pub struct Client { /* private fields */ }
Implementations§
Source§impl Client
impl Client
Sourcepub fn builder(
auth: impl Into<AzureOpenAIAuth>,
endpoint: &str,
) -> ClientBuilder<'_>
pub fn builder( auth: impl Into<AzureOpenAIAuth>, endpoint: &str, ) -> ClientBuilder<'_>
Create a new Azure OpenAI client builder.
§Example
use rig::providers::azure::{ClientBuilder, self};
// Initialize the Azure OpenAI client
let azure = Client::builder("your-azure-api-key", "https://{your-resource-name}.openai.azure.com")
.build()
Trait Implementations§
Source§impl CompletionClient for Client
impl CompletionClient for Client
Source§fn completion_model(&self, model: &str) -> CompletionModel
fn completion_model(&self, model: &str) -> CompletionModel
Create a completion model with the given name.
§Example
use rig::providers::azure::{Client, self};
// Initialize the Azure OpenAI client
let azure = Client::new("YOUR_API_KEY", "YOUR_API_VERSION", "YOUR_ENDPOINT");
let gpt4 = azure.completion_model(azure::GPT_4);
Source§type CompletionModel = CompletionModel
type CompletionModel = CompletionModel
The type of CompletionModel used by the client.
Source§fn agent(&self, model: &str) -> AgentBuilder<Self::CompletionModel>
fn agent(&self, model: &str) -> AgentBuilder<Self::CompletionModel>
Create an agent builder with the given completion model. Read more
Source§fn extractor<T: JsonSchema + for<'a> Deserialize<'a> + Serialize + Send + Sync>(
&self,
model: &str,
) -> ExtractorBuilder<T, Self::CompletionModel>
fn extractor<T: JsonSchema + for<'a> Deserialize<'a> + Serialize + Send + Sync>( &self, model: &str, ) -> ExtractorBuilder<T, Self::CompletionModel>
Create an extractor builder with the given completion model.
Source§impl EmbeddingsClient for Client
impl EmbeddingsClient for Client
Source§fn embedding_model(&self, model: &str) -> EmbeddingModel
fn embedding_model(&self, model: &str) -> EmbeddingModel
Create an embedding model with the given name.
Note: default embedding dimension of 0 will be used if model is not known.
If this is the case, it’s better to use function embedding_model_with_ndims
§Example
use rig::providers::azure::{Client, self};
// Initialize the Azure OpenAI client
let azure = Client::new("YOUR_API_KEY", "YOUR_API_VERSION", "YOUR_ENDPOINT");
let embedding_model = azure.embedding_model(azure::TEXT_EMBEDDING_3_LARGE);
Source§fn embedding_model_with_ndims(
&self,
model: &str,
ndims: usize,
) -> EmbeddingModel
fn embedding_model_with_ndims( &self, model: &str, ndims: usize, ) -> EmbeddingModel
Create an embedding model with the given name and the number of dimensions in the embedding generated by the model.
§Example
use rig::providers::azure::{Client, self};
// Initialize the Azure OpenAI client
let azure = Client::new("YOUR_API_KEY", "YOUR_API_VERSION", "YOUR_ENDPOINT");
let embedding_model = azure.embedding_model("model-unknown-to-rig", 3072);
Source§type EmbeddingModel = EmbeddingModel
type EmbeddingModel = EmbeddingModel
The type of EmbeddingModel used by the Client
Source§fn embeddings<D: Embed>(
&self,
model: &str,
) -> EmbeddingsBuilder<Self::EmbeddingModel, D>
fn embeddings<D: Embed>( &self, model: &str, ) -> EmbeddingsBuilder<Self::EmbeddingModel, D>
Create an embedding builder with the given embedding model. Read more
Source§fn embeddings_with_ndims<D: Embed>(
&self,
model: &str,
ndims: usize,
) -> EmbeddingsBuilder<Self::EmbeddingModel, D>
fn embeddings_with_ndims<D: Embed>( &self, model: &str, ndims: usize, ) -> EmbeddingsBuilder<Self::EmbeddingModel, D>
Create an embedding builder with the given name and the number of dimensions in the embedding generated by the model. Read more
Source§impl ProviderClient for Client
impl ProviderClient for Client
Source§fn from_env() -> Self
fn from_env() -> Self
Create a new Azure OpenAI client from the AZURE_API_KEY
or AZURE_TOKEN
, AZURE_API_VERSION
, and AZURE_ENDPOINT
environment variables.
fn from_val(input: ProviderValue) -> Self
Source§fn boxed(self) -> Box<dyn ProviderClient>where
Self: Sized + 'static,
fn boxed(self) -> Box<dyn ProviderClient>where
Self: Sized + 'static,
A helper method to box the client.
Source§fn from_env_boxed<'a>() -> Box<dyn ProviderClient + 'a>where
Self: Sized + 'a,
fn from_env_boxed<'a>() -> Box<dyn ProviderClient + 'a>where
Self: Sized + 'a,
Create a boxed client from the process’s environment.
Panics if an environment is improperly configured.
Source§fn from_val_boxed<'a>(input: ProviderValue) -> Box<dyn ProviderClient + 'a>where
Self: Sized + 'a,
fn from_val_boxed<'a>(input: ProviderValue) -> Box<dyn ProviderClient + 'a>where
Self: Sized + 'a,
Create a boxed client from the process’s environment.
Panics if an environment is improperly configured.
Source§impl TranscriptionClient for Client
impl TranscriptionClient for Client
Source§fn transcription_model(&self, model: &str) -> TranscriptionModel
fn transcription_model(&self, model: &str) -> TranscriptionModel
Create a transcription model with the given name.
§Example
use rig::providers::azure::{Client, self};
// Initialize the Azure OpenAI client
let azure = Client::new("YOUR_API_KEY", "YOUR_API_VERSION", "YOUR_ENDPOINT");
let whisper = azure.transcription_model("model-unknown-to-rig");
Source§type TranscriptionModel = TranscriptionModel
type TranscriptionModel = TranscriptionModel
The type of TranscriptionModel used by the Client
Auto Trait Implementations§
impl Freeze for Client
impl !RefUnwindSafe for Client
impl Send for Client
impl Sync for Client
impl Unpin for Client
impl !UnwindSafe for Client
Blanket Implementations§
Source§impl<T> AsCompletion for Twhere
T: CompletionClientDyn + Clone + 'static,
impl<T> AsCompletion for Twhere
T: CompletionClientDyn + Clone + 'static,
fn as_completion(&self) -> Option<Box<dyn CompletionClientDyn>>
Source§impl<T> AsEmbeddings for Twhere
T: EmbeddingsClientDyn + Clone + 'static,
impl<T> AsEmbeddings for Twhere
T: EmbeddingsClientDyn + Clone + 'static,
fn as_embeddings(&self) -> Option<Box<dyn EmbeddingsClientDyn>>
Source§impl<T> AsTranscription for Twhere
T: TranscriptionClientDyn + Clone + 'static,
impl<T> AsTranscription for Twhere
T: TranscriptionClientDyn + Clone + 'static,
fn as_transcription(&self) -> Option<Box<dyn TranscriptionClientDyn>>
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<T, M, R> CompletionClientDyn for Twhere
T: CompletionClient<CompletionModel = M>,
M: CompletionModel<StreamingResponse = R> + 'static,
R: Clone + Unpin + GetTokenUsage + 'static,
impl<T, M, R> CompletionClientDyn for Twhere
T: CompletionClient<CompletionModel = M>,
M: CompletionModel<StreamingResponse = R> + 'static,
R: Clone + Unpin + GetTokenUsage + 'static,
Source§fn completion_model<'a>(&self, model: &str) -> Box<dyn CompletionModelDyn + 'a>
fn completion_model<'a>(&self, model: &str) -> Box<dyn CompletionModelDyn + 'a>
Create a completion model with the given name.
Source§fn agent<'a>(&self, model: &str) -> AgentBuilder<CompletionModelHandle<'a>>
fn agent<'a>(&self, model: &str) -> AgentBuilder<CompletionModelHandle<'a>>
Create an agent builder with the given completion model.
Source§impl<T, M> EmbeddingsClientDyn for Twhere
T: EmbeddingsClient<EmbeddingModel = M>,
M: EmbeddingModel + 'static,
impl<T, M> EmbeddingsClientDyn for Twhere
T: EmbeddingsClient<EmbeddingModel = M>,
M: EmbeddingModel + 'static,
Source§fn embedding_model<'a>(&self, model: &str) -> Box<dyn EmbeddingModelDyn + 'a>
fn embedding_model<'a>(&self, model: &str) -> Box<dyn EmbeddingModelDyn + 'a>
Create an embedding model with the given name.
Note: default embedding dimension of 0 will be used if model is not known.
If this is the case, it’s better to use function
embedding_model_with_ndims
Source§fn embedding_model_with_ndims<'a>(
&self,
model: &str,
ndims: usize,
) -> Box<dyn EmbeddingModelDyn + 'a>
fn embedding_model_with_ndims<'a>( &self, model: &str, ndims: usize, ) -> Box<dyn EmbeddingModelDyn + 'a>
Create an embedding model with the given name and the number of dimensions in the embedding generated by the model.
Source§impl<T> Instrument for T
impl<T> Instrument for T
Source§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
Source§fn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
Source§impl<T> PolicyExt for Twhere
T: ?Sized,
impl<T> PolicyExt for Twhere
T: ?Sized,
Source§impl<T, M> TranscriptionClientDyn for Twhere
T: TranscriptionClient<TranscriptionModel = M>,
M: TranscriptionModel + 'static,
impl<T, M> TranscriptionClientDyn for Twhere
T: TranscriptionClient<TranscriptionModel = M>,
M: TranscriptionModel + 'static,
Source§fn transcription_model<'a>(
&self,
model: &str,
) -> Box<dyn TranscriptionModelDyn + 'a>
fn transcription_model<'a>( &self, model: &str, ) -> Box<dyn TranscriptionModelDyn + 'a>
Create a transcription model with the given name.