Crate orbok_embed 

orbok-embed

Embedding backend factory (RFC-021). Selects and constructs a local EmbeddingModel implementation from an EmbeddingModelConfig.

Backend selection

Backend	Feature flag	Notes
Mock	always	Deterministic 8-dim, test-only
CandleCpu/CandleCuda	candle	HuggingFace candle runtime
OnnxRuntime	tract	Tract ONNX runtime (pure Rust)

Without the candle or tract feature, create_embedding_model returns OrbokError::Cache when called with a non-mock backend. Enable the feature at build time and provide model weights to use real inference:

cargo build --features orbok-embed/tract

RFC-021 model comparison

Evaluated models for the default recommendation:

Model	Dim	Size	License	Japanese	Notes
all-MiniLM-L6-v2	384	~22 MB	Apache 2.0	Weak	Fast, widely supported
nomic-embed-text-v1.5	768	~137 MB	Apache 2.0	Moderate	Good multilingual
multilingual-e5-small	384	~118 MB	MIT	Strong	100 languages including Japanese

Recommended default (RFC-021): multilingual-e5-small for orbok’s mixed Japanese-English use case (RFC-014). The 384-dim vectors keep storage manageable while providing genuine multilingual recall. Users can override via EmbeddingModelConfig.

Constants

RECOMMENDED_HF_MODEL_ID

HuggingFace model ID for manual download reference.

RECOMMENDED_MODEL_DIMENSION

RECOMMENDED_MODEL_MAX_SEQ_LEN

RECOMMENDED_MODEL_NAME

Recommended default model configuration for new installations.

RECOMMENDED_MODEL_VERSION

RECOMMENDED_ONNX_FILE

Expected ONNX weights file name once downloaded.

Functions

create_embedding_model

Construct an embedding model from configuration.

recommended_config

Build a default configuration for the recommended model.