Struct Codex 

pub struct Codex { /* private fields */ }

A LanguageModel for a single model on the Codex subscription backend.

Implementations

impl Codex

pub fn new(credentials: CodexCredentials, model: impl Into<String>) -> Codex

Create a client for model using the given credentials.

pub fn with_base_url(self, base_url: impl Into<String>) -> Codex

Override the backend base URL (defaults to the Codex subscription endpoint).

Panics

Panics if the client has already been cloned/shared.

pub fn with_originator(self, originator: impl Into<String>) -> Codex

Override the originator header (defaults to ORIGINATOR).

Panics

Panics if the client has already been cloned/shared.

pub fn on_refresh( self, callback: impl Fn(&CodexCredentials) + Send + Sync + 'static, ) -> Codex

Register a callback fired whenever tokens rotate.

Panics

Panics if the client has already been cloned/shared.

pub async fn credentials(&self) -> CodexCredentials

A snapshot of the current credentials.

Trait Implementations

impl Clone for Codex

fn clone(&self) -> Codex

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Codex

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

Formats the value using the given formatter.

impl From<Codex> for CloudProvider

fn from(client: Codex) -> Self

Converts to this type from the input type.

impl LanguageModel for Codex

type Error = CodexError

The error type returned by this language model.

fn respond( &self, request: LLMRequest, ) -> impl Stream<Item = Result<Event, <Codex as LanguageModel>::Error>> + Send

Generates a streaming response to a conversation.

fn profile( &self, ) -> impl Future<Output = Result<Profile, <Codex as LanguageModel>::Error>> + Send

Returns model profile and capabilities.

fn respond_with_tools( &self, request: LLMRequestWithTools<'_>, ) -> impl Stream<Item = Result<Event, Self::Error>> + Send

Generates a streaming response with a mutable tool registry.

fn generate<T>( &self, request: LLMRequest, ) -> impl Future<Output = Result<T, GenerateError<Self::Error>>> + Send

where T: JsonSchema + DeserializeOwned + 'static,

Generates structured output conforming to JSON schema.

fn complete( &self, prefix: &str, ) -> impl Stream<Item = Result<Event, Self::Error>> + Send

Completes given text prefix.

fn summarize( &self, text: &str, ) -> impl Stream<Item = Result<Event, Self::Error>> + Send

Summarizes text.

fn categorize<T>( &self, text: &str, ) -> impl Future<Output = Result<T, GenerateError<Self::Error>>> + Send

where T: JsonSchema + DeserializeOwned + 'static,

Categorizes text.

fn retry_policy(&self) -> RetryPolicy

How a request to this model that failed with a retryable failure is sent again.