All Classes

Class	Description
ChatCompletionChoice	Represents a choice in the chat completion response.
ChatCompletionChoiceMessage	Represents the message content in a chat completion choice, including the role (e.g., user, assistant) and the actual text content of the message.
ChatCompletionFunctionCallDetails	Represents the a call of a function used as a tool in the chat completion request.
ChatCompletionFunctionDetails	Represents the details of a function used as a tool in the chat completion request.
ChatCompletionMessage	Represents a message in a chat completion request, containing the role of the speaker (user, assistant, or system) and the message content, which may include text or other parts.
ChatCompletionMessagePart	Represents a part of a chat completion message, which may be a text or an image URL.
ChatCompletionMessagePart.ChatCompletionMessagePartListDeSerializer
ChatCompletionMessagePart.ChatCompletionMessageUrlPart	Encodes URL part: { "url": "https://example.com/somepicture.jpg" }
ChatCompletionMessagePart.ImageDetail
ChatCompletionMessagePart.Type
ChatCompletionRequest	Represents a request to the OpenAI chat completion API, including model, messages, and optional parameters like max tokens, temperature, and response format.
ChatCompletionRequest.ResponseFormat
ChatCompletionRequest.ResponseFormatType
ChatCompletionRequest.Role
ChatCompletionResponse	Represents the response from the OpenAI chat completion API, containing details about the generated choices, token usage, and metadata like the model used and creation time.
ChatCompletionResponse.FinishReason
ChatCompletionToolCall	Represents a tool call generated by the model in a chat completion response.
ChatCompletionUsage	Represents the token usage details in a chat completion response, including the number of tokens used for the prompt, the completion, and the total.
ChatTool	Represents a tool in the OpenAI chat completion request, currently limited to functions.
GPTBackendConfiguration	Configuration for a generic LLM backend used by Composum AI.
GPTBackendsConfigurationService	A service that lists all backends usable with GPTChatCompletionService etc.
GPTBackendsConfigurationServiceImpl	Provides the backend configurations from OSGI.
GPTBackendsService	A service managing the backends for GPTChatCompletionService etc.
GPTBackendsServiceImpl
GPTChatCompletionService	Raw abstraction of the ChatGPT chat interface, with only the details that are needed.
GPTChatCompletionServiceImpl	Implements the actual access to the ChatGPT chat API.
GPTChatCompletionServiceImpl.EnsureResultFutureCallback	Makes doubly sure that result is somehow set after the call.
GPTChatCompletionServiceImpl.GPTChatCompletionServiceConfig
GPTChatCompletionServiceImpl.RetryableException	Thrown when we get a 429 rate limiting response.
GPTChatMessage	A chat message in a dialog with ChatGPT.
GPTChatMessagesTemplate	A template for chat messages, with placeholders.
GPTChatRequest	A request to ChatGPT.
GPTCompletionCallback	For a streaming mode this is given as parameter for the method call and receives the streamed data; the method returns only when the response is complete.
GPTCompletionCallback.GPTCompletionCallbackWrapper	Forwards all methods to a delegate.
GPTCompletionCallback.GPTCompletionCollector	A simple collector that just takes note of things.
GPTCompletionCallback.GPTToolExecutionContext	For tool calls: context to execute actions in.
GPTConfiguration	A configuration to use for accessing the external LLM service.
GPTConfiguration.AnswerType
GPTConfiguration.GPTContextInfo	Gives the conversation a history - additional assistant - user message pair.
GPTConfiguration.Mode
GPTContentCreationService	Service to generate content (keywords / descriptions from a text, and so forth.)
GPTContentCreationServiceImpl	Building on GPTChatCompletionService this implements generating keywords.
GPTDictationService	Services related to dictation.
GPTDictationServiceImpl
GPTDictationServiceImpl.GPTDictationServiceConfig	Configures whether it's enabled (default false), the model and the request counts, and the maximum request size.
GPTEmbeddingService	Methods related to embeddings.
GPTEmbeddingService.EmbeddingsCache	Optional cache for embedding values.
GPTEmbeddingServiceImpl
GPTException	Any kind of error when accessing GPT.
GPTException.GPTContextLengthExceededException	{ "error": { "message": "This model's maximum context length is 4097 tokens.
GPTException.GPTRetryableResponseErrorException	An exception that is thrown when the response from the GPT service is not as expected.
GPTException.GPTUserNotificationException	A special exception if the user should be notified about something instead of completing the task.
GPTFinishReason
GPTFunctionCallDetails	Represents the a call of a function used as a tool in the chat completion request.
GPTFunctionDetails	Represents the details of a function used as a tool in the chat completion request.
GPTInternalOpenAIHelper	Helpers for implementation in this package.
GPTInternalOpenAIHelper.GPTInternalOpenAIHelperInst
GPTMessageRole	Role of a GPTChatMessage in a dialog with ChatGPT.
GPTResponseCheck	An additional check that verifies whether the translation was carried out right - such as paths in HTML weren't translated.
GPTTool	An action the AI can perform - likely from the sidebar chat.
GPTToolCall	Represents a tool call generated by the model in a chat completion response.
GPTTranslationService	Building on GPTChatCompletionService this implements translation.
GPTTranslationServiceImpl	Building on GPTChatCompletionService this implements translation.
GPTTranslationServiceImpl.Config
HtmlToMarkdownConverter	A quick HTML markdown converter that handles the tags [a, strong, code, em, p, br, u, ul, li, ol] used in rich text editor.
OpenAIEmbeddings	Request and response for OpenAI embeddings API.
OpenAIEmbeddings.EmbeddingObject
OpenAIEmbeddings.EmbeddingRequest
OpenAIEmbeddings.EmbeddingResponse
RateLimiter	This class is used to limit the rate of requests to the chat service.
StringstreamSlowdown	For a stream of String segments (like the ChatGPT tokens that trickle in from ChatGPT when streaming) this collects the parts and forwards the collected part every 500ms to a given consumer.