Crate rightkit_embed 

Local embeddings and a persistent cosine vector store.

Feature boundaries: inference (ONNX text embedder) and vector (SQLite-backed cosine store). Both are default-on; a vector-only build does not pull ort or tokenizers.

Structs

AcceleratorParity

Result of the load-time vector parity check an accelerator passed; see Embedder::accelerator_parity.

Embedder

EmbedderConfig

Nearest

VectorStore

Enums

EmbedError

ExecutionProvider

Where inference runs.

VectorError

Constants

ACCELERATOR_PARITY_MIN_COSINE

An accelerator is admitted only if every parity prompt’s native-dimension vector has at least this cosine similarity to the CPU provider’s vector for the same prompt. Two correct runs of the same Q4 graph agree at about 0.999; a DirectML run of EmbeddingGemma 2 Q4 measured 0.58-0.72.

DEFAULT_MAX_BATCH

Default rows per ONNX call for embed_batch / embed_query_batch.

DEFAULT_VECTOR_DIM

EMBEDDINGGEMMA2_MODEL_ID

EmbeddingGemma 2 text-only Q4 export (b64, accuracy level 4). Selected when the model directory’s top-level config.json model_type is embedding_gemma2.

EMBEDDINGGEMMA_MODEL_ID

Functions

cosine_similarity

truncate_and_normalize