Crate orbok_models 

orbok-models

Local AI model vocabulary (RFC-012). Milestone M1–M6 only needs the shared types and the “what is available” summary the UI shows; the install/locate/validate workflow lands in M12.

Privacy rule carried from the requirements: model download is the only network operation orbok may ever perform, it is explicit, and it never involves document contents.

Structs

MockEmbeddingModel

Deterministic 8-dimensional mock embedding model.

MockReranker

Deterministic mock reranker: scores by passage length (longer = more informative). Useful for pipeline testing without an ML model.

RerankCandidate

A candidate document passed to the reranker.

RerankScore

Per-candidate rerank score (higher = more relevant).

VectorCandidate

A vector search candidate (RFC-008 §13).

Enums

ModelRole

Model roles (catalog models.role).

ModelStatus

Model availability (catalog models.status).

SearchCapability

Search capability derived from model availability. Keyword search never depends on models (RFC-007: works with zero models installed).

Traits

CrossEncoderReranker

Optional local cross-encoder reranker (RFC-010 §5).

EmbeddingModel

Local embedding model abstraction (RFC-008 §6).

Functions

blob_to_vec

Deserialize from BLOB bytes; returns None on length mismatch.

cosine_similarity

Compute cosine similarity between two L2-normalized vectors.

l2_normalize

L2-normalize a vector in-place. No-op for the zero vector.

search_capability

Derive the capability shown in the UI from model statuses.

vec_to_blob

Serialize a vector to little-endian bytes for BLOB storage (RFC-008 §12.1 “sqlite_blob with FP32”).