Skip to main content

Module fastembed_embedder

coding_agent_search::search

Module fastembed_embedder 

Source
Expand description

FastEmbed-based ML embedders.

Loads local ONNX model + tokenizer bundles and produces semantic embeddings. This implementation never downloads model assets; it expects the model files to be present on disk and returns a clear error when they are missing.

Supports multiple models:

  • MiniLM (baseline)
  • EmbeddingGemma (bake-off candidate)
  • Qwen3-Embedding (bake-off candidate)
  • ModernBERT-embed (bake-off candidate)
  • Snowflake Arctic Embed (bake-off candidate)
  • Nomic Embed Text (bake-off candidate)

Structs§

FastEmbedder
FastEmbed-backed semantic embedder.
OnnxEmbedderConfig
Configuration for loading an ONNX embedder.

Constants§

MODEL_ONNX_LEGACY
MODEL_ONNX_SUBDIR

Functions§

model_dir_override