Struct FoundryChatClient 

pub struct FoundryChatClient { /* private fields */ }

A ChatClient for the Azure AI Foundry project Responses API.

A thin wrapper around AzureOpenAIResponsesClient: constructs it against the Foundry project endpoint and model (deployment) with without_api_version applied (see the module docs). All request building, response parsing, SSE streaming, and HTTP-error classification are reused verbatim from that client — this type adds nothing beyond Foundry-shaped constructors and a plain delegating ChatClient impl.

Implementations

impl FoundryChatClient

pub fn new( endpoint: impl Into<String>, model: impl Into<String>, api_key: impl Into<String>, ) -> Self

Create a client authenticating with a static API key (api-key header).

pub fn with_token_credential( endpoint: impl Into<String>, model: impl Into<String>, credential: Arc<dyn TokenCredential>, ) -> Self

Create a client authenticating via a TokenCredential (Microsoft Entra ID Authorization: Bearer <token>) — the primary Foundry auth path. The credential should already be scoped to FOUNDRY_SCOPE, e.g. AzureCliCredential::new(FOUNDRY_SCOPE).

pub fn from_env() -> Result<Self>

Build a client from environment variables.

Reads FOUNDRY_ENDPOINT (alias FOUNDRY_PROJECT_ENDPOINT) and FOUNDRY_MODEL — the FOUNDRY_*/model naming mirrors upstream’s shift away from the old AZURE_AI_*/model_deployment_name convention. When FOUNDRY_API_KEY is set it authenticates with that key; otherwise it falls back to a DefaultAzureCredential scoped to FOUNDRY_SCOPE (a chain that tries a managed identity, then client-secret env vars, then the Azure CLI).

Errors

Error::Configuration when neither endpoint variable, or FOUNDRY_MODEL, is set.

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

Override the full base URL requests are built against — see AzureOpenAIResponsesClient::with_base_url.

pub fn endpoint(&self) -> &str

The Foundry project endpoint this client targets.

pub fn model_name(&self) -> &str

The model deployment name this client targets.

Trait Implementations

impl ChatClient for FoundryChatClient

fn get_response<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, options: ChatOptions, ) -> Pin<Box<dyn Future<Output = Result<ChatResponse>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Get a complete (non-streaming) response.

fn get_streaming_response<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, options: ChatOptions, ) -> Pin<Box<dyn Future<Output = Result<ChatStream>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Get a streaming response as a sequence of updates.

fn model(&self) -> Option<&str>

The default model id for this client, if any.

impl Clone for FoundryChatClient

fn clone(&self) -> FoundryChatClient

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FoundryChatClient

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

Formats the value using the given formatter.