Struct SemanticCachePutOpts 

pub struct SemanticCachePutOpts {
    pub content_type: String,
    pub ttl_secs: Option<u64>,
    pub cost_hint_ms: Option<u32>,
    pub model: String,
}

Options for crate::Mnemo::cache_put_semantic. Same as CachePutOpts plus a required model string — a hit from a different embedding model’s cache is a semantics bug, not a win, so the engine forces callers to declare the model and matches it on lookup.

The vector itself is a separate argument to cache_put_semantic (not inside opts) so callers who already own the vector don’t have to .clone() it into the struct.

Fields

content_type: String

Free-form content-type label recorded on the entry.

ttl_secs: Option<u64>

TTL in seconds. Omit for no expiry.

cost_hint_ms: Option<u32>

Cost hint recorded on the entry (see CachePutOpts::cost_hint_ms).

model: String

Embedding model identifier. Matched exactly on lookup; a different model’s cache is invisible to this query. Convention: "text-embedding-3-small", "bge-large-en-v1.5", etc.

Implementations

impl SemanticCachePutOpts

pub fn new(model: impl Into<String>) -> Self

Construct with just the required model; all other fields default (content_type = “text”, no TTL, no cost hint).

Trait Implementations

impl Clone for SemanticCachePutOpts

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for SemanticCachePutOpts

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

Formats the value using the given formatter.