pub struct InferenceRequest {
pub id: RequestId,
pub prompt: String,
pub model_id: ModelId,
pub sampling_params: SamplingParams,
pub stream: bool,
pub priority: Priority,
pub client_id: Option<ClientId>,
pub session_id: Option<SessionId>,
pub created_at: DateTime<Utc>,
pub metadata: HashMap<String, Value>,
}Expand description
Inference request
Fields§
§id: RequestIdUnique request identifier
prompt: StringInput prompt text
model_id: ModelIdModel to use for inference
sampling_params: SamplingParamsSampling parameters
stream: boolWhether to stream response
priority: PriorityRequest priority
client_id: Option<ClientId>Client identifier
session_id: Option<SessionId>Session identifier for stateful interactions
created_at: DateTime<Utc>Request creation timestamp
metadata: HashMap<String, Value>Additional metadata
Implementations§
Source§impl InferenceRequest
impl InferenceRequest
Sourcepub fn new(
prompt: impl Into<String>,
model_id: impl Into<ModelId>,
) -> InferenceRequest
pub fn new( prompt: impl Into<String>, model_id: impl Into<ModelId>, ) -> InferenceRequest
Create a new inference request
Sourcepub fn with_sampling_params(self, params: SamplingParams) -> InferenceRequest
pub fn with_sampling_params(self, params: SamplingParams) -> InferenceRequest
Set sampling parameters
Sourcepub fn with_stream(self, stream: bool) -> InferenceRequest
pub fn with_stream(self, stream: bool) -> InferenceRequest
Enable streaming
Sourcepub fn with_priority(self, priority: Priority) -> InferenceRequest
pub fn with_priority(self, priority: Priority) -> InferenceRequest
Set priority
Sourcepub fn with_client_id(self, client_id: impl Into<ClientId>) -> InferenceRequest
pub fn with_client_id(self, client_id: impl Into<ClientId>) -> InferenceRequest
Set client ID
Sourcepub fn with_session_id(self, session_id: SessionId) -> InferenceRequest
pub fn with_session_id(self, session_id: SessionId) -> InferenceRequest
Set session ID
Sourcepub fn with_metadata(
self,
key: impl Into<String>,
value: Value,
) -> InferenceRequest
pub fn with_metadata( self, key: impl Into<String>, value: Value, ) -> InferenceRequest
Add metadata
Trait Implementations§
Source§impl Clone for InferenceRequest
impl Clone for InferenceRequest
Source§fn clone(&self) -> InferenceRequest
fn clone(&self) -> InferenceRequest
Returns a duplicate of the value. Read more
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Debug for InferenceRequest
impl Debug for InferenceRequest
Source§impl<'de> Deserialize<'de> for InferenceRequest
impl<'de> Deserialize<'de> for InferenceRequest
Source§fn deserialize<__D>(
__deserializer: __D,
) -> Result<InferenceRequest, <__D as Deserializer<'de>>::Error>where
__D: Deserializer<'de>,
fn deserialize<__D>(
__deserializer: __D,
) -> Result<InferenceRequest, <__D as Deserializer<'de>>::Error>where
__D: Deserializer<'de>,
Deserialize this value from the given Serde deserializer. Read more
Source§impl Serialize for InferenceRequest
impl Serialize for InferenceRequest
Source§fn serialize<__S>(
&self,
__serializer: __S,
) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>where
__S: Serializer,
fn serialize<__S>(
&self,
__serializer: __S,
) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>where
__S: Serializer,
Serialize this value into the given Serde serializer. Read more
Auto Trait Implementations§
impl Freeze for InferenceRequest
impl RefUnwindSafe for InferenceRequest
impl Send for InferenceRequest
impl Sync for InferenceRequest
impl Unpin for InferenceRequest
impl UnsafeUnpin for InferenceRequest
impl UnwindSafe for InferenceRequest
Blanket Implementations§
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