Struct CpuBackend 

pub struct CpuBackend { /* private fields */ }

CPU backend — wraps the existing v0.7.0 inference path (embeddings::Embedder + llm::OllamaClient). This is a thin adapter; the underlying types are unchanged.

Implementations

impl CpuBackend

pub fn new(embedder: Arc<dyn Embed>, llm: Option<Arc<OllamaClient>>) -> Self

Construct a CPU backend from existing handles.

pub fn with_attested_weights(self, attested: AttestedWeights) -> Self

Pin an attested-weights record (issue #654). Returns a new backend wrapping the same handles. The hash is NOT recomputed here — the caller pre-computes it via compute_attested_weights at model-load time so the verify_attested_weights gate can refuse to serve from a tampered file.

Trait Implementations

impl InferenceBackend for CpuBackend

fn embed(&self, text: &str) -> Result<Vec<f32>>

Produce a single embedding vector for text.

fn chat(&self, prompt: &str) -> Result<String>

Generate a chat completion for prompt. Default system prompt is None (implementor decides); use a concrete backend’s API for system-prompt support.

fn attested_weights(&self) -> Option<AttestedWeights>

Return the loaded model’s SHA-256 + optional signature for issue #654 supply-chain attestation. None if the backend has no on-disk weights to attest (e.g. a network-only client).