Theia API Documentation v1.72.1
    Preparing search index...
    interface OpenAiModelDescription {
        apiKey: undefined | string | true;
        apiVersion: undefined | string | true;
        deployment?: string;
        developerMessageSettings?:
            | "user"
            | "system"
            | "developer"
            | "mergeWithFollowingUserMessage"
            | "skip";
        enableStreaming?: boolean;
        id: string;
        maxRetries: number;
        model: string;
        reasoningSupport?: ReasoningSupport;
        supportsStructuredOutput?: boolean;
        url?: string;
        useResponseApi?: boolean;
    }
    Index

    Properties

    apiKey: undefined | string | true

    The key for the model. If true is provided the global OpenAI API key will be used.

    apiVersion: undefined | string | true

    The version for the api. If true is provided the global OpenAI version will be used.

    deployment?: string

    Optional deployment name for Azure OpenAI.

    developerMessageSettings?:
        | "user"
        | "system"
        | "developer"
        | "mergeWithFollowingUserMessage"
        | "skip"

    Configures how system messages are handled. 'user' | 'system' | 'developer' use that role for the system message; 'mergeWithFollowingUserMessage' prepends the system message to the next user message (creating one when needed); 'skip' removes system messages. Defaults from the model id when unset (typically 'developer').

    enableStreaming?: boolean

    Indicate whether the streaming API shall be used. Defaults from the model id when unset.

    id: string

    The identifier of the model which will be shown in the UI.

    maxRetries: number

    Maximum number of retry attempts when a request fails. Default is 3.

    model: string

    The model ID as used by the OpenAI API.

    reasoningSupport?: ReasoningSupport

    When set, the UI exposes a reasoning selector. Defaults from the model id when unset.

    supportsStructuredOutput?: boolean

    Whether the model supports structured output (response_format JSON schemas). Defaults from the model id when unset.

    url?: string

    The OpenAI API compatible endpoint where the model is hosted. If not provided the default OpenAI endpoint will be used.

    useResponseApi?: boolean

    Use the newer OpenAI Response API instead of the Chat Completion API. Default is false.