Struct Loom

pub struct Loom<T: Config> {
    pub chest: T::Chest,
    /* private fields */
}

The machine that drives all of the core methods that should be used across any service that needs to prompt LLM and receive a response.

This is implemented over the Config trait.

Fields

chest: T::Chest

Implementations

impl<T: Config> Loom<T>

pub fn new() -> Self

Creates a new instance of Loom.

pub async fn weave<TID: TapestryId>( &self, prompt_llm_config: LlmConfig<T, T::PromptModel>, summary_llm_config: LlmConfig<T, T::SummaryModel>, tapestry_id: TID, instructions: String, msgs: Vec<ContextMessage<T>>, ) -> Result<(<<T as Config>::PromptModel as Llm<T>>::Response, u64, bool), Box<dyn Error + Send + Sync>>

Prompt LLM Weaver for a response for TapestryId.

Prompts LLM with the current TapestryFragment instance and the new msgs.

A summary will be generated of the current TapestryFragment instance if the total number of tokens in the context_messages exceeds the maximum number of tokens allowed for the current Config::PromptModel or custom max tokens. This threshold is affected by the Config::TOKEN_THRESHOLD_PERCENTILE.

Parameters

• prompt_llm_config: The Config::PromptModel to use for prompting LLM.
• summary_llm_config: The Config::SummaryModel to use for generating summaries.
• tapestry_id: The TapestryId to use for storing the TapestryFragment instance.
• instructions: The instruction message to be used for the current TapestryFragment instance.
• msgs: The messages to prompt the LLM with.

pub fn build_context_message( role: WrapperRole, content: String, account_id: Option<String>, ) -> ContextMessage<T>

Helper method to build a ContextMessage

Trait Implementations

impl<T: Debug + Config> Debug for Loom<T>

where T::Chest: Debug,

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.