pub struct ChatInput {
pub model: String,
pub messages: Vec<ChatMessage>,
pub tools: Vec<Tool>,
pub temperature: Option<f64>,
pub slot: Option<u32>,
pub max_tokens: Option<u32>,
}Fields§
§model: String§messages: Vec<ChatMessage>§tools: Vec<Tool>§temperature: Option<f64>§slot: Option<u32>llama.cpp request slot to run in (id_slot), so its KV cache can be saved and
restored later. Other backends ignore it.
max_tokens: Option<u32>Most tokens to generate for this reply (llama.cpp max_tokens, Ollama num_predict).
None: the server’s default, which may run to the end of the context.
Trait Implementations§
Source§impl<'de> Deserialize<'de> for ChatInput
impl<'de> Deserialize<'de> for ChatInput
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
Auto Trait Implementations§
impl Forget for ChatInput
impl Freeze for ChatInput
impl RefUnwindSafe for ChatInput
impl Send for ChatInput
impl Sync for ChatInput
impl Unpin for ChatInput
impl UnsafeUnpin for ChatInput
impl UnwindSafe for ChatInput
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