Files
engine/docs/EMBEDDINGS.md
zeekay 69a6e5fe83 merge: upstream mistral.rs 366db965f
Conflicts resolved:
- Cargo.toml: bumped workspace to 0.8.1, kept hanzo-ml candle paths and hanzoai URLs
- pipeline/mod.rs: adopted upstream Multimodal* renames + Gemma4Loader, kept BertEmbeddingLoader re-export
- docs/*.md, mistralrs*/README.md: took upstream content, applied Hanzo branding
- CLAUDE.md, AGENTS.md: kept HEAD (AGENTS.md is symlink to LLM.md)
- Cargo.lock: regenerated against new workspace
2026-05-12 12:00:37 -07:00

882 B
Raw Permalink Blame History

Embeddings Overview

Hanzo Engine can load embedding models alongside chat, multimodal, diffusion, and speech workloads. Embedding models produce dense vector representations that you can use for similarity search, clustering, reranking, and other semantic tasks.

Supported models

Model Notes Documentation
EmbeddingGemma Google’s multilingual embedding model. EMBEDDINGGEMMA.md
Qwen3 Embedding Qwen’s general-purpose embedding encoder. QWEN3_EMBEDDING.md

Have another embedding model you would like supported? Open an issue with the model ID and configuration.

Usage overview

  1. Choose a model from the table above.
  2. Load it through one of our APIs:
    • CLI/HTTP
    • Python
    • Rust

Detailed examples for each model live in their dedicated documentation pages.