our friendly logo that looks like a hashbrown character from an animated tv showhashbrown

@hashbrownai/coreHashbrown

Represents a Hashbrown chat instance, providing methods to send and observe messages, track state, and handle errors.

@template Output - The type of messages received from the LLM, either a string or structured output defined by HashbrownType. @template Tools - The set of tools available to the chat instance.

interface Hashbrown<Output, Tools extends Chat.AnyTool>  {
readonly error: Error | undefined;
readonly messages: Chat.Message<Output, Tools>[];
observeError: (onChange: (error: Error | undefined) => void) => void;
observeExhaustedRetries: (onChange: (exhaustedRetries: boolean) => void) => void;
observeIsLoading: (onChange: (isLoading: boolean) => void) => void;
observeIsReceiving: (onChange: (isReceiving: boolean) => void) => void;
observeIsRunningToolCalls: (onChange: (isRunningToolCalls: boolean) => void) => void;
observeIsSending: (onChange: (isSending: boolean) => void) => void;
observeMessages: (onChange: (messages: Chat.Message<Output, Tools>[]) => void) => void;
resendMessages: () => void;
sendMessage: (message: Chat.Message<Output, Tools>) => void;
setMessages: (messages: Chat.Message<Output, Tools>[]) => void;
teardown: () => void;
updateOptions: (options: Partial<{
        debugName?: string;
        apiUrl: string;
        model: string;
        system: string;
        tools: Tools[];
        responseSchema: s.HashbrownType;
        middleware: Chat.Middleware[];
        emulateStructuredOutput: boolean;
        debounce: number;
        retries: number;
    }>) => void;
}
@typeOutput
@typeTools
Chat.AnyTool

LiveLoveApp provides secure, compliant, and reliable long-term support to enterprises. We are a group of engineers who are passionate about open source.

Enterprise Support

AI Engineering Sprint

Get your team up-to-speed on AI engineering with a one week AI engineering sprint. Includes a workshop on AI engineering with hashbrown and a few days with the hashbrown developer team to bring your AI ideas to life.

Long Term Support

Keep your hashbrown deployments running at peak performance with our Long Term Support. Includes an ongoing support retainer for direct access to the hashbrown developer team, SLA-backed issue resolution, and guided upgrades.

Consulting

LiveLoveApp provides hands-on engagement with our AI engineers for architecture reviews, custom integrations, proof-of-concept builds, performance tuning, and expert guidance on best practices.