Struct llm_chain_openai::chatgpt::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, per_invocation_options: Option<PerInvocation> ) -> 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() -> Executor

Returns the “default value” for a type.

impl Executor for Executor

fn max_tokens_allowed(&self, opts: Option<&PerInvocation>) -> i32

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

type PerInvocationOptions = PerInvocation

The per-invocation options type used by this executor. These are the options you can send to each step.

type PerExecutorOptions = PerExecutor

The per-executor options type used by this executor. These are the options you can send to the executor and can’t be set per step.

type Output = Output

The output type produced by this executor.

type Token = usize

The token type used by this executor.

type StepTokenizer<'a> = OpenAITokenizer

type TextSplitter<'a> = OpenAITextSplitter

type Error = Error

The error type produced by this executor.

fn new_with_options( executor_options: Option<Self::PerExecutorOptions>, invocation_options: Option<Self::PerInvocationOptions> ) -> Result<Self, ExecutorCreationError>

Create a new executor with the given executor options and invocation options. If you don’t need to set any options, you can use the new method instead.

fn execute<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, opts: Option<&'life1 PerInvocation>, prompt: &'life2 Prompt ) -> Pin<Box<dyn Future<Output = Result<Self::Output, Self::Error>> + Send + 'async_trait>>where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

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

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

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

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

fn get_text_splitter( &self, options: Option<&PerInvocation> ) -> Result<Self::TextSplitter<'_>, Self::Error>

Creates a text splitter, depending on the model used by ‘step’

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