Struct VertexProvider 

pub struct VertexProvider { /* private fields */ }

Available on crate feature vertex only.

Google Vertex AI LLM provider.

Uses the same Gemini request/response format as GeminiProvider but authenticates via OAuth2 Bearer tokens and routes through the Vertex AI regional endpoint.

Claude models are also supported — the provider detects the publisher from the model name and uses the appropriate API format automatically.

Implementations

impl VertexProvider

pub fn new( access_token: String, project_id: String, region: String, model: String, ) -> VertexProvider

Create a new Vertex AI provider with full control over all parameters.

pub fn flash( access_token: String, project_id: String, region: String, ) -> VertexProvider

Create a provider using Gemini 3 Flash Preview on Vertex AI.

pub fn pro( access_token: String, project_id: String, region: String, ) -> VertexProvider

Create a provider using Gemini 3.1 Pro Preview on Vertex AI.

pub const fn with_thinking(self, thinking: ThinkingConfig) -> VertexProvider

Set the provider-owned thinking configuration for this model.

Trait Implementations

impl Clone for VertexProvider

fn clone(&self) -> VertexProvider

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl LlmProvider for VertexProvider

fn chat<'life0, 'async_trait>( &'life0 self, request: ChatRequest, ) -> Pin<Box<dyn Future<Output = Result<ChatOutcome, Error>> + Send + 'async_trait>>

where 'life0: 'async_trait, VertexProvider: 'async_trait,

Non-streaming chat completion.

fn chat_stream( &self, request: ChatRequest, ) -> Pin<Box<dyn Stream<Item = Result<StreamDelta, Error>> + Send + '_>>

Streaming chat completion.

fn validate_thinking_config( &self, thinking: Option<&ThinkingConfig>, ) -> Result<(), Error>

Validate a thinking configuration against the provider/model capabilities.

fn model(&self) -> &str

fn provider(&self) -> &'static str

fn configured_thinking(&self) -> Option<&ThinkingConfig>

Provider-owned thinking configuration, if any.

fn default_max_tokens(&self) -> u32

Default maximum output tokens for this provider/model when the caller does not explicitly override AgentConfig.max_tokens.

fn capabilities(&self) -> Option<&'static ModelCapabilities>

Canonical capability metadata for this provider/model, if known.

fn resolve_thinking_config( &self, request_thinking: Option<&ThinkingConfig>, ) -> Result<Option<ThinkingConfig>, Error>

Resolve the effective thinking configuration for a request.

fn structured_output_support(&self) -> StructuredOutputSupport

How this provider satisfies a structured-output (ResponseFormat) request.