Struct Executor

pub struct Executor { /* private fields */ }

The Executor struct for the ChatGPT model. This executor uses the async_openai crate to communicate with the OpenAI API.

Implementations

impl Executor

pub fn for_client(client: Client<OpenAIConfig>, options: Options) -> Self

Creates a new Executor with the given client.

Trait Implementations

impl Clone for Executor

fn clone(&self) -> Executor

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Default for Executor

fn default() -> Self

Returns the “default value” for a type.

impl Executor for Executor

fn new_with_options(options: Options) -> Result<Self, ExecutorCreationError>

Creates a new Executor with the given options.

if the OPENAI_ORG_ID environment variable is present, it will be used as the org_ig for the OpenAI client.

fn max_tokens_allowed(&self, opts: &Options) -> i32

Get the context size from the model or return default context size

type StepTokenizer<'a> = OpenAITokenizer

fn execute<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, options: &'life1 Options, prompt: &'life2 Prompt, ) -> Pin<Box<dyn Future<Output = Result<Output, ExecutorError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

fn tokens_used( &self, opts: &Options, prompt: &Prompt, ) -> Result<TokenCount, PromptTokensError>

Calculates the number of tokens used by the step given a set of parameters.

fn answer_prefix(&self, _prompt: &Prompt) -> Option<String>

Returns a possible answer prefix inserted by the model, during a certain prompt mode

fn get_tokenizer( &self, options: &Options, ) -> Result<OpenAITokenizer, TokenizerError>

Creates a tokenizer, depending on the model used by step.

fn new() -> Result<Self, ExecutorCreationError>