pub struct CreateCompletionRequest {Show 19 fields
pub model: String,
pub prompt: Prompt,
pub prompt_embeds: Option<String>,
pub suffix: Option<String>,
pub max_tokens: Option<u32>,
pub temperature: Option<f32>,
pub top_p: Option<f32>,
pub n: Option<u8>,
pub stream: Option<bool>,
pub stream_options: Option<ChatCompletionStreamOptions>,
pub logprobs: Option<u8>,
pub echo: Option<bool>,
pub stop: Option<Stop>,
pub presence_penalty: Option<f32>,
pub frequency_penalty: Option<f32>,
pub best_of: Option<u8>,
pub logit_bias: Option<HashMap<String, Value>>,
pub user: Option<String>,
pub seed: Option<i64>,
}Expand description
Completion request with inference-serving extensions.
Extends upstream CreateCompletionRequest with:
prompt_embeds: base64-encoded PyTorch tensor for pre-computed embeddingsecho: strict bool validation (rejects integers/strings)stream_options: uses our extendedChatCompletionStreamOptions(withcontinuous_usage_stats)
Fields§
§model: String§prompt: Prompt§prompt_embeds: Option<String>Base64-encoded PyTorch tensor containing pre-computed embeddings. At least one of prompt or prompt_embeds is required.
suffix: Option<String>§max_tokens: Option<u32>§temperature: Option<f32>§top_p: Option<f32>§n: Option<u8>§stream: Option<bool>§stream_options: Option<ChatCompletionStreamOptions>§logprobs: Option<u8>§echo: Option<bool>Echo back the prompt in addition to the completion. Strict bool validation – rejects integers and strings.
stop: Option<Stop>§presence_penalty: Option<f32>§frequency_penalty: Option<f32>§best_of: Option<u8>§logit_bias: Option<HashMap<String, Value>>§user: Option<String>§seed: Option<i64>Trait Implementations§
Source§impl Clone for CreateCompletionRequest
impl Clone for CreateCompletionRequest
Source§impl ComposeSchema for CreateCompletionRequest
Available on crate feature protocol-schema only.
impl ComposeSchema for CreateCompletionRequest
Available on crate feature
protocol-schema only.Source§impl Debug for CreateCompletionRequest
impl Debug for CreateCompletionRequest
Source§impl Default for CreateCompletionRequest
impl Default for CreateCompletionRequest
Source§impl<'de> Deserialize<'de> for CreateCompletionRequest
impl<'de> Deserialize<'de> for CreateCompletionRequest
Source§fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
Deserialize this value from the given Serde deserializer. Read more
Source§impl PartialEq for CreateCompletionRequest
impl PartialEq for CreateCompletionRequest
Source§impl Serialize for CreateCompletionRequest
impl Serialize for CreateCompletionRequest
impl StructuralPartialEq for CreateCompletionRequest
Source§impl ToSchema for CreateCompletionRequest
Available on crate feature protocol-schema only.
impl ToSchema for CreateCompletionRequest
Available on crate feature
protocol-schema only.Auto Trait Implementations§
impl Freeze for CreateCompletionRequest
impl RefUnwindSafe for CreateCompletionRequest
impl Send for CreateCompletionRequest
impl Sync for CreateCompletionRequest
impl Unpin for CreateCompletionRequest
impl UnsafeUnpin for CreateCompletionRequest
impl UnwindSafe for CreateCompletionRequest
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