio.
Create large batches of API requests to run asynchronously.
Given a list of messages comprising a conversation, the model will return a response.
Represents a chat completion response returned by model, based on the provided input.
A chat completion message generated by the model.
Represents a streamed chunk of a chat completion response returned by model, based on the
provided input.
A chat completion delta generated by streamed model responses.
An interface which is used to subscribe to streamed partial responses
Details of the tool call the
ThreadRunStepDelta was involved in.Represents an embedding vector returned by embedding endpoint.
Get a vector representation of a given input that can be easily consumed by machine learning
models and algorithms.
The expiration policy for a vector store.
Files are used to upload documents that can be used with features like Assistants and
Fine-tuning.
Manage fine-tuning jobs to tailor a model to your specific training data.
The fine_tuning.job object represents a fine-tuning job that has been created through the API.
The hyperparameters used for the fine-tuning job
The fine_tuning.job.checkpoint object represents a model checkpoint for a fine-tuning job that is
ready to use.
Function that the model may generate JSON inputs for.
Given a prompt and/or an input image, the model will generate a new image.
The last error associated with an object
Log probability information
Create messages within threads
List and describe the various models available in the API.
Represents if a given text input is potentially harmful.
Given some input text, outputs if the model classifies it as potentially harmful across several
categories.
A class which when created using the
OpenAI.newBuilder(String) can be used to create clients
based on the endpoints defined at API
Reference - OpenAI APIExceptions will be based on Error Codes - OpenAI
API
Represents the latest OpenAI models.
An object specifying the format that the model must output.
Represents an execution run on a thread.
Represents the steps (model and tool calls) taken during the run.
A Thread represents a conversation.
Represents a message within a thread.
On an incomplete message, details about why the message is incomplete.
Represents a message delta i.e.
The delta containing the fields that have changed on the Message.
Represents an execution run on a thread.
Details on why the run is incomplete.
Details on the action required to continue the run.
Represents a step in execution of a run.
The details of the run step.
Represents a run step delta i.e.
The delta containing the fields that have changed on the run step.
The details of the run step.
Create threads that assistants can interact with.
Specifies a tool the model should use.
A set of resources that are used by the assistant's tools.
Thread Truncation Controls
Usage statistics
A vector store is a collection of processed files can be used by the file_search tool.
A file attached to a vector store.
A batch of files attached to a vector store.
Vector store file batches represent operations to add multiple files to a vector store.
Vector store files represent files inside a vector store.
Vector stores are used to store files for use by the file_search tool.