Struct OpenAiAdapter 

pub struct OpenAiAdapter { /* private fields */ }

Thin wrapper that wires the HTTP client [OpenAiClient] into a value that implements [artificial_core::backend::Backend].

Think of it as the service locator for the OpenAI back-end:

• stores the API key (and optionally a custom base URL in the future),
• owns a shareable, connection-pooled reqwest::Client,
• provides a fluent OpenAiAdapterBuilder so callers don’t have to juggle Option<String> manually.

The type itself purposefully exposes no additional methods—all user- facing functionality sits on the generic artificial_core::ArtificialClient once the adapter is plugged in.

Trait Implementations

impl ChatCompletionProvider for OpenAiAdapter

type Message = ChatCompletionMessage

Chat message type consumed by this backend.

fn chat_complete<'s, M>( &'s self, params: ChatCompleteParameters<M>, ) -> Pin<Box<dyn Future<Output = Result<GenericChatCompletionResponse<GenericMessage>>> + Send + 's>>

where M: Into<Self::Message> + Clone + Send + Sync + 's,

Execute the chat prompt and deserialize the provider’s reply into P::Output.

impl PromptExecutionProvider for OpenAiAdapter

Implementation of [ChatCompletionProvider] for the OpenAiAdapter.

The type is only a thin glue layer—almost all heavy lifting is done by the inner OpenAiClient (HTTP) and the adapter’s config (API key, base URL, …).

Responsibilities:

1. Convert the generic prompt into OpenAI‐compatible chat messages.
2. Enrich the request with a JSON Schema derived from Prompt::Output.
3. Call the /v1/chat/completions endpoint and bubble up transport errors.
4. Validate & deserialize the returned JSON into Prompt::Output.

The implementation purposefully rejects any streaming or multi-choice responses for now; this keeps the surface minimal and makes error handling easier to reason about.

type Message = ChatCompletionMessage

Provider-specific chat message type.

fn prompt_execute<'a, 'p, P>( &'a self, prompt: P, ) -> Pin<Box<dyn Future<Output = Result<GenericChatCompletionResponse<P::Output>>> + Send + 'p>>

where P: PromptTemplate + Send + Sync + 'p, <P as IntoPrompt>::Message: Into<Self::Message>, 'a: 'p,

Perform a non-streaming chat completion and deserialize the result.

The method is object-safe by returning a boxed Future rather than using async/await syntax directly.

impl StreamingChatProvider for OpenAiAdapter

type Delta<'s> = Pin<Box<dyn Stream<Item = Result<String, ArtificialError>> + Send + 's>> where Self: 's

The item type returned on the stream. For now it is plain UTF-8 text chunks, but back-ends are free to wrap it in richer enums if needed.

fn chat_complete_stream<'s, M>( &'s self, params: ChatCompleteParameters<M>, ) -> Self::Delta<'s>

where M: Into<Self::Message> + Clone + Send + Sync + 's,

Start a streaming chat completion.

impl StreamingEventsProvider for OpenAiAdapter

type EventStream<'s> = Pin<Box<dyn Stream<Item = Result<StreamEvent, ArtificialError>> + Send + 's>> where Self: 's

fn chat_complete_events_stream<'s, M>( &'s self, params: ChatCompleteParameters<M>, ) -> Self::EventStream<'s>

where M: Into<Self::Message> + Clone + Send + Sync + 's,