Concepts
Concepts
Understand the ideas behind dish-embed. These pages explain how to think about the API without requiring ML expertise.
- How Food Embeddings Work - What embeddings are and why food needs specialized ones
- Matryoshka Dimensions - Trade-offs between embedding size, quality, and cost
- Built-in Preprocessing - Noise stripping and normalization you get for free
- Dietary Detection - How veg/non-veg signals are identified and enforced
DishEmbedClient Reference
Method reference for DishEmbedClient. Covers health, embed, search, match, dedup, classify, suggest, report, and balance with parameters and return types.
How Food Embeddings Work
How food embeddings work and why generic models fail on menus. Covers cosine similarity ranges, transliteration, noise, and cross-lingual mapping.