Struct LlamaResponse 

pub struct LlamaResponse {
    pub model: String,
    pub created_at: String,
    pub message: Message,
    pub done_reason: String,
    pub done: bool,
    pub total_duration: u64,
    pub load_duration: u64,
    pub prompt_eval_count: u64,
    pub prompt_eval_duration: u64,
    pub eval_count: u64,
    pub eval_duration: u64,
}

Response structure from Ollama LLM requests.

Contains the generated content along with metadata about the generation process including timing information.

Fields

model: String

Name of the model used

created_at: String

Timestamp of response creation

message: Message

Generated message content

done_reason: String

Reason for completion

done: bool

Whether generation is complete

total_duration: u64

Total processing time in microseconds

load_duration: u64

Model loading time in microseconds

prompt_eval_count: u64

Number of tokens in the prompt

prompt_eval_duration: u64

Time spent evaluating prompt in microseconds

eval_count: u64

Number of generated tokens

eval_duration: u64

Time spent generating tokens in microseconds

Trait Implementations

impl Debug for LlamaResponse

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for LlamaResponse

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for LlamaResponse

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.